Search Results for author:
Found 332 papers, 133 papers with code
\textrm{DuReader}_{\textrm{vis}}: A Chinese Dataset for Open-domain Document Visual Question Answering
Open-domain question answering has been used in a wide range of applications, such as web search and enterprise search, which usually takes clean texts extracted from various formats of documents (e. g., web pages, PDFs, or Word documents) as the information source.
CogBERT: Cognition-Guided Pre-trained Language Models
To fill the gap, we propose CogBERT, a framework that can induce fine-grained cognitive features from cognitive data and incorporate cognitive features into BERT by adaptively adjusting the weight of cognitive features for different NLP tasks.
Technical Report on Shared Task in DialDoc21
The task requires identifying the grounding knowledge in form of a document span for the next dialogue turn.
Weakly Supervised Semantic Parsing by Learning from Mistakes
Using only 10% of utterance-denotation pairs, the parser achieves 84. 2 denotation accuracy on WikiSQL, which is competitive with the previous state-of-the-art approaches using 100% labeled data.
Counterfactual Off-Policy Training for Neural Dialogue Generation
Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses.
Multi-Stage Pre-training for Automated Chinese Essay Scoring
This paper proposes a pre-training based automated Chinese essay scoring method.
All Information is Valuable: Question Matching over Full Information Transmission Network
In this process, there are two kinds of critical information that are commonly employed: the representation information of original questions and the interactive information between pairs of questions.
Benchmarking Meaning Representations in Neural Semantic Parsing
Thus, the impact of meaning representation on semantic parsing is less understood.
Discourse Self-Attention for Discourse Element Identification in Argumentative Student Essays
First, we propose structural sentence positional encodings to explicitly represent sentence positions.
Neural Natural Logic Inference for Interpretable Question Answering
Many open-domain question answering problems can be cast as a textual entailment task, where a question and candidate answers are concatenated to form hypotheses.
Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment
With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers.
Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation
To address this issue, we propose a novel framework, named Generalizable and Faithful Reasoner (GFaiR), which introduces the paradigm of resolution refutation.
RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict
Furthermore, we construct RU22Fact, a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022 of 16K samples, each containing real-world claims, optimized evidence, and referenced explanation.
iDAT: inverse Distillation Adapter-Tuning
Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks.
Meaningful Learning: Advancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
Large language models (LLMs) have developed impressive performance and strong explainability across various reasoning scenarios, marking a significant stride towards mimicking human-like intelligence.
AS-ES Learning: Towards Efficient CoT Learning in Small Models
Chain-of-Thought (CoT) serves as a critical emerging ability in LLMs, especially when it comes to logical reasoning.
VideoPrism: A Foundational Visual Encoder for Video Understanding
We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model.
Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning
Through pretraining on a corpus with various sources, Large Language Models (LLMs) have gained impressive performance.
Exploring Hybrid Question Answering via Program-based Prompting
Question answering over heterogeneous data requires reasoning over diverse sources of data, which is challenging due to the large scale of information and organic coupling of heterogeneous data.
Beyond the Answers: Reviewing the Rationality of Multiple Choice Question Answering for the Evaluation of Large Language Models
In the field of natural language processing (NLP), Large Language Models (LLMs) have precipitated a paradigm shift, markedly enhancing performance in natural language generation tasks.
Multiple-choice
Multiple Choice Question Answering (MCQA)
+1
Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis
Automatic diagnosis is a significant application of AI in healthcare, where diagnoses are generated based on the symptom description of patients.
Distilling Vision-Language Models on Millions of Videos
Our best model outperforms state-of-the-art methods on MSR-VTT zero-shot text-to-video retrieval by 6%.
Aligning Translation-Specific Understanding to General Understanding in Large Language Models
To align the translation-specific understanding to the general one, we propose a novel translation process xIoD (Cross-Lingual Interpretation of Difficult words), explicitly incorporating the general understanding on the content incurring inconsistent understanding to guide the translation.
CLAPP: Contrastive Language-Audio Pre-training in Passive Underwater Vessel Classification
Existing research on audio classification faces challenges in recognizing attributes of passive underwater vessel scenarios and lacks well-annotated datasets due to data privacy concerns.
Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding
In this survey, we present these advances towards length extrapolation in a unified notation from the perspective of PE.
LAMM: Label Alignment for Multi-Modal Prompt Learning
We conduct experiments on 11 downstream vision datasets and demonstrate that our method significantly improves the performance of existing multi-modal prompt learning models in few-shot scenarios, exhibiting an average accuracy improvement of 2. 31(\%) compared to the state-of-the-art methods on 16 shots.
GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction
2) They neglect the interaction between the intrinsic task-agnostic knowledge of pre-trained models and the task-specific knowledge in downstream tasks.
DAP: Domain-aware Prompt Learning for Vision-and-Language Navigation
Then we introduce soft visual prompts in the input space of the visual encoder in a pretrained model.
Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
In this paper, we propose a review to discuss the trends in integration of knowledge and large language models, including taxonomy of methods, benchmarks, and applications.
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), leading to remarkable advancements in text understanding and generation.
Efficient Cloud Pipelines for Neural Radiance Fields
Since their introduction in 2020, Neural Radiance Fields (NeRFs) have taken the computer vision community by storm.
On the Opportunities of Green Computing: A Survey
To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic.
Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements
Empathetic dialogue is an indispensable part of building harmonious social relationships and contributes to the development of a helpful AI.
A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
Chain-of-thought reasoning, a cognitive process fundamental to human intelligence, has garnered significant attention in the realm of artificial intelligence and natural language processing.
Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
To address this challenge, we propose knowledge-tuning, which leverages structured medical knowledge bases for the LLMs to grasp domain knowledge efficiently and facilitate reliable response generation.
Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification
Experimental results indicate that even without tuning any parameters, our LLE-INC is on par with automated verbalizers with parameter tuning.
Prompt-based Context- and Domain-aware Pretraining for Vision and Language Navigation
In the indoor-aware stage, we apply an efficient tuning paradigm to learn deep visual prompts from an indoor dataset, in order to augment pretrained models with inductive biases towards indoor environments.
Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistency
The task of shape abstraction with semantic part consistency is challenging due to the complex geometries of natural objects.
Class Binarization to NeuroEvolution for Multiclass Classification
In this paper, we apply class binarization techniques to a neuroevolution algorithm, NeuroEvolution of Augmenting Topologies (NEAT), that is used to generate neural networks for multiclass classification.
A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions
To model combined and incomplete constraints, we use a Transformer-based layout generation model and carefully design a way to represent constraints and layouts as sequences.
Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition
To facilitate the data efficiency of multiview learning, we further perform video-text alignment for first-person and third-person videos, to fully leverage the semantic knowledge to improve video representations.
Through the Lens of Core Competency: Survey on Evaluation of Large Language Models
From pre-trained language model (PLM) to large language model (LLM), the field of natural language processing (NLP) has witnessed steep performance gains and wide practical uses.
Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone
The diversity of building architecture styles of global cities situated on various landforms, the degraded optical imagery affected by clouds and shadows, and the significant inter-class imbalance of roof types pose challenges for designing a robust and accurate building roof instance segmentor.
HGDNet: A Height-Hierarchy Guided Dual-Decoder Network for Single View Building Extraction and Height Estimation
Unifying the correlative single-view satellite image building extraction and height estimation tasks indicates a promising way to share representations and acquire generalist model for large-scale urban 3D reconstruction.
EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation
Moreover, to our best knowledge, this is the first model with a parameter count limited to just 50KB.
VideoGLUE: Video General Understanding Evaluation of Foundation Models
We evaluate existing foundation models video understanding capabilities using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition, temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring a foundation model (FM) for a downstream task.
UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human language
In this paper, we propose fMRI2text, the first openvocabulary task aiming to bridge fMRI time series and human language.
I run as fast as a rabbit, can you? A Multilingual Simile Dialogue Dataset
Meanwhile, the MSD data can also be used on dialogue tasks to test the ability of dialogue systems when using similes.
Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
Through extensive experiments on various datasets, LLMs can effectively collaborate to reach a consensus despite noticeable inter-inconsistencies, but imbalances in their abilities can lead to domination by superior LLMs.
NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing
To mitigate the effects of label noise, learning with noisy labels (LNL) methods are designed to achieve better generalization performance.
Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation
Causal reasoning ability is crucial for numerous NLP applications.
CSED: A Chinese Semantic Error Diagnosis Corpus
Our experiments show that powerful pre-trained models perform poorly on this corpus.
Lyapunov-Stable Deep Equilibrium Models
Deep equilibrium (DEQ) models have emerged as a promising class of implicit layer models, which abandon traditional depth by solving for the fixed points of a single nonlinear layer.
Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identification
In this paper, we propose a Multi-Modal Equivalent Transformer called MMET for more robust visual-semantic embedding learning on visual, textual and visual-textual tasks respectively.
Generalizable Person Re-identification
Representation Learning
HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge
Large Language Models (LLMs), such as the LLaMA model, have demonstrated their effectiveness in various general-domain natural language processing (NLP) tasks.
Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection
The core idea of this work is to recover the per-pixel mask of each target from the given single point label by using clustering approaches, which looks simple but is indeed challenging since targets are always insalient and accompanied with background clutters.
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information in both videos and text, which is of importance to downstream tasks requiring temporal localization and semantic reasoning.
Unified Visual Relationship Detection with Vision and Language Models
To address this challenge, we propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models (VLMs).
Human-Object Interaction Detection
Relationship Detection
+2
Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting.
CluCDD:Contrastive Dialogue Disentanglement via Clustering
A huge number of multi-participant dialogues happen online every day, which leads to difficulty in understanding the nature of dialogue dynamics for both humans and machines.
BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing
We also make the first attempt to defend against the latest style-level backdoor attacks.
Learning to Generate Image Embeddings with User-level Differential Privacy
Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past.
LERT: A Linguistically-motivated Pre-trained Language Model
We propose LERT, a pre-trained language model that is trained on three types of linguistic features along with the original MLM pre-training task, using a linguistically-informed pre-training (LIP) strategy.
Ranked #6 on
Stock Market Prediction
on Astock
An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?
Recent research in clustering face embeddings has found that unsupervised, shallow, heuristic-based methods -- including $k$-means and hierarchical agglomerative clustering -- underperform supervised, deep, inductive methods.
MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation
To address this challenge, we propose a light-weight model to achieve competitive performances for skin lesion segmentation at the lowest cost of parameters and computational complexity so far.
Deep Multimodal Fusion for Generalizable Person Re-identification
Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance.
Domain Generalization
Generalizable Person Re-identification
+2
MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation
Specifically, our block performs a Fourier transform on the three axes of the input feature and assigns the external weight in the frequency domain, which is generated by our Weights Generator.
MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Due to the extremely large image coverage area (e. g., thousands square kilometers), candidate targets in these images are much smaller, dimer, more changeable than those targets observed by aerial-based and land-based imaging devices.
Prompt Combines Paraphrase: Teaching Pre-trained Models to Understand Rare Biomedical Words
Prompt-based fine-tuning for pre-trained models has proven effective for many natural language processing tasks under few-shot settings in general domain.
DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination
To relieve this issue, curriculum learning is proposed to improve model performance and generalization by ordering training samples in a meaningful (e. g., easy to hard) sequence.
SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation
This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval).
Text Difficulty Study: Do machines behave the same as humans regarding text difficulty?
Given a task, human learns from easy to hard, whereas the model learns randomly.
Multi-stage Moving Target Defense: A Security-enhanced D-FACTS Implementation Approach
We prove that a designed MMTD can significantly improve the detection capability compared to existing one-stage MTDs.
A Graph Enhanced BERT Model for Event Prediction
To this end, we incorporate an additional structured variable into BERT to learn to predict the event connections in the training process.
e-CARE: a New Dataset for Exploring Explainable Causal Reasoning
Understanding causality has vital importance for various Natural Language Processing (NLP) applications.
Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition
These errors have been studied extensively and are relatively simple for humans.
Surrogate Gap Minimization Improves Sharpness-Aware Training
Instead, we define a \textit{surrogate gap}, a measure equivalent to the dominant eigenvalue of Hessian at a local minimum when the radius of the neighborhood (to derive the perturbed loss) is small.
PERT: Pre-training BERT with Permuted Language Model
We permute a proportion of the input text, and the training objective is to predict the position of the original token.
Ranked #4 on
Stock Market Prediction
on Astock
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
We first evaluate CLIP's zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality transfer capability of CLIP on the visual entailment task.
LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training
In this work, we propose LEMON, a general framework for language-based environment manipulation tasks.
Hiding Data in Colors: Secure and Lossless Deep Image Steganography via Conditional Invertible Neural Networks
Deep image steganography is a data hiding technology that conceal data in digital images via deep neural networks.
A Semantic Web Technology Index
In this paper, we propose an SW technology index to standardize the development for ensuring that the work of SW technology is designed well and to quantitatively evaluate the quality of the work in SW technology.
LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection
LiDAR and camera are two common sensors to collect data in time for 3D object detection under the autonomous driving context.
Multi-Source Uncertainty Mining for Deep Unsupervised Saliency Detection
We design an Uncertainty Mining Network (UMNet) which consists of multiple Merge-and-Split (MS) modules to recursively analyze the commonality and difference among multiple noisy labels and infer pixel-wise uncertainty map for each label.
Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
3D human pose estimation (HPE) in autonomous vehicles (AV) differs from other use cases in many factors, including the 3D resolution and range of data, absence of dense depth maps, failure modes for LiDAR, relative location between the camera and LiDAR, and a high bar for estimation accuracy.
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects.
Ranked #2 on
Group Activity Recognition
on Collective Activity
Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views.
Exploring Temporal Granularity in Self-Supervised Video Representation Learning
The training objective consists of two parts: a fine-grained temporal learning objective to maximize the similarity between corresponding temporal embeddings in the short clip and the long clip, and a persistent temporal learning objective to pull together global embeddings of the two clips.
One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal
Single channel blind source separation (SCBSS) refers to separate multiple sources from a mixed signal collected by a single sensor.
Rethinking Person Re-Identification via Semantic-Based Pretraining
Pretraining is a dominant paradigm in computer vision.
Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification
Moreover, aiming to fully exploit the potential of FineGPR and promote the efficient training from millions of synthetic data, we propose an attribute analysis pipeline called AOST, which dynamically learns attribute distribution in real domain, then eliminates the gap between synthetic and real-world data and thus is freely deployed to new scenarios.
Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training
We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity.
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification
Specifically, we first retrieve logic-level program-like evidence from the given table and statement as supplementary evidence for the table.
Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs).
Neural Stylistic Response Generation with Disentangled Latent Variables
Generating open-domain conversational responses in the desired style usually suffers from the lack of parallel data in the style.
Verb Metaphor Detection via Contextual Relation Learning
Correct natural language understanding requires computers to distinguish the literal and metaphorical senses of a word.
Learning Event Graph Knowledge for Abductive Reasoning
Abductive reasoning aims at inferring the most plausible explanation for observed events, which would play critical roles in various NLP applications, such as reading comprehension and question answering.
IFlyEA: A Chinese Essay Assessment System with Automated Rating, Review Generation, and Recommendation
IFlyEA provides multi-level and multi-dimension analytical modules for essay assessment.
Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL
However, we identify two biases in existing datasets for XDTS: (1) a high proportion of context-independent questions and (2) a high proportion of easy SQL queries.
ExCAR: Event Graph Knowledge Enhanced Explainable Causal Reasoning
ExCAR first acquires additional evidence information from a large-scale causal event graph as logical rules for causal reasoning.
CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision
Recent work has shown success in incorporating pre-trained models like BERT to improve NLP systems.
Guided Generation of Cause and Effect
We present a conditional text generation framework that posits sentential expressions of possible causes and effects.
Consistency Regularization for Cross-Lingual Fine-Tuning
Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others.
BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
Maintaining consistent personas is essential for dialogue agents.
Adversarial Training for Machine Reading Comprehension with Virtual Embeddings
Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks.
GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling
Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention.
Ranked #1 on
Semantic Frame Parsing
on MixATIS
(Overall Accuracy metric)
Non-Convex Tensor Low-Rank Approximation for Infrared Small Target Detection
Considering that different singular values have different importance and should be treated discriminatively, in this paper, we propose a non-convex tensor low-rank approximation (NTLA) method for infrared small target detection.
Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization
Current dialogue summarization systems usually encode the text with a number of general semantic features (e. g., keywords and topics) to gain more powerful dialogue modeling capabilities.
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
However, dialogue language understanding contains two closely related tasks, i. e., intent detection and slot filling, and often benefits from jointly learning the two tasks.
ExpMRC: Explainability Evaluation for Machine Reading Comprehension
Achieving human-level performance on some of Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs).
Ranked #1 on
Multi-Choice MRC
on ExpMRC - RACE+ (test)
DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension
Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC.
Ranked #4 on
Question Answering
on Molweni
Learning to Share by Masking the Non-shared for Multi-domain Sentiment Classification
To this end, we propose the BertMasker network which explicitly masks domain-related words from texts, learns domain-invariant sentiment features from these domain-agnostic texts, and uses those masked words to form domain-aware sentence representations.
General Classification
Multi-Domain Sentiment Classification
+3
Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification
Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation.
A Survey on Spoken Language Understanding: Recent Advances and New Frontiers
Spoken Language Understanding (SLU) aims to extract the semantics frame of user queries, which is a core component in a task-oriented dialog system.
Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering
To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose graph-based methods to retrieve them.
Discovering Dialog Structure Graph for Open-Domain Dialog Generation
Learning interpretable dialog structure from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation.
Multiple Structural Priors Guided Self Attention Network for Language Understanding
Self attention networks (SANs) have been widely utilized in recent NLP studies.
Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification
The dialog context information (contextual information) and the mutual interaction information are two key factors that contribute to the two related tasks.
C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling
Slot filling, a fundamental module of spoken language understanding, often suffers from insufficient quantity and diversity of training data.
Biomedical Knowledge Graph Refinement with Embedding and Logic Rules
This paper proposes a method BioGRER to improve the BioKG's quality, which comprehensively combines the knowledge graph embedding and logic rules that support and negate triplets in the BioKG.
Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization
To evaluate the power of the learned representations, in addition to the conventional fully-supervised action recognition settings, we introduce a novel task called single-shot cross-view action recognition.
TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching
Although neural table-to-text models have achieved remarkable progress with the help of large-scale datasets, they suffer insufficient learning problem with limited training data.
HIT-SCIR at SemEval-2020 Task 5: Training Pre-trained Language Model with Pseudo-labeling Data for Counterfactuals Detection
In this task, we dedicate to detecting causation, especially counterfactuals from texts.
Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification
Table-based fact verification is expected to perform both linguistic reasoning and symbolic reasoning.
Unsupervised Explanation Generation for Machine Reading Comprehension
With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances.
CharBERT: Character-aware Pre-trained Language Model
Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable.
Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification
Neural table-to-text models, which select and order salient data, as well as verbalizing them fluently via surface realization, have achieved promising progress.
HIT-SCIR at MRP 2020: Transition-based Parser and Iterative Inference Parser
This paper describes our submission system (HIT-SCIR) for the CoNLL 2020 shared task: Cross-Framework and Cross-Lingual Meaning Representation Parsing.
Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection
Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice.
View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people.
Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks
In detail, we consider utterance and commonsense knowledge as two different types of data and design a Dialogue Heterogeneous Graph Network (D-HGN) for modeling both information.
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
In this paper, we propose a novel and effective regularization term for adversarial data augmentation.
Few-shot Learning for Multi-label Intent Detection
In this paper, we study the few-shot multi-label classification for user intent detection.
Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding
In this paper, we improve Chinese spoken language understanding (SLU) by injecting word information.
A Co-Interactive Transformer for Joint Slot Filling and Intent Detection
Instead of adopting the self-attention mechanism in vanilla Transformer, we propose a co-interactive module to consider the cross-impact by building a bidirectional connection between the two related tasks.
A Compare Aggregate Transformer for Understanding Document-grounded Dialogue
Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses.
Combining ResNet and Transformer for Chinese Grammatical Error Diagnosis
Grammatical error diagnosis is an important task in natural language processing.
N-LTP: An Open-source Neural Language Technology Platform for Chinese
We introduce \texttt{N-LTP}, an open-source neural language technology platform supporting six fundamental Chinese NLP tasks: {lexical analysis} (Chinese word segmentation, part-of-speech tagging, and named entity recognition), {syntactic parsing} (dependency parsing), and {semantic parsing} (semantic dependency parsing and semantic role labeling).
Profile Consistency Identification for Open-domain Dialogue Agents
Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans.
FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding
In this paper, we present FewJoint, a novel Few-Shot Learning benchmark for NLP.
DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification
In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately.
Can We Trust Your Explanations? Sanity Checks for Interpreters in Android Malware Analysis
For this reason, a variety of explanation approaches are proposed to interpret predictions by providing important features.
Cryptography and Security Software Engineering
Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network
Data-driven approaches using neural networks have achieved promising performances in natural language generation (NLG).
Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation
To address the challenge of policy learning in open-domain multi-turn conversation, we propose to represent prior information about dialog transitions as a graph and learn a graph grounded dialog policy, aimed at fostering a more coherent and controllable dialog.
Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?
It is unknown whether there are any connections and common characteristics between the defenses against these two attacks.
Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network
Noun phrases and relational phrases in Open Knowledge Bases are often not canonical, leading to redundant and ambiguous facts.
Attribute analysis with synthetic dataset for person re-identification
To address this problem, firstly, we develop a large-scale synthetic data engine, the salient characteristic of this engine is controllable.
Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
In this paper, we explore the slot tagging with only a few labeled support sentences (a. k. a.
Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer).
Towards Conversational Recommendation over Multi-Type Dialogs
We propose a new task of conversational recommendation over multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e. g., QA) to a recommendation dialog, taking into account user's interests and feedback.
How Does Selective Mechanism Improve Self-Attention Networks?
Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words.
Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterization
Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain.
Counterfactual Off-Policy Training for Neural Response Generation
Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses.
Benchmarking Robustness of Machine Reading Comprehension Models
To fill this important gap, we construct AdvRACE (Adversarial RACE), a new model-agnostic benchmark for evaluating the robustness of MRC models under four different types of adversarial attacks, including our novel distractor extraction and generation attacks.
Revisiting Pre-Trained Models for Chinese Natural Language Processing
Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models.
Ranked #13 on
Stock Market Prediction
on Astock
Conversational Word Embedding for Retrieval-Based Dialog System
Human conversations contain many types of information, e. g., knowledge, common sense, and language habits.
Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning.
Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
However, there has been relatively little research on how to effectively use data from all domains to improve the performance of each domain and also unseen domains.
Ranked #1 on
Task-Oriented Dialogue Systems
on Kvret
AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information, making a fine-grained intent information integration for the token-level slot prediction.
A Survey of Document Grounded Dialogue Systems (DGDS)
We believe that extracting unstructured document(s) information is the future trend of the DS because a great amount of human knowledge lies in these document(s).
Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines.
Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure
Research into the area of multiparty dialog has grown considerably over recent years.
Ranked #7 on
Discourse Parsing
on Molweni
Is Graph Structure Necessary for Multi-hop Question Answering?
We construct a strong baseline model to establish that, with the proper use of pre-trained models, graph structure may not be necessary for multi-hop question answering.
A Sentence Cloze Dataset for Chinese Machine Reading Comprehension
To add diversity in this area, in this paper, we propose a new task called Sentence Cloze-style Machine Reading Comprehension (SC-MRC).
TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing
In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing.
Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation
In this paper, we focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer and aims to preserve text styles while altering the content.
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks.
Ranked #1 on
Code Documentation Generation
on CodeSearchNet - Go
EEV: A Large-Scale Dataset for Studying Evoked Expressions from Video
The ability to predict evoked affect from a video, before viewers watch the video, can help in content creation and video recommendation.
Discriminative Sentence Modeling for Story Ending Prediction
Story Ending Prediction is a task that needs to select an appropriate ending for the given story, which requires the machine to understand the story and sometimes needs commonsense knowledge.
CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension
We present a Chinese judicial reading comprehension (CJRC) dataset which contains approximately 10K documents and almost 50K questions with answers.
View-Invariant Probabilistic Embedding for Human Pose
Depictions of similar human body configurations can vary with changing viewpoints.
Ranked #1 on
Pose Retrieval
on MPI-INF-3DHP
GLA in MediaEval 2018 Emotional Impact of Movies Task
Towards a better understanding of viewer impact, we present our methods for the MediaEval 2018 Emotional Impact of Movies Task to predict the expected valence and arousal continuously in movies.
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed.
Ranked #6 on
Panoptic Segmentation
on Cityscapes test
(using extra training data)
Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
Consistency is one of the major challenges faced by dialogue agents.
Contextual Recurrent Units for Cloze-style Reading Comprehension
Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks.
Improving Machine Reading Comprehension via Adversarial Training
With virtual adversarial training (VAT), we explore the possibility of improving the RC models with semi-supervised learning and prove that examples from a different task are also beneficial.
An Annotation Scheme of A Large-scale Multi-party Dialogues Dataset for Discourse Parsing and Machine Comprehension
In this paper, we propose the scheme for annotating large-scale multi-party chat dialogues for discourse parsing and machine comprehension.
Transforming Wikipedia into Augmented Data for Query-Focused Summarization
The limited size of existing query-focused summarization datasets renders training data-driven summarization models challenging.
HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding
This paper describes our system (HIT-SCIR) for CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing.
Ranked #1 on
UCCA Parsing
on CoNLL 2019
Multi-Input Multi-Output Sequence Labeling for Joint Extraction of Fact and Condition Tuples from Scientific Text
In this work, we propose a new sequence labeling framework (as well as a new tag schema) to jointly extract the fact and condition tuples from statement sentences.
IFlyLegal: A Chinese Legal System for Consultation, Law Searching, and Document Analysis
To our knowledge, IFlyLegal is the first Chinese legal system that employs up-to-date NLP techniques and caters for needs of different user groups, such as lawyers, judges, procurators, and clients.
Panoptic-DeepLab
The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e. g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression.
TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots
The heart of TripleNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels.
Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder
Understanding event and event-centered commonsense reasoning are crucial for natural language processing (NLP).
Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing
In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages.
Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system.
Ranked #6 on
Task-Oriented Dialogue Systems
on KVRET
A Corpus-free State2Seq User Simulator for Task-oriented Dialogue
The framework builds a user simulator by first generating diverse dialogue data from templates and then build a new State2Seq user simulator on the data.
Event Representation Learning Enhanced with External Commonsense Knowledge
Prior work has proposed effective methods to learn event representations that can capture syntactic and semantic information over text corpus, demonstrating their effectiveness for downstream tasks such as script event prediction.
Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)
To address aforementioned problems, not only do we model each table cell considering other records in the same row, we also enrich table's representation by modeling each table cell in context of other cells in the same column or with historical (time dimension) data respectively.
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding
In our framework, we adopt a joint model with Stack-Propagation which can directly use the intent information as input for slot filling, thus to capture the intent semantic knowledge.
Ranked #2 on
Intent Detection
on SNIPS
Cross-Lingual Machine Reading Comprehension
In this paper, we propose Cross-Lingual Machine Reading Comprehension (CLMRC) task for the languages other than English.
Multi-Task Self-Supervised Learning for Disfluency Detection
The pre-trained network is then fine-tuned using human-annotated disfluency detection training data.
ELG: An Event Logic Graph
The evolution and development of events have their own basic principles, which make events happen sequentially.
Constructing Information-Lossless Biological Knowledge Graphs from Conditional Statements
Conditions are essential in the statements of biological literature.
