Search Results for author: Deyu Zhou

Found 43 papers, 9 papers with code

Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge

no code implementations ACL 2022 Linhai Zhang, Xuemeng Hu, Boyu Wang, Deyu Zhou, Qian-Wen Zhang, Yunbo Cao

Recent years have witnessed growing interests in incorporating external knowledge such as pre-trained word embeddings (PWEs) or pre-trained language models (PLMs) into neural topic modeling.

Topic Models Word Embeddings

Implicit Sentiment Analysis with Event-centered Text Representation

no code implementations EMNLP 2021 Deyu Zhou, Jianan Wang, Linhai Zhang, Yulan He

Implicit sentiment analysis, aiming at detecting the sentiment of a sentence without sentiment words, has become an attractive research topic in recent years.

Representation Learning Sentence +1

Temporal Knowledge Graph Completion with Approximated Gaussian Process Embedding

no code implementations COLING 2022 Linhai Zhang, Deyu Zhou

Due to their incompleteness, a fundamental task for KGs, which is known as Knowledge Graph Completion (KGC), is to perform link prediction and infer new facts based on the known facts.

Gaussian Processes Link Prediction +2

Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity

no code implementations10 Mar 2024 Xin Zhang, Linhai Zhang, Deyu Zhou, Guoqiang Xu

Due to the sparsity of user data, sentiment analysis on user reviews in e-commerce platforms often suffers from poor performance, especially when faced with extremely sparse user data or long-tail labels.

Attribute Sentiment Analysis

Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment

no code implementations5 Mar 2024 Congzhi Zhang, Linhai Zhang, Jialong Wu, Deyu Zhou, Yulan He

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases.

Contrastive Learning Data Augmentation +3

Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment

1 code implementation5 Mar 2024 Congzhi Zhang, Linhai Zhang, Deyu Zhou

Conventional multi-hop fact verification models are prone to rely on spurious correlations from the annotation artifacts, leading to an obvious performance decline on unbiased datasets.

Causal Inference counterfactual +4

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models

1 code implementation2 Mar 2024 Linhai Zhang, Jialong Wu, Deyu Zhou, Guoqiang Xu

For poor model calibration, we incorporate the regularization method during LoRA training to keep the model from being over-confident, and the Monte-Carlo dropout mechanism is employed to enhance the uncertainty estimation.

Active Learning Few-Shot Learning

DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference

1 code implementation2 Mar 2024 Jialong Wu, Linhai Zhang, Deyu Zhou, Guoqiang Xu

However, most of the present debiasing methods focus on single-variable causal inference, which is not suitable for ABSA with two input variables (the target aspect and the review).

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3

EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification

1 code implementation23 Oct 2023 Yingjie Zhu, Jiasheng Si, Yibo Zhao, Haiyang Zhu, Deyu Zhou, Yulan He

Experimental results show that the proposed approach outperforms the SOTA baselines and can generate linguistically diverse counterfactual data without disrupting their logical relationships.

counterfactual Data Augmentation +1

Explainable Topic-Enhanced Argument Mining from Heterogeneous Sources

no code implementations22 Jul 2023 Jiasheng Si, Yingjie Zhu, Xingyu Shi, Deyu Zhou, Yulan He

Specifically, with the use of the neural topic model and the language model, the target information is augmented by explainable topic representations.

Argument Mining Language Modelling +1

Feature Representation Learning for NL2SQL Generation Based on Coupling and Decoupling

no code implementations30 Jun 2023 Chenduo Hao, Xu Zhang, Chuanbao Gao, Deyu Zhou

To address this issue, we propose the Clause Feature Correlation Decoupling and Coupling (CFCDC) model, which uses a feature representation decoupling method to separate the SELECT and WHERE clauses at the parameter level.

Feature Correlation Multi-Task Learning +3

Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification

no code implementations16 May 2023 Jiasheng Si, Yingjie Zhu, Deyu Zhou

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity.

Fact Verification Sentence

Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning

no code implementations2 Dec 2022 Jiasheng Si, Yingjie Zhu, Deyu Zhou

In specific, GCN is utilized to incorporate the topological interaction information among multiple pieces of evidence for learning evidence representation.

Fact Verification Graph Learning

SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition

1 code implementation COLING 2022 Zeng Yang, Linhai Zhang, Deyu Zhou

Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used.

Few-shot NER Low Resource Named Entity Recognition +2

Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verification

1 code implementation ACL 2021 Jiasheng Si, Deyu Zhou, Tongzhe Li, Xingyu Shi, Yulan He

To alleviate the above issues, we propose a novel topic-aware evidence reasoning and stance-aware aggregation model for more accurate fact verification, with the following four key properties: 1) checking topical consistency between the claim and evidence; 2) maintaining topical coherence among multiple pieces of evidence; 3) ensuring semantic similarity between the global topic information and the semantic representation of evidence; 4) aggregating evidence based on their implicit stances to the claim.

Fact Verification Semantic Similarity +1

Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection

1 code implementation ACL 2021 Lixing Zhu, Gabriele Pergola, Lin Gui, Deyu Zhou, Yulan He

Emotion detection in dialogues is challenging as it often requires the identification of thematic topics underlying a conversation, the relevant commonsense knowledge, and the intricate transition patterns between the affective states.

Decoder Emotion Recognition in Conversation

Variational Gaussian Topic Model with Invertible Neural Projections

no code implementations21 May 2021 Rui Wang, Deyu Zhou, Yuxuan Xiong, Haiping Huang

Based on the variational auto-encoder, the proposed VaGTM models each topic with a multivariate Gaussian in decoder to incorporate word relatedness.

Decoder Topic Models +1

Neural Topic Modeling by Incorporating Document Relationship Graph

no code implementations EMNLP 2020 Deyu Zhou, Xuemeng Hu, Rui Wang

Graph Neural Networks (GNNs) that capture the relationships between graph nodes via message passing have been a hot research direction in the natural language processing community.

A Neural Generative Model for Joint Learning Topics and Topic-Specific Word Embeddings

1 code implementation11 Aug 2020 Lixing Zhu, Yulan He, Deyu Zhou

We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings.

Sentiment Analysis Sentiment Classification +4

Neural Temporal Opinion Modelling for Opinion Prediction on Twitter

no code implementations ACL 2020 Lixing Zhu, Yulan He, Deyu Zhou

Opinion prediction on Twitter is challenging due to the transient nature of tweet content and neighbourhood context.

Neural Topic Modeling with Bidirectional Adversarial Training

1 code implementation ACL 2020 Rui Wang, Xuemeng Hu, Deyu Zhou, Yulan He, Yuxuan Xiong, Chenchen Ye, Haiyang Xu

Recent years have witnessed a surge of interests of using neural topic models for automatic topic extraction from text, since they avoid the complicated mathematical derivations for model inference as in traditional topic models such as Latent Dirichlet Allocation (LDA).

Clustering Text Clustering +1

Interpretable Relevant Emotion Ranking with Event-Driven Attention

no code implementations IJCNLP 2019 Yang Yang, Deyu Zhou, Yulan He, Meng Zhang

Unveiling the hidden event information can help to understand how the emotions are evoked and provide explainable results.

Variational Conditional GAN for Fine-grained Controllable Image Generation

no code implementations22 Sep 2019 Mingqi Hu, Deyu Zhou, Yulan He

In this paper, we propose a novel variational generator framework for conditional GANs to catch semantic details for improving the generation quality and diversity.

Image Generation Variational Inference

Open Event Extraction from Online Text using a Generative Adversarial Network

no code implementations IJCNLP 2019 Rui Wang, Deyu Zhou, Yulan He

Experimental results show that our model outperforms the baseline approaches on all the datasets, with more significant improvements observed on the news article dataset where an increase of 15\% is observed in F-measure.

Event Extraction Generative Adversarial Network

ATM:Adversarial-neural Topic Model

no code implementations1 Nov 2018 Rui Wang, Deyu Zhou, Yulan He

The proposed ATM models topics with Dirichlet prior and employs a generator network to capture the semantic patterns among latent topics.

Event Extraction Topic Models

Relevant Emotion Ranking from Text Constrained with Emotion Relationships

no code implementations NAACL 2018 Deyu Zhou, Yang Yang, Yulan He

As such, emotion detection, to predict multiple emotions associated with a given text, can be cast into a multi-label classification problem.

Multi-Label Classification Multi-Label Learning +1

Neural Storyline Extraction Model for Storyline Generation from News Articles

no code implementations NAACL 2018 Deyu Zhou, Linsen Guo, Yulan He

To tackle this problem, approaches based on probabilistic graphic models jointly model the generations of events and storylines without the use of annotated data.

Topic Models

Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings

no code implementations EACL 2017 Deyu Zhou, Xuan Zhang, Yulan He

To extract structured representations of newsworthy events from Twitter, unsupervised models typically assume that tweets involving the same named entities and expressed using similar words are likely to belong to the same event.

Event Extraction Word Embeddings

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