检索结果-内蒙古大学图书馆

Knowledge-enriched joint-learning model for implicit emotion cause extraction

CAAI Transactions on Intelligence Technology 2023年第1期8卷 118-128页

作者： Chenghao Wu Shumin Shi Jiaxing Hu Heyan Huang School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications BeijingChina

Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention ***,current work neglects the implicit emotion expressed without any explicit emotional keywords,which appears more frequently in application *** lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local ***,an entire event is usually across multiple clauses,while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event *** address these issues,the events are first redefined at the tuple level and a span-based tuple-level algorithm is proposed to extract events from different *** on it,a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is *** authors propose a knowledge-enriched jointlearning model of implicit emotion recognition and implicit emotion cause extraction tasks(KJ-IECE),which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause *** on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.

关键词： emotion cause extraction external knowledge fusion implicit emotion recognition joint learning

来源：评论

学校读者我要写书评

暂无评论

PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer

PSST: A Benchmark for Evaluation-driven Text Public-Speaking...

引用

2024 Conference on Empirical Methods in Natural language processing, EMNLP 2024

作者： Sun, Huashan Wu, Yixiao Ye, Yuhao Yang, Yizhe Li, Yinghao Li, Jiawei Gao, Yang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

ISBN: (纸本)9798891761681

language style is necessary for AI systems to understand and generate diverse human language ***, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application *** overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking *** in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of *** such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized *** experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Dependency-Type Weighted Graph Convolutional Network on End-to-End Aspect-Based Sentiment Analysis 13th

Dependency-Type Weighted Graph Convolutional Network on End...

引用

13th IFIP TC 12 International Conference on Intelligent information processing, IIP 2024

作者： Mu, Yusong Shi, Shumin School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

ISBN: (纸本)9783031579189

Previous studies consider little on using dependency-type messages in the E2E-ABSA task. Studies using dependency-type messages just contact the dependency-type message and word embedding vectors, which may not fully fuse the context feature and information from the dependency type. This paper proposes a new model called Dependency-Type Weighted Graph Convolution Network (DTW-GCN) to compose dependency-type messages and word embedding. We use a type-weighted matrix to combine the dependency-type message, and DTW-GCN could fuse the dependency-type message and word embedding vectors. Experiments conducted on three benchmark datasets verify the effectiveness of our model. © IFIP International Federation for information processing 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Implicit Discourse Relation Recognition with Semantics Confrontation 30

Improving Implicit Discourse Relation Recognition with Seman...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on language Resources and Evaluation, LREC-COLING 2024

作者： Cai, Mingyang Yang, Zhen Jian, Ping School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Beijing China

ISBN: (纸本)9782493814104

Implicit Discourse Relation Recognition (IDRR), which infers discourse logical relations without explicit connectives, is one of the most challenging tasks in natural language processing (NLP). Recently, pre-trained language models (PLMs) have yielded impressive results across numerous NLP tasks, but their performance still remains unsatisfactory in IDRR. We argue that prior studies have not fully harnessed the potential of PLMs, thereby resulting in a mixture of logical semantics, which determine the logical relations between discourse arguments, and general semantics, which encapsulate the non-logical contextual aspects (detailed in Sec.1). Such a mixture would inevitably compromise the logic reasoning ability of PLMs. Therefore, we propose a novel method that trains the PLMs through two semantics enhancers to implicitly differentiate logical and general semantics, ultimately achieving logical semantics enhancement. Due to the characteristic of PLM in word representation learning, these two semantics enhancers will inherently confront with each other, facilitating an augmentation of logical semantics by disentangling them from general semantics. The experimental results on PDTB 2.0 dataset show that the confrontation approach exceeds our baseline by 3.81% F1 score, and the effectiveness of the semantics confrontation method is validated by comprehensive ablation experiments. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Effective Integration of Text Diffusion and Pre-Trained language Models with Linguistic Easy-First Schedule 30

Effective Integration of Text Diffusion and Pre-Trained Lang...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on language Resources and Evaluation, LREC-COLING 2024

作者： Ou, Yimin Jian, Ping School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology Beijing China

ISBN: (纸本)9782493814104

Diffusion models have become a powerful generative modeling paradigm, achieving great success in continuous data patterns. However, the discrete nature of text data results in compatibility issues between continuous diffusion models (CDMs) and pre-trained language models (PLMs). That is, the performance of diffusion models even degrades when combined with PLMs. To alleviate this issue, we propose to utilize a pre-trained decoder to convert the denoised embedding vectors into natural language instead of using the widely used rounding operation. In this way, CDMs can be more effectively combined with PLMs. Additionally, considering that existing noise schedules in text diffusion models do not take into account the linguistic differences among tokens, which violates the easy-first policy for text generation, we propose a linguistic easy-first schedule that incorporates the measure of word importance, conforming to easy-first-generation linguistic features and bringing about improved generation quality. Experiment results on the E2E dataset and five controllable tasks show that our approach can combine the merits of CDMs and PLMs, significantly outperforming other diffusion-based models. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Augmenting Context Representation with Triggers Knowledge for Relation Extraction 12th

Augmenting Context Representation with Triggers Knowledge fo...

引用

12th IFIP TC 12 International Conference on Intelligent information processing, IIP 2022

作者： Li, En Shi, Shumin Yang, Zhikun Huang, He Yan School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

ISBN: (纸本)9783031039478

Relation Extraction (RE) requires the model to classify the correct relation from a set of relation candidates given the corresponding sentence and two entities. Recent work mainly studies how to utilize more data or incorporate extra context information especially with Pre-trained language Models (PLMs). However, these models still face with the challenges of avoiding being affected by irrelevant or misleading words. In this paper, we propose a novel model to help alleviate such deficiency. Specifically, our model automatically mines the triggers of the sentence iteratively with the sentence itself from the previous iteration, and augment the semantics of the context representation from BERT with both entity pair and triggers skillfully. We conduct extensive experiments to evaluate the proposed model and effectively obtain empirical improvement in TACRED. © 2022, IFIP International Federation for information processing.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Multimodal Sentiment Analysis Model Based on Gated Fusion and Multi-Task Learning

A Novel Multimodal Sentiment Analysis Model Based on Gated F...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xin Sun Xiangyu Ren Xiaohao Xie School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Applications Research Center on High Volume Language Information Processing and Cloud Computing

Sentiment analysis is an important research area in Natural language processing (NLP). With the explosion of multimodal data, Multimodal Sentiment Analysis (MSA) attracts more and more attention in recent years. How to Effectively harnessing the interplay between diverse modalities is paramount to achieving comprehensive fusion of MSA. However, current research predominantly emphasizes modality interaction, while overlooking unimodal information, thus neglecting the inherent disparities between modalities. To address these issues, we propose a novel model for multimodal sentiment analysis based on gated fusion and multi-task learning. The model adopts multi-task learning to concurrently address both multimodal and unimodal sentiment analysis tasks. Specifically, for the multimodal task, we leverage cross-modal Transformers with gating mechanisms to facilitate modality fusion. Subsequently, the fused representations are harnessed to generate sentiment labels for the unimodal tasks. Experiments on the CMU-MOSI and CMU-MOSEI datasets demonstrate that our model outperforms the existing methods and achieves the state-of-the art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

System Report for CCL23-Eval Task 9: Improving MRC Robustness with Overlapping Segments Generation for GCRC advRobust 22

System Report for CCL23-Eval Task 9: Improving MRC Robustnes...

引用

22nd Chinese National Conference on Computational Linguistics, CCL 2023

作者： He, Suzhe Yang, Chongsheng Shi, Shumin Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

ISBN: (纸本)9781713889908

There are many challenges in machine reading comprehension when it comes to extracting semantically complete evidence for specific statement. Existing works on unsupervised evidence extraction can be mainly divided into two categories. The first category utilizes static word vectors and employs beam search iteratively to extract relevant sentences. The second category uses instance-level supervised methods, including independent evidence extraction and end-to-end evidence extraction. The former category involves a more complex process, while the latter category suffers from instability during joint training, which directly affects the stable improvement of model performance. In Task 9 of CCL23-Eval, this paper proposes an adaptive end-to-end evidence extraction method based on overlapping segments generation. This method addresses the uncertainty in evidence sentence boundaries by dividing the document into multiple overlapping sentence segments and extracting key parts as evidence to achieve overall semantic extraction. Simultaneously, the evidence extraction embedding module is optimized to achieve automatic adjustment of evidence segment confidence. Experimental results demonstrate that the proposed method greatly eliminates interference from redundant content, and with just one hyperparameter, it can stably improve the performance of the reading comprehension model, improving model robustness. © 2023 China National Conference on Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Approximating to the Real Translation Quality for Neural Machine Translation via Causal Motivated Methods

引用

ACM Transactions on Asian and Low-Resource language information processing 2023年第5期22卷 1-26页

作者： Xuewen Shi Heyan Huang Ping Jian Yi-Kun Tang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Haidian District Beijing China

It is hard to evaluate translations objectively and accurately, which limits the applications of machine translation. In this article, we assume that the above phenomenon is caused by noise interference during translation evaluation, and we handle the problem through a perspective of causal inference. We assume that the observable translation score is affected by the unobservable true translation quality and some noise simultaneously. If there is a variable that is related to the noise and independent to the true translation quality, the related noise can be eliminated by removing the effect of that variable from the observed score. Based on the above causality hypothesis, this article studies the length bias problem of beam search for neural machine translation (NMT) and the input related noise problem of translation quality estimation (QE). For the NMT length bias problem, we conduct the experiments on four typical NMT tasks (Uyghur–Chinese, Chinese–English, English–German, and English–French) with different scales of datasets. Comparing with previous approaches, the proposed causal motivated method is model-agnostic and does not require supervised training. For QE tasks, we conduct the experiments on the WMT’20 submissions. Experimental results show that the denoised QE results gain better Pearson’s correlation scores with human assessed scores compared to the original submissions. Further analyses on the NMT and QE tasks also demonstrate the rationality of the empirical assumptions made on our methods.

关键词： Neural machine translation causal inference half-sibling regression quality estimation

来源：评论

学校读者我要写书评

暂无评论

ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension 29

ET5: A Novel End-to-end Framework for Conversational Machine...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhang, Xiao Huang, Heyan Chi, Zewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China

Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. Existing methods typically require three steps: (1) decision making based on entailment reasoning;(2) span extraction if required by the above decision;(3) question rephrasing based on the extracted span. However, for nearly all these methods, the span extraction and question rephrasing steps cannot fully exploit the fine-grained entailment reasoning information in decision making step because of their relative independence, which will further enlarge the information gap between decision making and question phrasing. Thus, to tackle this problem, we propose a novel end-to-end framework for conversational machine reading comprehension based on shared parameter mechanism, called entailment reasoning T5 (ET5). Despite the lightweight of our proposed framework, experimental results show that the proposed ET5 achieves new state-of-the-art results on the ShARC leaderboard with the BLEU-4 score of 55.2. Our model and code are publicly available © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：