Search Results for author:
Found 90 papers, 42 papers with code
S^2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers
The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing.
A Survey on Self-Evolution of Large Language Models
Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications.
Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
As intelligent agents, LLMs need to have the capabilities of task planning, long-term memory, and the ability to leverage external tools to achieve satisfactory performance.
Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
We observe that adapter tuning demonstrates superiority over prompt-based methods, even without parameter expansion in each learning session.
Fine-Tuning Language Models with Reward Learning on Policy
RLHF contains three steps, i. e., human preference collecting, reward learning, and policy optimization, which are usually performed serially.
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
Additionally, the concept of diversity for prompts can be more complex than responses that are typically quantified by single digits.
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains.
SoFA: Shielded On-the-fly Alignment via Priority Rule Following
The alignment problem in Large Language Models (LLMs) involves adapting them to the broad spectrum of human values.
Self-Retrieval: Building an Information Retrieval System with One Large Language Model
The rise of large language models (LLMs) has transformed the role of information retrieval (IR) systems in the way to humans accessing information.
DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever
Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems.
Unifying Structured Data as Graph for Data-to-Text Pre-Training
In this paper, we unify different types of structured data (i. e., table, key-value data, knowledge graph) into the graph format and cast different data-to-text generation tasks as graph-to-text generation.
One Shot Learning as Instruction Data Prospector for Large Language Models
Nuggets assesses the potential of individual instruction examples to act as effective one shot examples, thereby identifying those that can significantly enhance diverse task performance.
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
Specifically, the crucial information in the context will be potentially overlooked by model when it is positioned in the trough zone of the attention waveform, leading to decreased performance.
Ranked #2 on
Trajectory Planning
on ToolBench
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Then, we use DARE as a versatile plug-and-play technique to sparsify delta parameters of multiple SFT homologous models for mitigating parameter interference and merge them into a single model by parameter fusing.
Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs
Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation.
Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue
This paper investigates the effectiveness of combining LLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS.
Diversify Question Generation with Retrieval-Augmented Style Transfer
Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems.
Improving Question Generation with Multi-level Content Planning
Previous studies have suggested that key phrase selection is essential for question generation (QG), yet it is still challenging to connect such disjointed phrases into meaningful questions, particularly for long context.
Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection
Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning.
Constructive Large Language Models Alignment with Diverse Feedback
This limitation leads to suboptimal performance, even when ample training data is available.
Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these intricate contexts.
UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt
Using the high-quality prompts generated, we scale the corpus of the pre-trained conversation model to 122 datasets from 15 dialog-related tasks, resulting in Universal Pre-trained Conversation Model (UniPCM), a powerful foundation model for various conversational tasks and different dialog systems.
VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue
Visually-grounded dialog systems, which integrate multiple modes of communication such as text and visual inputs, have become an increasingly popular area of investigation.
UniSA: Unified Generative Framework for Sentiment Analysis
Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment
Training large language models (LLMs) with open-domain instruction data has yielded remarkable success in aligning to end tasks and human preferences.
Wider and Deeper LLM Networks are Fairer LLM Evaluators
Each perspective corresponds to the role of a specific LLM neuron in the first layer.
Preference Ranking Optimization for Human Alignment
In this manner, PRO effectively transforms human alignment into aligning the probability ranking of n responses generated by LLM with the preference ranking of humans towards these responses.
Unified Language Representation for Question Answering over Text, Tables, and Images
When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data.
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality
To alleviate these limitations, in this paper, we present CATS, a pragmatic Chinese answer-to-sequence dataset with large scale and high quality.
Universal Information Extraction with Meta-Pretrained Self-Retrieval
Inspired by the fact that large amount of knowledge are stored in the pretrained language models~(PLM) and can be retrieved explicitly, in this paper, we propose MetaRetriever to retrieve task-specific knowledge from PLMs to enhance universal IE.
History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling
Context information modeling is an important task in conversational KBQA.
Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark
Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario.
PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
It utilizes a combination of several fundamental experts to accommodate multiple dialogue-related tasks and can be pre-trained using limited dialogue and extensive non-dialogue multi-modal data.
Ranked #1 on
Response Generation
on SIMMC2.0
SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
SpokenWOZ further incorporates common spoken characteristics such as word-by-word processing and reasoning in spoken language.
Iterative Forward Tuning Boosts In-context Learning in Language Models
In this paper, we propose an effective and efficient two-stage framework to boost ICL in LLMs by exploiting a dual form between Transformer attention and gradient descent-based optimization.
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model.
Ranked #1 on
Multimodal Sentiment Analysis
on MOSI
Emotion Recognition in Conversation
Multimodal Intent Recognition
+1
Causal Document-Grounded Dialogue Pre-training
To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora.
Domain Incremental Lifelong Learning in an Open World
Specifically, we dedicate task-level prompts to capture task-specific knowledge to retain high LL performances and maintain instance-level prompts to learn knowledge shared across input samples to improve the model's generalization performance.
Long-Tailed Question Answering in an Open World
A retrieve-then-rerank frame is further introduced to select in-context examples, which guild the LM to generate text that express knowledge for QA tasks.
U-NEED: A Fine-grained Dataset for User Needs-Centric E-commerce Conversational Recommendation
In this paper, we construct a user needs-centric E-commerce conversational recommendation dataset (U-NEED) from real-world E-commerce scenarios.
Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts
Out-of-Domain (OOD) intent detection is vital for practical dialogue systems, and it usually requires considering multi-turn dialogue contexts.
A Survey on Out-of-Distribution Detection in NLP
Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of machine learning systems in the real world.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases.
Ranked #1 on
Text-To-SQL
on BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
(Execution Accurarcy (Human) metric)
Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks.
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
(2) How can we enhance LLMs' ability to utilize tools?
Empathetic Response Generation via Emotion Cause Transition Graph
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e. g., emotion status) and cognitive factors (e. g., cause of the emotion).
Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs
Specifically, the former efficiently finds relevant passages in a retrieval-and-reranking process, whereas the latter effectively extracts finer-grain spans within those passages to incorporate into a parametric answer generation model (BART, T5).
Plan-then-Seam: Towards Efficient Table-to-Text Generation
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables.
Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning
To alleviate the above challenges, we exploit large language models (LLMs) as decomposers for effective table-based reasoning, which (i) decompose huge evidence (a huge table) into sub-evidence (a small table) to mitigate the interference of useless information for table reasoning; and (ii) decompose complex questions into simpler sub-questions for text reasoning.
Ranked #1 on
Table-based Fact Verification
on TabFact
Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
Recently, the pre-trained text-to-text transformer model, namely T5, though not specialized for text-to-SQL parsing, has achieved state-of-the-art performance on standard benchmarks targeting domain generalization.
Ranked #4 on
Semantic Parsing
on spider
SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph
Existing multimodal conversation agents have shown impressive abilities to locate absolute positions or retrieve attributes in simple scenarios, but they fail to perform well when complex relative positions and information alignments are involved, which poses a bottleneck in response quality.
Towards Generalized Open Information Extraction
Open Information Extraction (OpenIE) facilitates the open-domain discovery of textual facts.
Semi-Supervised Lifelong Language Learning
In this paper, we explore a novel setting, semi-supervised lifelong language learning (SSLL), where a model learns sequentially arriving language tasks with both labeled and unlabeled data.
UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors.
Ranked #1 on
Multimodal Sentiment Analysis
on CMU-MOSI
CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation
Practical dialog systems need to deal with various knowledge sources, noisy user expressions, and the shortage of annotated data.
Estimating Soft Labels for Out-of-Domain Intent Detection
Out-of-Domain (OOD) intent detection is important for practical dialog systems.
Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings
In this paper, we introduce the task of learning unsupervised dialogue embeddings.
Towards Generalizable and Robust Text-to-SQL Parsing
Text-to-SQL parsing tackles the problem of mapping natural language questions to executable SQL queries.
STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing
Concretely, we propose two novel pre-training objectives which respectively explore the context-dependent interactions of NL utterances and SQL queries within each text-to-SQL conversation: (i) schema state tracking (SST) objective that tracks and explores the schema states of context-dependent SQL queries in the form of schema-states by predicting and updating the value of each schema slot during interaction; (ii) utterance dependency tracking (UDT) objective that employs weighted contrastive learning to pull together two semantically similar NL utterances and push away the representations of semantically dissimilar NL utterances within each conversation.
Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots
This paper introduces Doc2Bot, a novel dataset for building machines that help users seek information via conversations.
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems.
Graph-to-Text Generation with Dynamic Structure Pruning
Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism.
SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation
To capture the structured dialog semantics, we pre-train the dialog understanding module via a novel tree-induced semi-supervised contrastive learning objective with the help of extra dialog annotations.
SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers
To improve the generalizability and stability of neural text-to-SQL parsers, we propose a model uncertainty constraint to refine the query representations by enforcing the output representations of different perturbed encoding networks to be consistent with each other.
SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding
Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks.
EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models
Although the AI community has expanded the model scale to the trillion parameter level, the practical deployment of 10-100 billion parameter models is still uncertain due to the latency, throughput, and memory constraints.
A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions
In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query.
A Frequency-aware Software Cache for Large Recommendation System Embeddings
Deep learning recommendation models (DLRMs) have been widely applied in Internet companies.
Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration
In this paper, we propose a Layout-aware document-level Information Extraction dataset, LIE, to facilitate the study of extracting both structural and semantic knowledge from visually rich documents (VRDs), so as to generate accurate responses in dialogue systems.
Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing
The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i. e., properly recognizing mentions of unseen columns or tables when generating SQLs.
Multi-View Active Fine-Grained Recognition
As fine-grained visual classification (FGVC) being developed for decades, great works related have exposed a key direction -- finding discriminative local regions and revealing subtle differences.
Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems
In this paper, we present Duplex Conversation, a multi-turn, multimodal spoken dialogue system that enables telephone-based agents to interact with customers like a human.
A Survey on Neural Open Information Extraction: Current Status and Future Directions
Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational facts from large corpora.
Ranked #1 on
Open Information Extraction
on CaRB
Natural Language Understanding
Open-Domain Question Answering
+1
Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server.
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots
We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task.
Ranked #1 on
SSTOD
on SSD_NAME
S$^2$SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers
The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing.
GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems.
Ranked #1 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
Linking-Enhanced Pre-Training for Table Semantic Parsing
Recently pre-training models have significantly improved the performance of various NLP tasks by leveraging large-scale text corpora to improve the contextual representation ability of the neural network.
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking
Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.
Ranked #1 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Sequence Parallelism: Long Sequence Training from System Perspective
That is, with sparse attention, our sequence parallelism enables us to train transformer with infinite long sequence.
Improving Text-to-SQL with Schema Dependency Learning
In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Semantic parsing has long been a fundamental problem in natural language processing.
Ranked #5 on
Dialogue State Tracking
on CoSQL
Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment
Existing end-to-end dialog systems perform less effectively when data is scarce.
Dynamic Memory Induction Networks for Few-Shot Text Classification
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification.
A Survey on Dialog Management: Recent Advances and Challenges
Dialog management (DM) is a crucial component in a task-oriented dialog system.
Induction Networks for Few-Shot Text Classification
Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries.
Ranked #1 on
Few-Shot Text Classification
on ODIC 5-way (10-shot)
Lyb3b at SemEval-2018 Task 12: Ensemble-based Deep Learning Models for Argument Reasoning Comprehension Task
In this task, given a natural language argument with a reason and a claim, the goal is to choose the correct implicit reasoning from two options, in order to form a reasonable structure of (Reason, Warrant, Claim).
Lyb3b at SemEval-2018 Task 11: Machine Comprehension Task using Deep Learning Models
This paper is to solve the task 11 of SemEval-2018, Machine Comprehension using Commonsense Knowledge task.
YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations
In this paper, we perform convolutional neural networks (CNN) to learn the joint representations of question-answer pairs first, then use the joint representations as the inputs of the long short-term memory (LSTM) with attention to learn the answer sequence of a question for labeling the matching quality of each answer.
