Search Results for author:
Found 91 papers, 49 papers with code
Understanding Procedural Text using Interactive Entity Networks
Recent efforts have made great progress to track multiple entities in a procedural text, but usually treat each entity separately and ignore the fact that there are often multiple entities interacting with each other during one process, some of which are even explicitly mentioned.
Dual-Channel Evidence Fusion for Fact Verification over Texts and Tables
Different from previous fact extraction and verification tasks that only consider evidence of a single format, FEVEROUS brings further challenges by extending the evidence format to both plain text and tables.
SchemaAgent: A Multi-Agents Framework for Generating Relational Database Schema
In this paper, we propose SchemaAgent, a unified LLM-based multi-agent framework for the automated generation of high-quality database schema.
Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions
While Large Language Model-based agents have demonstrated substantial progress in task completion, existing evaluation benchmarks tend to overemphasize single-task performance, with insufficient attention given to the crucial aspects of multitask planning and execution efficiency required in real-world scenarios.
MiLiC-Eval: Benchmarking Multilingual LLMs for China's Minority Languages
Large language models (LLMs) excel in high-resource languages but struggle with low-resource languages (LRLs), particularly those spoken by minority communities in China, such as Tibetan, Uyghur, Kazakh, and Mongolian.
Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge
Longitudinal network data are essential for analyzing political, economic, and social systems and processes.
JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning
The Four-Element Theory is a fundamental framework in criminal law, defining the constitution of crime through four dimensions: Subject, Object, Subjective aspect, and Objective aspect.
Automating Legal Concept Interpretation with LLMs: Retrieval, Generation, and Evaluation
Multi-faceted evaluations by legal experts indicate that the quality of our concept interpretations is comparable to those written by human experts.
Only One Relation Possible? Modeling the Ambiguity in Event Temporal Relation Extraction
Event Temporal Relation Extraction (ETRE) aims to identify the temporal relationship between two events, which plays an important role in natural language understanding.
ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice
ELLA also retrieves relevant legal cases for user reference.
Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering
Conditional question answering (CQA) is an important task that aims to find probable answers and identify missing conditions.
Unlocking the Potential of Model Merging for Low-Resource Languages
Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT).
Overview of the CAIL 2023 Argument Mining Track
We give a detailed overview of the CAIL 2023 Argument Mining Track, one of the Chinese AI and Law Challenge (CAIL) 2023 tracks.
What Kinds of Tokens Benefit from Distant Text? An Analysis on Long Context Language Modeling
In this paper, we aim to explore which kinds of words benefit more from long contexts in language models.
DiNeR: a Large Realistic Dataset for Evaluating Compositional Generalization
To better investigate compositional generalization with more linguistic phenomena and compositional diversity, we propose the DIsh NamE Recognition (DiNeR) task and create a large realistic Chinese dataset.
Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?
Recent studies have shown that Large Language Models (LLMs) have the potential to process extremely long text.
Motion Generation from Fine-grained Textual Descriptions
The task of text2motion is to generate human motion sequences from given textual descriptions, where the model explores diverse mappings from natural language instructions to human body movements.
Harder Tasks Need More Experts: Dynamic Routing in MoE Models
In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input difficulty.
ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context
Our work underscores the importance of the planning and reasoning abilities towards a model over tabular tasks with generalizability and interpretability.
Teaching Large Language Models an Unseen Language on the Fly
We introduce DiPMT++, a framework for adapting LLMs to unseen languages by in-context learning.
Probing Multimodal Large Language Models for Global and Local Semantic Representations
The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images.
Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data
To address this gap, we introduce the Quantitative Reasoning with Data (QRData) benchmark, aiming to evaluate Large Language Models' capability in statistical and causal reasoning with real-world data.
Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering
Open-ended question answering requires models to find appropriate evidence to form wellreasoned, comprehensive and helpful answers.
CASA: Causality-driven Argument Sufficiency Assessment
Motivated by the definition of probability of sufficiency (PS) in the causal literature, we proposeCASA, a zero-shot causality-driven argument sufficiency assessment framework.
MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China
To address this accessibility challenge, we present MC$^2$, a Multilingual Corpus of Minority Languages in China, which is the largest open-source corpus of its kind so far.
From the One, Judge of the Whole: Typed Entailment Graph Construction with Predicate Generation
Entailment Graphs (EGs) have been constructed based on extracted corpora as a strong and explainable form to indicate context-independent entailment relations in natural languages.
How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension
We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances.
The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code
Causal reasoning, the ability to identify cause-and-effect relationship, is crucial in human thinking.
More than Classification: A Unified Framework for Event Temporal Relation Extraction
After examining the relation definitions in various ETRE tasks, we observe that all relations can be interpreted using the start and end time points of events.
Lawyer LLaMA Technical Report
Specifically, we inject domain knowledge during the continual training stage and teach the model to learn professional skills using properly designed supervised fine-tuning tasks.
A Frustratingly Easy Improvement for Position Embeddings via Random Padding
Since the embeddings of rear positions are updated fewer times than the front position embeddings, the rear ones may not be properly trained.
Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study
Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks.
Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension
We convert KB subgraphs into passages to narrow the gap between KB schemas and questions, which enables our model to benefit from recent advances in multilingual pre-trained language models (MPLMs) and cross-lingual machine reading comprehension (xMRC).
Cross-Lingual Question Answering
Machine Reading Comprehension
Do Charge Prediction Models Learn Legal Theory?
The charge prediction task aims to predict the charge for a case given its fact description.
Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario
Although pretrained language models can generate fluent recipe texts, they fail to truly learn and use the culinary knowledge in a compositional way.
Improve Discourse Dependency Parsing with Contextualized Representations
Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and their relations to the context.
Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED
DocRED is a widely used dataset for document-level relation extraction.
Entailment Graph Learning with Textual Entailment and Soft Transitivity
Typed entailment graphs try to learn the entailment relations between predicates from text and model them as edges between predicate nodes.
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals
We probe PLMs and models with visual signals, including vision-language pretrained models and image synthesis models, on this benchmark, and find that image synthesis models are more capable of learning accurate and consistent spatial knowledge than other models.
Extract, Integrate, Compete: Towards Verification Style Reading Comprehension
In this paper, we present a new verification style reading comprehension dataset named VGaokao from Chinese Language tests of Gaokao.
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences.
Ranked #48 on
Relation Extraction
on DocRED
Exploring Distantly-Labeled Rationales in Neural Network Models
Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales.
Why Machine Reading Comprehension Models Learn Shortcuts?
A thorough empirical analysis shows that MRC models tend to learn shortcut questions earlier than challenging questions, and the high proportions of shortcut questions in training sets hinder models from exploring the sophisticated reasoning skills in the later stage of training.
Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study
Sequential information, a. k. a., orders, is assumed to be essential for processing a sequence with recurrent neural network or convolutional neural network based encoders.
Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
Causal inference is the process of capturing cause-effect relationship among variables.
Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models
Further analysis shows that Lattice-BERT can harness the lattice structures, and the improvement comes from the exploration of redundant information and multi-granularity representations.
Latent Template Induction with Gumbel-CRFs
Learning to control the structure of sentences is a challenging problem in text generation.
Exploring Question-Specific Rewards for Generating Deep Questions
Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing.
Towards Context-Aware Code Comment Generation
Code comments are vital for software maintenance and comprehension, but many software projects suffer from the lack of meaningful and up-to-date comments in practice.
Domain Adaptation for Semantic Parsing
In this paper, we propose a novel semantic parser for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain.
Neighborhood Matching Network for Entity Alignment
This paper presents Neighborhood Matching Network (NMN), a novel entity alignment framework for tackling the structural heterogeneity challenge.
Semantic Graphs for Generating Deep Questions
This paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information of the input passage.
Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment
Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity.
Paraphrase Generation with Latent Bag of Words
Inspired by variational autoencoders with discrete latent structures, in this work, we propose a latent bag of words (BOW) model for paraphrase generation.
Integrating Relation Constraints with Neural Relation Extractors
However, such models often make predictions for each entity pair individually, thus often fail to solve the inconsistency among different predictions, which can be characterized by discrete relation constraints.
Learning to Update Knowledge Graphs by Reading News
News streams contain rich up-to-date information which can be used to update knowledge graphs (KGs).
Easy First Relation Extraction with Information Redundancy
Many existing relation extraction (RE) models make decisions globally using integer linear programming (ILP).
Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems
We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems.
Jointly Learning Entity and Relation Representations for Entity Alignment
Entity alignment is a viable means for integrating heterogeneous knowledge among different knowledge graphs (KGs).
Ranked #18 on
Entity Alignment
on DBP15k zh-en
(using extra training data)
A Sketch-Based System for Semantic Parsing
The sketch is a high-level structure of the logical form exclusive of low-level details such as entities and predicates.
Generating Classical Chinese Poems from Vernacular Chinese
According to experiments, our approach significantly improve the perplexity and BLEU compared with typical UMT models.
Cultural Vocal Bursts Intensity Prediction
Reinforcement Learning
+3
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods.
Ranked #20 on
Entity Alignment
on DBP15k zh-en
(using extra training data)
Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems
Under the framework, we simultaneously learn two matching models with independent training sets.
Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering
However, extending KV-MemNNs to Knowledge Based Question Answering (KB-QA) is not trivia, which should properly decompose a complex question into a sequence of queries against the memory, and update the query representations to support multi-hop reasoning over the memory.
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.
Lattice CNNs for Matching Based Chinese Question Answering
Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words explicitly.
Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach
Relation extraction is the task of identifying predefined relationship between entities, and plays an essential role in information extraction, knowledge base construction, question answering and so on.
To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference
We experimentally show that how two mainstream compression techniques, data quantization and pruning, perform on these network architectures and the implications of compression techniques to the model storage size, inference time, energy consumption and performance metrics.
Overview of CAIL2018: Legal Judgment Prediction Competition
In this paper, we give an overview of the Legal Judgment Prediction (LJP) competition at Chinese AI and Law challenge (CAIL2018).
Multi-grained Attention Network for Aspect-Level Sentiment Classification
We propose a fine-grained attention mechanism, which can capture the word-level interaction between aspect and context.
SQL-to-Text Generation with Graph-to-Sequence Model
Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query.
Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection
In this paper, we study context-response matching with pre-trained contextualized representations for multi-turn response selection in retrieval-based chatbots.
CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
In this paper, we introduce the \textbf{C}hinese \textbf{AI} and \textbf{L}aw challenge dataset (CAIL2018), the first large-scale Chinese legal dataset for judgment prediction.
Modeling discourse cohesion for discourse parsing via memory network
Identifying long-span dependencies between discourse units is crucial to improve discourse parsing performance.
Natural Answer Generation with Heterogeneous Memory
Memory augmented encoder-decoder framework has achieved promising progress for natural language generation tasks.
Marrying up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding
The success of many natural language processing (NLP) tasks is bound by the number and quality of annotated data, but there is often a shortage of such training data.
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings.
Ranked #1 on
SQL-to-Text
on WikiSQL
Scale Up Event Extraction Learning via Automatic Training Data Generation
We show that this large volume of training data not only leads to a better event extractor, but also allows us to detect multiple typed events.
Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems
The study on human-computer conversation systems is a hot research topic nowadays.
Learning to Predict Charges for Criminal Cases with Legal Basis
The charge prediction task is to determine appropriate charges for a given case, which is helpful for legal assistant systems where the user input is fact description.
How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models
Generative conversational systems are attracting increasing attention in natural language processing (NLP).
Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision.
A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification
For word-level studies, words are simplified but also have potential grammar errors due to different usages of words before and after simplification.
Hybrid Question Answering over Knowledge Base and Free Text
While these systems are able to provide more precise answers than information retrieval (IR) based QA systems, the natural incompleteness of KB inevitably limits the question scope that the system can answer.
Question Answering on Freebase via Relation Extraction and Textual Evidence
Existing knowledge-based question answering systems often rely on small annotated training data.
Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
Syntactic features play an essential role in identifying relationship in a sentence.
Ranked #3 on
Relation Classification
on SemEval 2010 Task 8
