Search Results for author:
Found 80 papers, 36 papers with code
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer
Text style transfer aims to change an input sentence to an output sentence by changing its text style while preserving the content.
Instance-adaptive training with noise-robust losses against noisy labels
In order to alleviate the huge demand for annotated datasets for different tasks, many recent natural language processing datasets have adopted automated pipelines for fast-tracking usable data.
Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution
Coreference resolution over semantic graphs like AMRs aims to group the graph nodes that represent the same entity.
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference.
HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving
We introduce HunyuanProver, an language model finetuned from the Hunyuan 7B for interactive automatic theorem proving with LEAN4.
Teaching LLMs to Refine with Tools
We propose CaP, a novel approach that uses external tools to refine chain-of-thought (CoT) responses generated by the same or other LLMs.
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs.
Mitigating the Negative Impact of Over-association for Conversational Query Production
We carefully analyze the negative effects of this phenomenon on pretrained Seq2seq query producers and then propose effective instance-level weighting strategies for training to mitigate these issues from multiple perspectives.
SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding.
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Specifically, we formulate the problem as a two-player game and propose a novel online algorithm, iterative Nash policy optimization (INPO).
LiteSearch: Efficacious Tree Search for LLM
Recent research suggests that tree search algorithms (e. g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks.
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning.
Ranked #1 on
GSM8K
on GSM8K
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Current state-of-the-art approaches refine decoding by contrasting early-exit distributions from a lower layer with the final layer to exploit information related to factuality within the model forward procedure.
Self-Consistency Boosts Calibration for Math Reasoning
Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development.
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
In this paper, we present a high-quality benchmark named multi-source Wizard of Wikipedia (Ms. WoW) for evaluating multi-source dialogue knowledge selection and response generation.
Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent.
Collaborative decoding of critical tokens for boosting factuality of large language models
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model.
Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i. e. "hallucinations", even when they hold relevant knowledge.
Inconsistent dialogue responses and how to recover from them
One critical issue for chat systems is to stay consistent about preferences, opinions, beliefs and facts of itself, which has been shown a difficult problem.
Response Enhanced Semi-supervised Dialogue Query Generation
Based on the observation that the search query is typically related to the topic of dialogue response, we train a response-augmented query producer (RA) to provide rich and effective training signals for QP.
The Trickle-down Impact of Reward (In-)consistency on RLHF
We propose Contrast Instructions -- a benchmarking strategy for the consistency of RM.
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge.
Discrete Conditional Diffusion for Reranking in Recommendation
To overcome these challenges, we propose a novel Discrete Conditional Diffusion Reranking (DCDR) framework for recommendation.
Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation
An accurate prediction of watch time has been of vital importance to enhance user engagement in video recommender systems.
A Survey on Zero Pronoun Translation
Zero pronouns (ZPs) are frequently omitted in pro-drop languages (e. g. Chinese, Hungarian, and Hindi), but should be recalled in non-pro-drop languages (e. g. English).
Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production
We propose a dialogue model that can access the vast and dynamic information from any search engine for response generation.
Friend-training: Learning from Models of Different but Related Tasks
Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes.
Getting the Most out of Simile Recognition
Simile recognition involves two subtasks: simile sentence classification that discriminates whether a sentence contains simile, and simile component extraction that locates the corresponding objects (i. e., tenors and vehicles).
Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing
Pretrained natural language processing (NLP) models have achieved high overall performance, but they still make systematic errors.
Cross-domain Generalization for AMR Parsing
Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively.
Learning a Grammar Inducer from Massive Uncurated Instructional Videos
While previous work focuses on building systems for inducing grammars on text that are well-aligned with video content, we investigate the scenario, in which text and video are only in loose correspondence.
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
We first design a SQL-to-text model conditioned on a sampled goal query, which represents a user's intent, that then converses with a text-to-SQL semantic parser to generate new interactions.
Semantic-based Pre-training for Dialogue Understanding
However, these models are typically trained on surface dialogue text, thus are proven to be weak in understanding the main semantic meaning of a dialogue context.
Hierarchical Context Tagging for Utterance Rewriting
HCT (i) tags the source string with token-level edit actions and slotted rules and (ii) fills in the resulting rule slots with spans from the dialogue context.
An Empirical Study of Retrieval-enhanced Graph Neural Networks
Graph Neural Networks (GNNs) are effective tools for graph representation learning.
Distant finetuning with discourse relations for stance classification
Approaches for the stance classification task, an important task for understanding argumentation in debates and detecting fake news, have been relying on models which deal with individual debate topics.
End-to-End AMR Coreference Resolution
Although parsing to Abstract Meaning Representation (AMR) has become very popular and AMR has been shown effective on the many sentence-level downstream tasks, little work has studied how to generate AMRs that can represent multi-sentence information.
TexSmart: A System for Enhanced Natural Language Understanding
This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues
Conversational discourse structures aim to describe how a dialogue is organised, thus they are helpful for dialogue understanding and response generation.
Ranked #3 on
Discourse Parsing
on STAC
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments.
Ranked #1 on
KG-to-Text Generation
on WebQuestions
Domain-Adaptive Pretraining Methods for Dialogue Understanding
Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks.
Semantic Representation for Dialogue Modeling
Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities.
Ranked #8 on
Dialog Relation Extraction
on DialogRE
Abstract Meaning Representation
Dialog Relation Extraction
+3
Conversational Semantic Role Labeling
Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence.
Video-aided Unsupervised Grammar Induction
We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video.
Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning
In aspect-based sentiment analysis (ABSA), many neural models are equipped with an attention mechanism to quantify the contribution of each context word to sentiment prediction.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Structural Information Preserving for Graph-to-Text Generation
The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs.
Ranked #10 on
Data-to-Text Generation
on WebNLG
TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Robust Dialogue Utterance Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
Online Back-Parsing for AMR-to-Text Generation
AMR-to-text generation aims to recover a text containing the same meaning as an input AMR graph.
Ranked #9 on
AMR-to-Text Generation
on LDC2017T10
Semantic Role Labeling Guided Multi-turn Dialogue ReWriter
For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance.
ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT
Zero pronoun recovery and resolution aim at recovering the dropped pronoun and pointing out its anaphoric mentions, respectively.
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.
Neural Simile Recognition with Cyclic Multitask Learning and Local Attention
Simile recognition is to detect simile sentences and to extract simile components, i. e., tenors and vehicles.
Graph-based Neural Sentence Ordering
Sentence ordering is to restore the original paragraph from a set of sentences.
Leveraging Dependency Forest for Neural Medical Relation Extraction
Medical relation extraction discovers relations between entity mentions in text, such as research articles.
Multi-Granular Text Encoding for Self-Explaining Categorization
Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence.
Tackling Graphical NLP problems with Graph Recurrent Networks
How to properly model graphs is a long-existing and important problem in NLP area, where several popular types of graphs are knowledge graphs, semantic graphs and dependency graphs.
Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning
However, most neural collective EL methods depend entirely upon neural networks to automatically model the semantic dependencies between different EL decisions, which lack of the guidance from external knowledge.
Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis
In aspect-level sentiment classification (ASC), it is prevalent to equip dominant neural models with attention mechanisms, for the sake of acquiring the importance of each context word on the given aspect.
Aspect-Based Sentiment Analysis (ABSA)
Sentiment Classification
SemBleu: A Robust Metric for AMR Parsing Evaluation
Evaluating AMR parsing accuracy involves comparing pairs of AMR graphs.
Ranked #3 on
Graph Matching
on RARE
Semantic Neural Machine Translation using AMR
It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models.
Neural Transition-based Syntactic Linearization
The task of linearization is to find a grammatical order given a set of words.
N-ary Relation Extraction using Graph-State LSTM
Cross-sentence $n$-ary relation extraction detects relations among $n$ entities across multiple sentences.
Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question.
Ranked #2 on
Question Answering
on COMPLEXQUESTIONS
N-ary Relation Extraction using Graph State LSTM
Cross-sentence $n$-ary relation extraction detects relations among $n$ entities across multiple sentences.
Sequence-to-sequence Models for Cache Transition Systems
In this paper, we present a sequence-to-sequence based approach for mapping natural language sentences to AMR semantic graphs.
Leveraging Context Information for Natural Question Generation
The task of natural question generation is to generate a corresponding question given the input passage (fact) and answer.
Ranked #11 on
Question Generation
on SQuAD1.1
A Graph-to-Sequence Model for AMR-to-Text Generation
The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph.
Ranked #1 on
Graph-to-Sequence
on LDC2015E86:
(using extra training data)
Sentence-State LSTM for Text Representation
Bi-directional LSTMs are a powerful tool for text representation.
Ranked #10 on
Part-Of-Speech Tagging
on Penn Treebank
A Unified Query-based Generative Model for Question Generation and Question Answering
In the QG task, a question is generated from the system given the passage and the target answer, whereas in the QA task, the answer is generated given the question and the passage.
$k$-Nearest Neighbor Augmented Neural Networks for Text Classification
However, it lacks the capacity of utilizing instance-level information from individual instances in the training set.
AMR-to-text Generation with Synchronous Node Replacement Grammar
This paper addresses the task of AMR-to-text generation by leveraging synchronous node replacement grammar.
Question Generation from a Knowledge Base with Web Exploration
Question generation from a knowledge base (KB) is the task of generating questions related to the domain of the input KB.
AMR-to-text generation as a Traveling Salesman Problem
The task of AMR-to-text generation is to generate grammatical text that sustains the semantic meaning for a given AMR graph.
Sense Embedding Learning for Word Sense Induction
In the training stage, our method induces several sense centroids (embedding) for each polysemous word.
Ranked #4 on
Word Sense Induction
on SemEval 2010 WSI
