Search Results for author: Weiming Lu

Found 35 papers, 19 papers with code

De-Bias for Generative Extraction in Unified NER Task

no code implementations ACL 2022 Shuai Zhang, Yongliang Shen, Zeqi Tan, Yiquan Wu, Weiming Lu

Named entity recognition (NER) is a fundamental task to recognize specific types of entities from a given sentence.

Attribute Data Augmentation +4

ProSwitch: Knowledge-Guided Language Model Fine-Tuning to Generate Professional and Non-Professional Styled Text

no code implementations14 Mar 2024 Chang Zong, Yuyan Chen, Weiming Lu, Jian Shao, Yueting Zhuang

Large Language Models (LLMs) have demonstrated efficacy in various linguistic applications, including text summarization and controlled text generation.

Language Modelling Text Generation +1

Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering

no code implementations22 Feb 2024 Chang Zong, Yuchen Yan, Weiming Lu, Eliot Huang, Jian Shao, Yueting Zhuang

We evaluated the performance of our framework using three benchmark datasets, and the results show that our framework outperforms state-of-the-art systems on the LC-QuAD and YAGO-QA benchmarks, yielding F1 scores of 11. 8% and 20. 7%, respectively.

Knowledge Base Question Answering

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives

no code implementations4 Jan 2024 Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, Weiming Lu

Experiments conducted on a series of reasoning and translation tasks with different LLMs serve to underscore the effectiveness and generality of our strategy.

Language Modelling Large Language Model

An Expression Tree Decoding Strategy for Mathematical Equation Generation

no code implementations14 Oct 2023 Wenqi Zhang, Yongliang Shen, Qingpeng Nong, Zeqi Tan, Yanna Ma, Weiming Lu

To generate a tree with expression as its node, we employ a layer-wise parallel decoding strategy: we decode multiple independent expressions (leaf nodes) in parallel at each layer and repeat parallel decoding layer by layer to sequentially generate these parent node expressions that depend on others.

Math Math Word Problem Solving +1

Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration

no code implementations13 Oct 2023 Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, Kun Kuang

Precedents are the previous legal cases with similar facts, which are the basis for the judgment of the subsequent case in national legal systems.

MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition

1 code implementation12 Oct 2023 Shuhui Wu, Yongliang Shen, Zeqi Tan, Wenqi Ren, Jietian Guo, ShiLiang Pu, Weiming Lu

Distantly supervised named entity recognition (DS-NER) aims to locate entity mentions and classify their types with only knowledge bases or gazetteers and unlabeled corpus.

named-entity-recognition Named Entity Recognition +1

PUMGPT: A Large Vision-Language Model for Product Understanding

no code implementations18 Aug 2023 Shuhui Wu, Zengming Tang, Zongyi Guo, Weiwei Zhang, Baoliang Cui, Haihong Tang, Weiming Lu

Simultaneously, we utilize open-domain datasets during training to improve the performance of PUMGPT and its generalization ability.

Attribute Attribute Extraction +2

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

1 code implementation12 Jun 2023 Wenqi Zhang, Yongliang Shen, Weiming Lu, Yueting Zhuang

Various industries such as finance, meteorology, and energy generate vast amounts of heterogeneous data every day.

DiffusionNER: Boundary Diffusion for Named Entity Recognition

2 code implementations22 May 2023 Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang

In this paper, we propose DiffusionNER, which formulates the named entity recognition task as a boundary-denoising diffusion process and thus generates named entities from noisy spans.

Chinese Named Entity Recognition Denoising +4

Taxonomy Completion with Probabilistic Scorer via Box Embedding

1 code implementation18 May 2023 Wei Xue, Yongliang Shen, Wenqi Ren, Jietian Guo, ShiLiang Pu, Weiming Lu

Specifically, TaxBox consists of three components: (1) a graph aggregation module to leverage the structural information of the taxonomy and two lightweight decoders that map features to box embedding and capture complex relationships between concepts; (2) two probabilistic scorers that correspond to attachment and insertion operations and ensure the avoidance of pseudo-leaves; and (3) three learning objectives that assist the model in mapping concepts more granularly onto the box embedding space.

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

1 code implementation NeurIPS 2023 Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang

Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence.


Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem

1 code implementation21 Oct 2022 Wenqi Zhang, Yongliang Shen, Yanna Ma, Xiaoxia Cheng, Zeqi Tan, Qingpeng Nong, Weiming Lu

Math word problem solver requires both precise relation reasoning about quantities in the text and reliable generation for the diverse equation.

 Ranked #1 on Math Word Problem Solving on Math23K (using extra training data)

Contrastive Learning Math +3

Citation Trajectory Prediction via Publication Influence Representation Using Temporal Knowledge Graph

no code implementations2 Oct 2022 Chang Zong, Yueting Zhuang, Weiming Lu, Jian Shao, Siliang Tang

In this paper, we propose CTPIR, a new citation trajectory prediction framework that is able to represent the influence (the momentum of citation) of either new or existing publications using the history information of all their attributes.

Attribute Graph Embedding +1

Molecular Substructure-Aware Network for Drug-Drug Interaction Prediction

1 code implementation24 Aug 2022 Xinyu Zhu, Yongliang Shen, Weiming Lu

Concomitant administration of drugs can cause drug-drug interactions (DDIs).

Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt

no code implementations16 May 2022 Xinyin Ma, Xinchao Wang, Gongfan Fang, Yongliang Shen, Weiming Lu

Data-free knowledge distillation (DFKD) conducts knowledge distillation via eliminating the dependence of original training data, and has recently achieved impressive results in accelerating pre-trained language models.

Data-free Knowledge Distillation

Propose-and-Refine: A Two-Stage Set Prediction Network for Nested Named Entity Recognition

1 code implementation27 Apr 2022 Shuhui Wu, Yongliang Shen, Zeqi Tan, Weiming Lu

In the refine stage, proposals interact with each other, and richer contextual information is incorporated into the proposal representations.

named-entity-recognition Named Entity Recognition +3

MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations

1 code implementation EMNLP 2021 Xinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Weiming Lu

Entity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing.

Entity Linking Entity Retrieval +1

Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational Data

no code implementations NAACL 2021 Chenghao Jia, Yongliang Shen, Yechun Tang, Lu Sun, Weiming Lu

Prerequisite relations among concepts are crucial for educational applications, such as curriculum planning and intelligent tutoring.


A Sequence-to-Set Network for Nested Named Entity Recognition

1 code implementation19 May 2021 Zeqi Tan, Yongliang Shen, Shuai Zhang, Weiming Lu, Yueting Zhuang

We utilize a non-autoregressive decoder to predict the final set of entities in one pass, in which we are able to capture dependencies between entities.

named-entity-recognition Named Entity Recognition +2

Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition

1 code implementation ACL 2021 Yongliang Shen, Xinyin Ma, Zeqi Tan, Shuai Zhang, Wen Wang, Weiming Lu

Although these methods have the innate ability to handle nested NER, they suffer from high computational cost, ignorance of boundary information, under-utilization of the spans that partially match with entities, and difficulties in long entity recognition.

Chinese Named Entity Recognition named-entity-recognition +3

A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction

1 code implementation25 Jan 2021 Yongliang Shen, Xinyin Ma, Yechun Tang, Weiming Lu

Joint entity and relation extraction framework constructs a unified model to perform entity recognition and relation extraction simultaneously, which can exploit the dependency between the two tasks to mitigate the error propagation problem suffered by the pipeline model.

 Ranked #1 on Relation Extraction on CoNLL04 (NER Micro F1 metric)

Joint Entity and Relation Extraction Reading Comprehension +2

Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network

no code implementations11 Jun 2020 Zeyun Tang, Yongliang Shen, Xinyin Ma, Wei Xu, Jiale Yu, Weiming Lu

Meanwhile, we propose Gated-RGCN to accumulate evidence on the path-based reasoning graph, which contains a new question-aware gating mechanism to regulate the usefulness of information propagating across documents and add question information during reasoning.

Multi-Hop Reading Comprehension

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