Search Results for author: Le Sun

Found 71 papers, 32 papers with code

ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

no code implementations8 Jun 2023 Qiaoyu Tang, Ziliang Deng, Hongyu Lin, Xianpei Han, Qiao Liang, Le Sun

This validation supports the notion that learning generalized tool-use abilities is feasible for compact language models.

Learning In-context Learning for Named Entity Recognition

1 code implementation18 May 2023 Jiawei Chen, Yaojie Lu, Hongyu Lin, Jie Lou, Wei Jia, Dai Dai, Hua Wu, Boxi Cao, Xianpei Han, Le Sun

M}$, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i. e., $\mathcal{ (\lambda .

few-shot-ner Few-shot NER +3

DLUE: Benchmarking Document Language Understanding

no code implementations16 May 2023 Ruoxi Xu, Hongyu Lin, Xinyan Guan, Xianpei Han, Yingfei Sun, Le Sun

Understanding documents is central to many real-world tasks but remains a challenging topic.

Benchmarking Document Classification

Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models

no code implementations16 May 2023 Boxi Cao, Qiaoyu Tang, Hongyu Lin, Xianpei Han, Jiawei Chen, Tianshu Wang, Le Sun

Memory is one of the most essential cognitive functions serving as a repository of world knowledge and episodes of activities.

Harvesting Event Schemas from Large Language Models

1 code implementation12 May 2023 Jialong Tang, Hongyu Lin, Zhuoqun Li, Yaojie Lu, Xianpei Han, Le Sun

Event schema provides a conceptual, structural and formal language to represent events and model the world event knowledge.

A Drop of Ink Makes a Million Think: The Spread of False Information in Large Language Models

no code implementations8 May 2023 Ning Bian, Peilin Liu, Xianpei Han, Hongyu Lin, Yaojie Lu, Ben He, Le Sun

Large language models (LLMs) have gained increasing prominence in artificial intelligence, making a profound impact on society and various industries like business and science.

Towards Imperceptible Document Manipulations against Neural Ranking Models

no code implementations3 May 2023 Xuanang Chen, Ben He, Zheng Ye, Le Sun, Yingfei Sun

Additionally, current methods rely heavily on the use of a well-imitated surrogate NRM to guarantee the attack effect, which makes them difficult to use in practice.

Adversarial Text Language Modelling +1

Understanding Differential Search Index for Text Retrieval

1 code implementation3 May 2023 Xiaoyang Chen, Yanjiang Liu, Ben He, Le Sun, Yingfei Sun

The Differentiable Search Index (DSI) is a novel information retrieval (IR) framework that utilizes a differentiable function to generate a sorted list of document identifiers in response to a given query.

Information Retrieval Retrieval +1

The Life Cycle of Knowledge in Big Language Models: A Survey

1 code implementation14 Mar 2023 Boxi Cao, Hongyu Lin, Xianpei Han, Le Sun

Knowledge plays a critical role in artificial intelligence.

Semantic-aware Contrastive Learning for More Accurate Semantic Parsing

no code implementations19 Jan 2023 Shan Wu, Chunlei Xin, Bo Chen, Xianpei Han, Le Sun

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an autoregressive fashion.

Contrastive Learning Semantic Parsing

Universal Information Extraction as Unified Semantic Matching

no code implementations9 Jan 2023 Jie Lou, Yaojie Lu, Dai Dai, Wei Jia, Hongyu Lin, Xianpei Han, Le Sun, Hua Wu

Based on this paradigm, we propose to universally model various IE tasks with Unified Semantic Matching (USM) framework, which introduces three unified token linking operations to model the abilities of structuring and conceptualizing.

Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction

no code implementations12 May 2022 Tianshu Wang, Hongyu Lin, Cheng Fu, Xianpei Han, Le Sun, Feiyu Xiong, Hui Chen, Minlong Lu, Xiuwen Zhu

Experimental results demonstrate that the assumptions made in the previous benchmark construction process are not coincidental with the open environment, which conceal the main challenges of the task and therefore significantly overestimate the current progress of entity matching.

Entity Resolution

Groupwise Query Performance Prediction with BERT

1 code implementation25 Apr 2022 Xiaoyang Chen, Ben He, Le Sun

While large-scale pre-trained language models like BERT have advanced the state-of-the-art in IR, its application in query performance prediction (QPP) is so far based on pointwise modeling of individual queries.

Learning-To-Rank Re-Ranking

Few-shot Named Entity Recognition with Self-describing Networks

1 code implementation ACL 2022 Jiawei Chen, Qing Liu, Hongyu Lin, Xianpei Han, Le Sun

In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set.

Few-shot NER Named Entity Recognition

Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View

1 code implementation ACL 2022 Boxi Cao, Hongyu Lin, Xianpei Han, Fangchao Liu, Le Sun

Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs).

Pre-training to Match for Unified Low-shot Relation Extraction

1 code implementation ACL 2022 Fangchao Liu, Hongyu Lin, Xianpei Han, Boxi Cao, Le Sun

Low-shot relation extraction~(RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application.

Meta-Learning Relation Extraction

Procedural Text Understanding via Scene-Wise Evolution

no code implementations15 Mar 2022 Jialong Tang, Hongyu Lin, Meng Liao, Yaojie Lu, Xianpei Han, Le Sun, Weijian Xie, Jin Xu

In this paper, we propose a new \textbf{scene-wise} paradigm for procedural text understanding, which jointly tracks states of all entities in a scene-by-scene manner.

Procedural Text Understanding

Fine-grained Entity Typing via Label Reasoning

no code implementations EMNLP 2021 Qing Liu, Hongyu Lin, Xinyan Xiao, Xianpei Han, Le Sun, Hua Wu

Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types.

Entity Typing

Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention

1 code implementation EMNLP 2021 Jiawei Chen, Hongyu Lin, Xianpei Han, Le Sun

In this paper, we identify and solve the trigger curse problem in few-shot event detection (FSED) from a causal view.

Event Detection

Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model

1 code implementation17 Jun 2021 Wenkai Zhang, Hongyu Lin, Xianpei Han, Le Sun, Huidan Liu, Zhicheng Wei, Nicholas Jing Yuan

Specifically, during neural network training, we naturally model the noise samples in each batch following a hypergeometric distribution parameterized by the noise-rate.

Denoising named-entity-recognition +2

Element Intervention for Open Relation Extraction

no code implementations ACL 2021 Fangchao Liu, Lingyong Yan, Hongyu Lin, Xianpei Han, Le Sun

Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction.

Relation Extraction

Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases

1 code implementation ACL 2021 Boxi Cao, Hongyu Lin, Xianpei Han, Le Sun, Lingyong Yan, Meng Liao, Tong Xue, Jin Xu

Previous literatures show that pre-trained masked language models (MLMs) such as BERT can achieve competitive factual knowledge extraction performance on some datasets, indicating that MLMs can potentially be a reliable knowledge source.

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding

no code implementations ACL 2021 Shan Wu, Bo Chen, Chunlei Xin, Xianpei Han, Le Sun, Weipeng Zhang, Jiansong Chen, Fan Yang, Xunliang Cai

During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly.

Unsupervised semantic parsing

Co-BERT: A Context-Aware BERT Retrieval Model Incorporating Local and Query-specific Context

no code implementations17 Apr 2021 Xiaoyang Chen, Kai Hui, Ben He, Xianpei Han, Le Sun, Zheng Ye

BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently.

Learning-To-Rank Re-Ranking +1

Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning

1 code implementation5 Mar 2021 Jinsong Su, Jialong Tang, Hui Jiang, Ziyao Lu, Yubin Ge, Linfeng Song, Deyi Xiong, Le Sun, Jiebo Luo

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 (ABSA)

Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation

no code implementations4 Jan 2021 Ning Bian, Xianpei Han, Bo Chen, Le Sun

Experiments show that: (1) Our knowledge-to-text framework is effective and achieves state-of-the-art performance on CommonsenseQA dataset, providing a simple and strong knowledge-enhanced baseline for CQA; (2) The potential of knowledge is still far from being fully exploited in CQA -- there is a significant performance gap from current models to our models with golden knowledge; and (3) Context-sensitive knowledge selection, heterogeneous knowledge exploitation, and commonsense-rich language models are promising CQA directions.

Benchmarking Question Answering

From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension

1 code implementation8 Dec 2020 Lingyong Yan, Xianpei Han, Le Sun, Fangchao Liu, Ning Bian

By re-organizing all sentences about an entity as a document and extracting relations via querying the document with relation-specific questions, the document-based DS paradigm can simultaneously encode and exploit all sentence-level, inter-sentence-level, and entity-level evidence.

Denoising Machine Reading Comprehension +1

Global Bootstrapping Neural Network for Entity Set Expansion

1 code implementation Findings of the Association for Computational Linguistics 2020 Lingyong Yan, Xianpei Han, Ben He, Le Sun

Bootstrapping for entity set expansion (ESE) has been studied for a long period, which expands new entities using only a few seed entities as supervision.

ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling

1 code implementation SEMEVAL 2020 Yaojie Lu, Annan Li, Hongyu Lin, Xianpei Han, Le Sun

ISCAS participated in two subtasks of SemEval 2020 Task 5: detecting counterfactual statements and detecting antecedent and consequence.

Question Answering

End-to-End Neural Event Coreference Resolution

1 code implementation17 Sep 2020 Yaojie Lu, Hongyu Lin, Jialong Tang, Xianpei Han, Le Sun

Traditional event coreference systems usually rely on pipeline framework and hand-crafted features, which often face error propagation problem and have poor generalization ability.

coreference-resolution Coreference Resolution +2

Simplified TinyBERT: Knowledge Distillation for Document Retrieval

2 code implementations16 Sep 2020 Xuanang Chen, Ben He, Kai Hui, Le Sun, Yingfei Sun

Despite the effectiveness of utilizing the BERT model for document ranking, the high computational cost of such approaches limits their uses.

Document Ranking Knowledge Distillation +1

A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?

no code implementations EMNLP 2020 Hongyu Lin, Yaojie Lu, Jialong Tang, Xianpei Han, Le Sun, Zhicheng Wei, Nicholas Jing Yuan

Specifically, we erase name regularity, mention coverage and context diversity respectively from the benchmarks, in order to explore their impact on the generalization ability of models.

named-entity-recognition Named Entity Recognition +1

Gazetteer-Enhanced Attentive Neural Networks for Named Entity Recognition

no code implementations IJCNLP 2019 Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun, Bin Dong, Shanshan Jiang

Current region-based NER models only rely on fully-annotated training data to learn effective region encoder, which often face the training data bottleneck.

named-entity-recognition Named Entity Recognition +1

Learning to Bootstrap for Entity Set Expansion

no code implementations IJCNLP 2019 Lingyong Yan, Xianpei Han, Le Sun, Ben He

Bootstrapping for Entity Set Expansion (ESE) aims at iteratively acquiring new instances of a specific target category.

EUSP: An Easy-to-Use Semantic Parsing PlatForm

no code implementations IJCNLP 2019 Bo An, Chen Bo, Xianpei Han, Le Sun

Semantic parsing aims to map natural language utterances into structured meaning representations.

Semantic Parsing

Distilling Discrimination and Generalization Knowledge for Event Detection via Delta-Representation Learning

1 code implementation ACL 2019 Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Event detection systems rely on discrimination knowledge to distinguish ambiguous trigger words and generalization knowledge to detect unseen/sparse trigger words.

Event Detection Representation Learning

Cost-sensitive Regularization for Label Confusion-aware Event Detection

1 code implementation ACL 2019 Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type.

Event Detection Vocal Bursts Type Prediction

Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks

1 code implementation ACL 2019 Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

In this paper, we propose to resolve this problem by modeling and leveraging the head-driven phrase structures of entity mentions, i. e., although a mention can nest other mentions, they will not share the same head word.

NER Nested Mention Recognition +1

Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis

1 code implementation ACL 2019 Jialong Tang, Ziyao Lu, Jinsong Su, Yubin Ge, Linfeng Song, Le Sun, Jiebo Luo

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

Sentence Rewriting for Semantic Parsing

no code implementations ACL 2016 Bo Chen, Le Sun, Xianpei Han, Bo An

A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology.

Semantic Parsing Sentence ReWriting

NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval

1 code implementation EMNLP 2018 Canjia Li, Yingfei Sun, Ben He, Le Wang, Kai Hui, Andrew Yates, Le Sun, Jungang Xu

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document vocabulary mismatches.

Ad-Hoc Information Retrieval Information Retrieval +1

Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing

1 code implementation ACL 2018 Bo Chen, Le Sun, Xianpei Han

This paper proposes a neural semantic parsing approach -- Sequence-to-Action, which models semantic parsing as an end-to-end semantic graph generation process.

Graph Generation Representation Learning +1

Model-Free Context-Aware Word Composition

no code implementations COLING 2018 Bo An, Xianpei Han, Le Sun

Word composition is a promising technique for representation learning of large linguistic units (e. g., phrases, sentences and documents).

Dimensionality Reduction Learning Word Embeddings +3

Accurate Text-Enhanced Knowledge Graph Representation Learning

no code implementations NAACL 2018 Bo An, Bo Chen, Xianpei Han, Le Sun

Previous representation learning techniques for knowledge graph representation usually represent the same entity or relation in different triples with the same representation, without considering the ambiguity of relations and entities.

General Classification Graph Representation Learning +3

Adaptive Scaling for Sparse Detection in Information Extraction

1 code implementation ACL 2018 Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

This paper focuses on detection tasks in information extraction, where positive instances are sparsely distributed and models are usually evaluated using F-measure on positive classes.

Nugget Proposal Networks for Chinese Event Detection

1 code implementation ACL 2018 Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

Neural network based models commonly regard event detection as a word-wise classification task, which suffer from the mismatch problem between words and event triggers, especially in languages without natural word delimiters such as Chinese.

Event Detection General Classification

Investigating the content and form of referring expressions in Mandarin: introducing the Mtuna corpus

no code implementations WS 2017 Kees van Deemter, Le Sun, Rint Sybesma, Xiao Li, Bo Chen, Muyun Yang

East Asian languages are thought to handle reference differently from languages such as English, particularly in terms of the marking of definiteness and number.

Text Generation

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

no code implementations EMNLP 2017 Hongyu Lin, Le Sun, Xianpei Han

Then we propose a multi-knowledge reasoning model, which selects inference rules for a specific reasoning context using attention mechanism, and reasons by summarizing all valid inference rules.

Natural Language Understanding Reading Comprehension

Context-Sensitive Inference Rule Discovery: A Graph-Based Method

no code implementations COLING 2016 Xianpei Han, Le Sun

Firstly, these methods are mostly context-insensitive, cannot accurately measure the similarity between two predicates in a specific context.

Natural Language Inference Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.