Search Results for author:
Found 390 papers, 173 papers with code
数据标注方法比较研究:以依存句法树标注为例(Comparison Study on Data Annotation Approaches: Dependency Tree Annotation as Case Study)
“数据标注最重要的考虑因素是数据的质量和标注代价。我们调研发现自然语言处理领域的数据标注工作通常采用机标人校的标注方法以降低代价;同时, 很少有工作严格对比不同标注方法, 以探讨标注方法对标注质量和代价的影响。该文借助一个成熟的标注团队, 以依存句法数据标注为案例, 实验对比了机标人校、双人独立标注、及本文通过融合前两种方法所新提出的人机独立标注方法, 得到了一些初步的结论。”
Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis
This essentially allows the framework to understand the appropriate graph structures for learning intricate relations among different modalities.
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task.
HW-TSC’s Submissions to the WMT21 Biomedical Translation Task
This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).
HW-TSC’s Participation in the WMT 2021 Large-Scale Multilingual Translation Task
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to the WMT 2021 Large-Scale Multilingual Translation Task.
HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task.
HW-TSC’s Participation in the WMT 2021 News Translation Shared Task
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task.
How Length Prediction Influence the Performance of Non-Autoregressive Translation?
Length prediction is a special task in a series of NAT models where target length has to be determined before generation.
Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection
Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA).
Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation
In this paper we apply “one translation per discourse” in NMT, and aim to encourage lexical translation consistency for document-level NMT.
APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing
Thanks to the strong representation learning capability of deep learning, especially pre-training techniques with language model loss, dependency parsing has achieved great performance boost in the in-domain scenario with abundant labeled training data for target domains.
Speaker-Aware Discourse Parsing on Multi-Party Dialogues
It is believed that speaker interactions are helpful for this task.
Ranked #2 on
Discourse Parsing
on STAC
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation
For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022.
A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing
In the coarse labeling stage, the joint model outputs a bracketed tree, in which each node corresponds to one of four labels (i. e., phrase, subphrase, word, subword).
Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network
To address this issue, we for the first time apply a dynamic matching network on the shared-private model for semi-supervised cross-domain dependency parsing.
RST Discourse Parsing with Second-Stage EDU-Level Pre-training
Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i. e. element discourse unit (EDU). To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP). We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective, leading a 2. 1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.
Prediction Difference Regularization against Perturbation for Neural Machine Translation
Regularization methods applying input perturbation have drawn considerable attention and have been frequently explored for NMT tasks in recent years.
HW-TSC at SemEval-2022 Task 7: Ensemble Model Based on Pretrained Models for Identifying Plausible Clarifications
This paper describes the system for the identifying Plausible Clarifications of Implicit and Underspecified Phrases.
Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation
Diverse NMT aims at generating multiple diverse yet faithful translations given a source sentence.
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training
Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
Synchronous Refinement for Neural Machine Translation
Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner.
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
This paper describes in detail the construction process and data statistics of DuSQL.
Stacked AMR Parsing with Silver Data
In particular, one recent seq-to-seq work directly fine-tunes AMR graph sequences on the encoder-decoder pre-trained language model and achieves new state-of-the-art results, outperforming previous works by a large margin.
Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation
Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT.
HI-CMLM: Improve CMLM with Hybrid Decoder Input
Mask-predict CMLM (Ghazvininejad et al., 2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence.
Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference
Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity.
HW-TSC at SemEval-2022 Task 3: A Unified Approach Fine-tuned on Multilingual Pretrained Model for PreTENS
In order to verify whether our model could also perform better in subtask 2 (the regression subtask), the ranking score is transformed into classification labels by an up-sampling strategy.
A User-Centric Benchmark for Evaluating Large Language Models
To address this oversight, we propose benchmarking LLMs from a user perspective in both dataset construction and evaluation designs.
In-Context Learning State Vector with Inner and Momentum Optimization
In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector.
Collaborative-Enhanced Prediction of Spending on Newly Downloaded Mobile Games under Consumption Uncertainty
In summary, our contributions underscore the importance of stable model training frameworks and the efficacy of collaborative-enhanced models in predicting user spending behavior in mobile gaming.
Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training
Experimental results on Chinese sequence labeling datasets demonstrate that the improved BABERT variant outperforms the vanilla version, not only on these tasks but also more broadly across a range of Chinese natural language understanding tasks.
Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy.
Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems
We also devise a simulation-guided approach for training NBCs, aiming to achieve tightness in computing precise certified lower and upper bounds.
EEG-SVRec: An EEG Dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation
To address these challenges and provide a more comprehensive understanding of user affective experience and cognitive activity, we propose EEG-SVRec, the first EEG dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation.
Instruction-Driven Game Engines on Large Language Models
The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game rules and autonomously generate game-play processes.
Aiming at the Target: Filter Collaborative Information for Cross-Domain Recommendation
In CUT, user similarity in the target domain is adopted as a constraint for user transformation learning to filter the user collaborative information from the source domain.
To Recommend or Not: Recommendability Identification in Conversations with Pre-trained Language Models
First, we propose and define the recommendability identification task, which investigates the need for recommendations in the current conversational context.
Improving Attributed Text Generation of Large Language Models via Preference Learning
Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content.
A Situation-aware Enhancer for Personalized Recommendation
In this paper, we provide a new perspective that takes situations as the preconditions for users' interactions.
Common Sense Enhanced Knowledge-based Recommendation with Large Language Model
Knowledge-based recommendation models effectively alleviate the data sparsity issue leveraging the side information in the knowledge graph, and have achieved considerable performance.
Sequential Recommendation with Latent Relations based on Large Language Model
Different from previous relation-aware models that rely on predefined rules, we propose to leverage the Large Language Model (LLM) to provide new types of relations and connections between items.
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success.
From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation
Machine Translation Quality Estimation (MTQE) is the task of estimating the quality of machine-translated text in real time without the need for reference translations, which is of great importance for the development of MT.
GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning
To tackle these challenges, we present GenView, a controllable framework that augments the diversity of positive views leveraging the power of pretrained generative models while preserving semantics.
Evaluation Ethics of LLMs in Legal Domain
In recent years, the utilization of large language models for natural language dialogue has gained momentum, leading to their widespread adoption across various domains.
Backdoor Attack with Mode Mixture Latent Modification
Backdoor attacks become a significant security concern for deep neural networks in recent years.
Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder
Reconstructing natural language from non-invasive electroencephalography (EEG) holds great promise as a language decoding technology for brain-computer interfaces (BCIs).
Rethinking Negative Instances for Generative Named Entity Recognition
In the Named Entity Recognition (NER) task, recent advancements have seen the remarkable improvement of LLMs in a broad range of entity domains via instruction tuning, by adopting entity-centric schema.
SelectIT: Selective Instruction Tuning for Large Language Models via Uncertainty-Aware Self-Reflection
In this work, we propose a novel approach, termed SelectIT, that capitalizes on the foundational capabilities of the LLM itself.
EasyRL4Rec: A User-Friendly Code Library for Reinforcement Learning Based Recommender Systems
Reinforcement Learning (RL)-Based Recommender Systems (RSs) are increasingly recognized for their ability to improve long-term user engagement.
Multi-Agent Collaboration Framework for Recommender Systems
LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks.
DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators
In this paper, we propose an alternative adaptation approach, named Decoding-enhanced Multi-phase Prompt Tuning (DeMPT), to make LLMs discriminately model and utilize the inter- and intra-sentence context and more effectively adapt LLMs to context-aware NMT.
Recommender for Its Purpose: Repeat and Exploration in Food Delivery Recommendations
This paper emphasizes the importance of dedicated analyses and methods for domain-specific characteristics for the recommender system studies.
A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation
For this setting, previous methods utilize visual and textual encoders to encode the image and keywords and employ a language model-based decoder to generate the product description.
LLMs Meet Long Video: Advancing Long Video Comprehension with An Interactive Visual Adapter in LLMs
Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence.
Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment
Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e. g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i. e., connecting visuals to their relevant knowledge.
SiLLM: Large Language Models for Simultaneous Machine Translation
We propose SiLLM, which delegates the two sub-tasks to separate agents, thereby incorporating LLM into SiMT.
FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema
In the quest to facilitate the deep intelligence of Large Language Models (LLMs) accessible in final-end user-bot interactions, the art of prompt crafting emerges as a critical yet complex task for the average user.
DB-LLM: Accurate Dual-Binarization for Efficient LLMs
Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment.
Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection
This serves as a reminder to carefully consider sensitivity and confidence in the pursuit of model fairness.
Case Study: Testing Model Capabilities in Some Reasoning Tasks
Large Language Models (LLMs) excel in generating personalized content and facilitating interactive dialogues, showcasing their remarkable aptitude for a myriad of applications.
Unsupervised Sign Language Translation and Generation
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without parallel sign language data.
RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner
This pioneering work lays the groundwork for future research in semi-supervised learning for referring expression segmentation.
Intersectional Two-sided Fairness in Recommendation
Fairness of recommender systems (RS) has attracted increasing attention recently.
In-Context Learning for Few-Shot Nested Named Entity Recognition
In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address.
When Large Language Models Meet Vector Databases: A Survey
This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area.
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
This paper serves as a comprehensive system description of version 2. 0 of the Marabou framework for formal analysis of neural networks.
Revisiting Demonstration Selection Strategies in In-Context Learning
In this work, we first revisit the factors contributing to this variance from both data and model aspects, and find that the choice of demonstration is both data- and model-dependent.
Using Large Language Model for End-to-End Chinese ASR and NER
In this work, we connect the Whisper encoder with ChatGLM3 and provide in-depth comparisons of these two approaches using Chinese automatic speech recognition (ASR) and name entity recognition (NER) tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions
Our proposed translation mixed-instructions enable LLMs (Llama-2~7B and 13B) to maintain consistent translation performance from the sentence level to documents containing as many as 2048 tokens.
UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction
Previous works usually adopt end-to-end models and has strong dependency on Pseudo Paired Data and Original Paired Data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
HA-HI: Synergising fMRI and DTI through Hierarchical Alignments and Hierarchical Interactions for Mild Cognitive Impairment Diagnosis
Early diagnosis of mild cognitive impairment (MCI) and subjective cognitive decline (SCD) utilizing multi-modal magnetic resonance imaging (MRI) is a pivotal area of research.
Learning to Reweight for Graph Neural Network
In this paper, we study the problem of the generalization ability of GNNs in Out-Of-Distribution (OOD) settings.
Expressive Forecasting of 3D Whole-body Human Motions
Human motion forecasting, with the goal of estimating future human behavior over a period of time, is a fundamental task in many real-world applications.
Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA.
Robustness Verification of Deep Reinforcement Learning Based Control Systems using Reward Martingales
In this work, we present the first approach for robustness verification of DRL-based control systems by introducing reward martingales, which offer a rigorous mathematical foundation to characterize the impact of state perturbations on system performance in terms of cumulative rewards.
Can LLM find the green circle? Investigation and Human-guided tool manipulation for compositional generalization
The meaning of complex phrases in natural language is composed of their individual components.
Relevance Feedback with Brain Signals
To explore the effectiveness of brain signals in the context of RF, we propose a novel RF framework that combines BCI-based relevance feedback with pseudo-relevance signals and implicit signals to improve the performance of document re-ranking.
Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix
In multilingual translation research, the comprehension and utilization of language families are of paramount importance.
TSRankLLM: A Two-Stage Adaptation of LLMs for Text Ranking
Text ranking is a critical task in various information retrieval applications, and the recent success of pre-trained language models (PLMs), especially large language models (LLMs), has sparked interest in their application to text ranking.
Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs
These models predominantly map visual information into language representation space, leveraging the vast knowledge and powerful text generation abilities of LLMs to produce multimodal instruction-following responses.
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions.
Addressing the Length Bias Problem in Document-Level Neural Machine Translation
To solve the length bias problem, we propose to improve the DNMT model in training method, attention mechanism, and decoding strategy.
Collaborative Word-based Pre-trained Item Representation for Transferable Recommendation
In this paper, we propose CoWPiRec, an approach of Collaborative Word-based Pre-trained item representation for Recommendation.
Language Generation from Brain Recordings
Inspired by recent research that revealed associations between the brain and the large computational language models, we propose a generative language BCI that utilizes the capacity of a large language model (LLM) jointly with a semantic brain decoder to directly generate language from functional magnetic resonance imaging (fMRI) input.
Temporal Knowledge Question Answering via Abstract Reasoning Induction
In this paper, we tackle the significant challenge of temporal knowledge reasoning in Large Language Models (LLMs), an area where such models frequently encounter difficulties.
Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration
Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks.
How Well Do Large Language Models Understand Syntax? An Evaluation by Asking Natural Language Questions
While recent advancements in large language models (LLMs) bring us closer to achieving artificial general intelligence, the question persists: Do LLMs truly understand language, or do they merely mimic comprehension through pattern recognition?
A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering
The emergence of multimodal large models (MLMs) has significantly advanced the field of visual understanding, offering remarkable capabilities in the realm of visual question answering (VQA).
Context Consistency between Training and Testing in Simultaneous Machine Translation
Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context.
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction
In this paper, we propose a novel approach for few-shot relation extraction using large language models, named CoT-ER, chain-of-thought with explicit evidence reasoning.
Mirror: A Universal Framework for Various Information Extraction Tasks
Sharing knowledge between information extraction tasks has always been a challenge due to the diverse data formats and task variations.
A Survey of Large Language Models Attribution
Open-domain generative systems have gained significant attention in the field of conversational AI (e. g., generative search engines).
LLM-enhanced Self-training for Cross-domain Constituency Parsing
Our experimental results demonstrate that self-training for constituency parsing, equipped with an LLM, outperforms traditional methods regardless of the LLM's performance.
Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions
Legal case retrieval aims to help legal workers find relevant cases related to their cases at hand, which is important for the guarantee of fairness and justice in legal judgments.
An Empirical Study of Frame Selection for Text-to-Video Retrieval
In this paper, we make the first empirical study of frame selection for TVR.
Non-autoregressive Streaming Transformer for Simultaneous Translation
Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality.
Improving Seq2Seq Grammatical Error Correction via Decoding Interventions
In this paper, we propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally, and then dynamically influence the choice of the next token.
Ranked #1 on
Grammatical Error Correction
on MuCGEC
Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting
By leveraging the augmenting data from the GEC models themselves in the post-training process and introducing regularization data for cycle training, our proposed method can effectively improve the model robustness of well-trained GEC models with only a few more training epochs as an extra cost.
Revisiting Sparse Retrieval for Few-shot Entity Linking
Entity linking aims to link ambiguous mentions to their corresponding entities in a knowledge base.
A Read-and-Select Framework for Zero-shot Entity Linking
Zero-shot entity linking (EL) aims at aligning entity mentions to unseen entities to challenge the generalization ability.
G-SPEED: General SParse Efficient Editing MoDel
Large Language Models~(LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages.
Language Models are Universal Embedders
As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is desirable to build a unified embedding model rather than dedicated ones for each scenario.
Empower Nested Boolean Logic via Self-Supervised Curriculum Learning
Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data.
Investigating the Influence of Legal Case Retrieval Systems on Users' Decision Process
Given a specific query case, legal case retrieval systems aim to retrieve a set of case documents relevant to the case at hand.
Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning
Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services.
OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
This report provides the main details to pre-train an analogous model, including pre-training data processing, Bilingual Flan data collection, the empirical observations that inspire our model architecture design, training objectives of different stages, and other enhancement techniques.
A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting
End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations, and terminologies not frequently encountered in the training data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Self-Correlation and Cross-Correlation Learning for Few-Shot Remote Sensing Image Semantic Segmentation
To tackle these challenges, we propose a Self-Correlation and Cross-Correlation Learning Network for the few-shot remote sensing image semantic segmentation.
Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models
Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks.
An Empirical Study of CLIP for Text-based Person Search
TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS.
Ranked #4 on
Text based Person Retrieval
on RSTPReid
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning.
CMD: a framework for Context-aware Model self-Detoxification
In view of this, we introduce a Context-aware Model self-Detoxification~(CMD) framework that pays attention to both the context and the detoxification process, i. e., first detoxifying the context and then making the language model generate along the safe context.
Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognition
In this paper, a semi-supervised Dual-stream Self-Attentive Adversarial Graph Contrastive learning framework (termed as DS-AGC) is proposed to tackle the challenge of limited labeled data in cross-subject EEG-based emotion recognition.
Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
A scene-event mapping mechanism is first designed to bridge the gap between the underlying scene structure and the high-level event semantic structure, resulting in an overall hierarchical scene-event (termed ICE) graph structure.
XNLP: An Interactive Demonstration System for Universal Structured NLP
Structured Natural Language Processing (XNLP) is an important subset of NLP that entails understanding the underlying semantic or syntactic structure of texts, which serves as a foundational component for many downstream applications.
Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm
In this paper, we conduct a holistic exploration of the Universal Decompositional Semantic (UDS) Parsing.
Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction
To directly introduce the correct feedback label information, we propose an Unbiased delayed feedback Label Correction framework (ULC), which uses an auxiliary model to correct labels for observed negative feedback samples.
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
Measuring Item Global Residual Value for Fair Recommendation
In this paper, we call for a shift of attention from modeling user preferences to developing fair exposure mechanisms for items.
Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking
In order to pass better ads from the early to the final stage ranking, we propose a multi-task learning framework for early stage ranking to capture multiple final stage ranking components (i. e. ads clicks and ads quality events) and their task relations.
THUIR2 at NTCIR-16 Session Search (SS) Task
Our team(THUIR2) participated in both FOSS and POSS subtasks of the NTCIR-161 Session Search (SS) Task.
Understanding Prompt Tuning for V-L Models Through the Lens of Neural Collapse
It is found that NC optimality of text-to-image representations shows a positive correlation with downstream generalizability, which is more severe under class imbalance settings.
Generative Multimodal Entity Linking
Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base.
FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation
Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos.
Rethinking Document-Level Relation Extraction: A Reality Check
Recently, numerous efforts have continued to push up performance boundaries of document-level relation extraction (DocRE) and have claimed significant progress in DocRE.
Knowledge-Prompted Estimator: A Novel Approach to Explainable Machine Translation Assessment
Cross-lingual Machine Translation (MT) quality estimation plays a crucial role in evaluating translation performance.
ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images
It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.
Disambiguated Lexically Constrained Neural Machine Translation
Lexically constrained neural machine translation (LCNMT), which controls the translation generation with pre-specified constraints, is important in many practical applications.
Large language models improve Alzheimer's disease diagnosis using multi-modality data
In diagnosing challenging conditions such as Alzheimer's disease (AD), imaging is an important reference.
Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation
$k$-Nearest neighbor machine translation ($k$NN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains.
A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation
In this paper, we study existing approaches and identify a dominant factor in defining tight approximation, namely the approximation domain of the activation function.
Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization
With contrastive learning, we propose a learning potential-guided metric for domain heterogeneity by promoting learning variant features.
NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts
We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains.
Revisiting Token Dropping Strategy in Efficient BERT Pretraining
Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers.
RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search
RA offsets the overfitting risk by introducing a novel positive relation detection task (i. e., learning to distinguish strong and weak positive pairs).
Ranked #2 on
Text based Person Retrieval
on RSTPReid
ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination
As ChatGPT and GPT-4 spearhead the development of Large Language Models (LLMs), more researchers are investigating their performance across various tasks.
CopyNE: Better Contextual ASR by Copying Named Entities
However, traditional token-level ASR models have struggled with accurately transcribing entities due to the problem of homophonic and near-homophonic tokens.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Text-based Person Search without Parallel Image-Text Data
Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description.
A Pilot Study on Dialogue-Level Dependency Parsing for Chinese
Dialogue-level dependency parsing has received insufficient attention, especially for Chinese.
Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination
In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs.
Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e. g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages.
Generating Visual Spatial Description via Holistic 3D Scene Understanding
With an external 3D scene extractor, we obtain the 3D objects and scene features for input images, based on which we construct a target object-centered 3D spatial scene graph (Go3D-S2G), such that we model the spatial semantics of target objects within the holistic 3D scenes.
Can Diffusion Model Achieve Better Performance in Text Generation? Bridging the Gap between Training and Inference!
Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space.
A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues
This makes the language model well-suitable for such multi-modal reasoning scenario on joint textual and visual clues.
Toward Adversarial Training on Contextualized Language Representation
Based on the observation, we propose simple yet effective \textit{Contextualized representation-Adversarial Training} (CreAT), in which the attack is explicitly optimized to deviate the contextualized representation of the encoder.
LMEye: An Interactive Perception Network for Large Language Models
LMEye addresses this issue by allowing the LLM to request the desired visual information aligned with various human instructions, which we term as the dynamic visual information interaction.
A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text
Inspired by the Divide-and-Conquer algorithm and dual-process theory, in this paper, we regard linguistically complex texts as compound proposition texts composed of multiple simple proposition sentences and propose an end-to-end Neural Divide-and-Conquer Reasoning framework, dubbed NDCR.
Test-Time Adaptation with Perturbation Consistency Learning
Accordingly, in this paper, we propose perturbation consistency learning (PCL), a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts.
Intent-aware Ranking Ensemble for Personalized Recommendation
To address such a task, we propose an Intent-aware ranking Ensemble Learning~(IntEL) model to fuse multiple single-objective item lists with various user intents, in which item-level personalized weights are learned.
LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model
Universally modeling all typical information extraction tasks (UIE) with one generative language model (GLM) has revealed great potential by the latest study, where various IE predictions are unified into a linearized hierarchical expression under a GLM.
Learning Reliable Representations for Incomplete Multi-View Partial Multi-Label Classification
The application of multi-view contrastive learning has further facilitated this process, however, the existing multi-view contrastive learning methods crudely separate the so-called negative pair, which largely results in the separation of samples belonging to the same category or similar ones.
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs.
Towards Making the Most of ChatGPT for Machine Translation
We show that: 1) The performance of ChatGPT depends largely on temperature, and a lower temperature usually can achieve better performance; 2) Emphasizing the task information can further improve ChatGPT's performance, particularly in complex MT tasks; 3) Introducing domain information can elicit ChatGPT's generalization ability and improve its performance in the specific domain; 4) ChatGPT tends to generate hallucinations for non-English-centric MT tasks, which can be partially addressed by our proposed prompts but still need to be highlighted for the MT/NLP community.
Boosting Verified Training for Robust Image Classifications via Abstraction
Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training.
A Tiny Machine Learning Model for Point Cloud Object Classification
On the other hand, the model size and inference complexity of DGCNN are 42X and 1203X of those of Green-PointHop, respectively.
Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning
A contributing factor to this problem is that NMT models trained with the one-to-one paradigm struggle to handle the source diversity phenomenon, where inputs with the same meaning can be expressed differently.
Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening
The proposed framework equipped with only two embedding layers achieves $O(1)$ querying time complexity, while improving the retrieval efficiency and keeping its performance, when applied prior to the common image-text retrieval methods.
RenewNAT: Renewing Potential Translation for Non-Autoregressive Transformer
Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance.
AMOM: Adaptive Masking over Masking for Conditional Masked Language Model
Experiments on \textbf{3} different tasks (neural machine translation, summarization, and code generation) with \textbf{15} datasets in total confirm that our proposed simple method achieves significant performance improvement over the strong CMLM model.
Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation
Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem.
RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning
OOD exacerbates inconsistencies in magnitudes and directions of task gradients, which brings challenges for GBML to optimize the meta-knowledge by minimizing the sum of task gradients in each minibatch.
The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting
On typical MuJoCo and DeepMind Control Suite (DMC) benchmarks, we find common phenomena for TD3 and RAD agents: 1) the activity of policy network parameters is highly asymmetric and policy networks advance monotonically along very few major parameter directions; 2) severe detours occur in parameter update and harmonic-like changes are observed for all minor parameter directions.
S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification
Many point cloud classification methods are developed under the assumption that all point clouds in the dataset are well aligned with the canonical axes so that the 3D Cartesian point coordinates can be employed to learn features.
KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation.
OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks
The experimental results demonstrate our approach's effectiveness and efficiency in verifying DNNs' robustness against various occlusions, and its ability to generate counterexamples when these DNNs are not robust.
A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues.
MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters
To achieve this goal, we apply a bilevel optimization to explicitly model and optimize the coupling relationship between the OOD model and auxiliary adapter layers.
SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation
In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image.
Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low.
P-Transformer: Towards Better Document-to-Document Neural Machine Translation
To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention.
QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks
Experimental results on QNNs with different quantization bits confirm the effectiveness and efficiency of our approach, e. g., two orders of magnitude faster and able to solve more verification tasks in the same time limit than the state-of-the-art methods.
ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation
In this paper, we propose a novel transfer learning method for NMT, namely ConsistTL, which can continuously transfer knowledge from the parent model during the training of the child model.
Improving Simultaneous Machine Translation with Monolingual Data
Preliminary experiments on En-Zh and En-Ja news domain corpora demonstrate that monolingual data can significantly improve translation quality (e. g., +3. 15 BLEU on En-Zh).
Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling
Existing research generally treats Chinese character as a minimum unit for representation.
Ranked #1 on
Machine Translation
on WMT2017 Chinese-English
Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training
The experimental results on a wide range of benchmarks show that the DNNs trained by using our approach exhibit comparable performance, while the reachability analysis of the corresponding systems becomes more amenable with significant tightness and efficiency improvement over the state-of-the-art white-box approaches.
DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximation
We observe that existing approaches only rely on overestimated domains, while the corresponding tight approximation may not necessarily be tight on its actual domain.
WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation
Keyphrase generation aims to automatically generate short phrases summarizing an input document.
Third-Party Aligner for Neural Word Alignments
Word alignment is to find translationally equivalent words between source and target sentences.
Revisiting Grammatical Error Correction Evaluation and Beyond
Pretraining-based (PT-based) automatic evaluation metrics (e. g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e. g., machine translation and text summarization) due to their better correlation with human judgments over traditional overlap-based methods.
Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change
Existing methods mainly perform continual training to mitigate such a misalignment.
Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data
Inspired by early research on exploring naturally annotated data for Chinese word segmentation (CWS), and also by recent research on integration of speech and text processing, this work for the first time proposes to mine word boundaries from parallel speech/text data.
Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
We apply BABERT for feature induction of Chinese sequence labeling tasks.
Ranked #1 on
Chinese Word Segmentation
on MSRA
Chinese Named Entity Recognition
Chinese Word Segmentation
+3
Extending Phrase Grounding with Pronouns in Visual Dialogues
First, we construct a dataset of phrase grounding with both noun phrases and pronouns to image regions.
Semantic Structure Enhanced Contrastive Adversarial Hash Network for Cross-media Representation Learning
Secondly, for further improving learning ability of implicit cross-media semantic associations, a semantic label association graph is constructed, and the graph convolutional network is utilized to mine the implicit semantic structures, thus guiding learning of discriminative features of different modalities.
SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser
Then, we obtain parse trees of the source incorrect sentences by projecting trees of the target correct sentences.
Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation
Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-BART and VL-T5 as backbones.
Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning
Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios.
SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training
The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks.
Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes
First, we propose a unified policy abstraction theory, containing three types of policy abstraction associated to policy features at different levels.
SeSQL: Yet Another Large-scale Session-level Chinese Text-to-SQL Dataset
As the first session-level Chinese dataset, CHASE contains two separate parts, i. e., 2, 003 sessions manually constructed from scratch (CHASE-C), and 3, 456 sessions translated from English SParC (CHASE-T).
Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks
Considerable efforts have been devoted to finding the so-called tighter approximations to obtain more precise verification results.
Brain Topography Adaptive Network for Satisfaction Modeling in Interactive Information Access System
We explore the effectiveness of BTA for satisfaction modeling in two popular information access scenarios, i. e., search and recommendation.
Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval
By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data.
Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network
Normalizing flow models have been used successfully for generative image super-resolution (SR) by approximating complex distribution of natural images to simple tractable distribution in latent space through Invertible Neural Networks (INN).
Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations
CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr.
Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation
To solve this problem, we present a plug-in Hierarchical Tree Structure-aware (HTS) method, which not only learns the relationship of FSL and pretext tasks, but more importantly, can adaptively select and aggregate feature representations generated by pretext tasks to maximize the performance of FSL tasks.
Towards Representation Alignment and Uniformity in Collaborative Filtering
Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance.
