检索结果-内蒙古大学图书馆

16th workshop on graph-based methods for natural language processing, Textgraphs 2022, in conjunction with the 29th International Conference on Computational Linguistics, COLING 2022

作者： Dong, MeiXing Xu, Xueming Mihalcea, Rada University of Michigan United States

Predicting user behavior is essential for a large number of applications including recommender and dialog systems, and more broadly in domains such as healthcare, education, and economics. In this paper, we show that we can effectively predict donation behavior by using text-aware graph models, building upon graphs that connect user behaviors and their interests. Using a university donation dataset, we show that the graph representation significantly improves over learning from textual representations. Moreover, we show how incorporating implicit information inferred from text associated with the graph entities brings additional improvements. Our results demonstrate the role played by text-aware graph representations in predicting donation behavior. © 2022 proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Gen-IR @ SIGIR 2023: The first workshop on Generative Information Retrieval 46

Gen-IR @ SIGIR 2023: The First Workshop on Generative Inform...

引用

46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Benedict, Gabriel Zhang, Ruqing Metzler, Donald Univ Amsterdam Amsterdam Netherlands RTL NL Amsterdam Netherlands Chinese Acad Sci ICT Beijing Peoples R China Google Res Mountain View CA USA

ISBN: (纸本)9781450394086

Generative information retrieval (IR) has experienced substantial growth across multiple research communities (e.g., information retrieval, computer vision, natural language processing, and machine learning), and has been highly visible in the popular press. Theoretical, empirical, and actual user-facing products have been released that retrieve documents (via generation) or directly generate answers given an input request. We would like to investigate whether end-to-end generative models are just another trend or, as some claim, a paradigm change for IR. This necessitates new metrics, theoretical grounding, evaluation methods, task definitions, models, user interfaces, etc. The goal of this workshop(1) is to focus on previously explored Generative IR techniques like document retrieval and direct Grounded Answer Generation, while also offering a venue for the discussion and exploration of how Generative IR can be applied to new domains like recommendation systems, summarization, etc. The format of the workshop is interactive, including roundtable and keynote sessions and tends to avoid the one-sided dialogue of a mini-conference.

关键词： Generative Models Information Retrieval Large language Models

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Linguistically-Driven and Transfer Learning methods for Euphemism Detection 3

An Exploration of Linguistically-Driven and Transfer Learnin...

引用

3rd workshop on Figurative language processing, FigLang 2022, as part of EMNLP 2022

作者： Tiwari, Devika Parde, Natalie Natural Language Processing Laboratory Department of Computer Science University of Illinois Chicago United States

ISBN: (纸本)9781959429111

Euphemisms are often used to drive rhetoric, but their automated recognition and interpretation are under-explored. We investigate four methods for detecting euphemisms in sentences containing potentially euphemistic terms. The first three linguistically-motivated methods rest on an understanding of (1) euphemism's role to attenuate the harsh connotations of a taboo topic and (2) euphemism's metaphorical underpinnings. In contrast, the fourth method follows recent innovations in other tasks and employs transfer learning from a general-domain pre-trained language model. While the latter method ultimately (and perhaps surprisingly) performed best (F1 = 0.74), we comprehensively evaluate all four methods to derive additional useful insights from the negative results. © 2022 Association for Computational Linguistics.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Interpretation of BERT embeddings with Knowledge graphs 31

Semantic Interpretation of BERT embeddings with Knowledge Gr...

引用

31st Symposium of Advanced Database Systems, SEBD 2023

作者： De Bellis, Alessandro Biancofiore, Giovanni Maria Anelli, Vito Walter Narducci, Fedelucio Di Noia, Tommaso Ragone, Azzurra Di Sciascio, Eugenio Polytechnic University of Bari Bari Italy University of Bari Bari Italy

Pretrained language models have transformed the way we process natural languages, enhancing the performance of related systems. BERT has played a pivotal role in revolutionizing the field of natural language processing (NLP). However, the deep learning framework behind BERT lacks interpretability. Recent research has focused on explaining the knowledge BERT acquires from the textual sources used for pre-training its linguistic model. In this study, we analyze the latent vector space produced by BERT's context-aware word embeddings. Our aim is to determine whether certain areas of the BERT vector space have an explicit meaning related to a Knowledge graph (KG). Using the Link Prediction (LP) task, we demonstrate the presence of explicit and meaningful regions of the BERT vector space. Moreover, we establish links between BERT's vector space and specific ontology concepts in the KG by learning classification patterns. To the best of our knowledge, this is the first attempt to interpret BERT's learned linguistic knowledge through a KG by relying on its pre-trained context-aware word embeddings. © 2023 CEUR-WS. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Construction and Analysis of Surrounding Travel Demanding graph based on Dual Contrastive Learning Text Classification and graph Neural Network 3

Construction and Analysis of Surrounding Travel Demanding Gr...

引用

3rd International Conference on Big Data and Artificial Intelligence and Software Engineering, ICBASE 2022

作者： Lai, Guoping Chi, Zhiheng Pan, Fan Xu, Zhihao Hu, Hao Information Engineering University Zhengzhou450001 China

Understanding the main information about the current situation of the tourism market has become an urgent need and new trends in the development of the tourism market. In this paper, we use natural language processing technology to analyze the development of tourism around Maoming City, Guangdong Province during the COVID-19 epidemic by means of data mining methods to build a local tourism graph, refine and design models and methods such as RoBERTa-BiGRU-Attention fusion model, dual contrastive learning, BERT-BiLSTM-CRF named entity identification technique, improved Apriori algorithm, GNNLP model based on conventional models and proved the rationality and efficiency of the improved model by comparative test, provide oriented suggestions to help government departments promote tourism and tourism enterprises product supply, optimize resource allocation and explore the market constantly during the epidemic period after scientific analysis and summary. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Pair-based Joint Encoding with Relational graph Convolutional Networks for Emotion-Cause Pair Extraction

Pair-Based Joint Encoding with Relational Graph Convolutiona...

引用

2022 Conference on Empirical methods in natural language processing, EMNLP 2022

作者： Liu, Junlong Shang, Xichen Ma, Qianli School of Computer Science and Engineering South China University of Technology Guangzhou China

Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention. Previous methods sequentially encode features with a specified order. They first encode the emotion and cause features for clause extraction and then combine them for pair extraction. This lead to an imbalance in inter-task feature interaction where features extracted later have no direct contact with the former. To address this issue, we propose a novel Pair-based Joint Encoding (PBJE) network, which generates pairs and clauses features simultaneously in a joint feature encoding manner to model the causal relationship in clauses. PBJE can balance the information flow among emotion clauses, cause clauses and pairs. From a multi-relational perspective, we construct a heterogeneous undirected graph and apply the Relational graph Convolutional Network (RGCN) to capture the various relationship between clauses and the relationship between pairs and clauses. Experimental results show that PBJE achieves state-of-the-art performance on the Chinese benchmark corpus. © 2022 Association for Computational Linguistics.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Knowledge graph-based Hierarchical Text Semantic Representation

引用

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS 2024年第1期2024卷 5583270-5583270页

作者： Wu, Yongliang Pan, Xiao Li, Jinghui Dou, Shimao Dong, Jiahao Wei, Dan Shijiazhuang Tiedao Univ Sch Informat Sci & Technol Shijiazhuang 050023 Hebei Peoples R China

Document representation is the basis of language modeling. Its goal is to turn natural language text that flows into a structured form that can be stored and processed by a computer. The bag-of-words model is used by most of the text-representation methods that are currently available. And yet, they do not consider how phrases are used in the text, which hurts the performance of tasks that use natural language processing later on. Representing the meaning of text by phrases is a promising area of future research, but it is hard to do well because phrases are organized in a hierarchy and mining efficiency is low. In this paper, we put forward a method called hierarchical text semantic representation using the knowledge graph (HTSRKG), which uses syntactic structure features to find hierarchical phrases and knowledge graphs to improve how phrases are evaluated. first, we use CKY and PCFG to build the syntax tree sentence by sentence. Second, we walk through the parse tree using the hierarchical routing process to obtain the mixed phrase semantics in passages. Finally, the introduction of the knowledge graph improves the efficiency of text semantic extraction and the accuracy of text representation. This gives us a solid foundation for tasks involving natural language processing that come after. Extensive testing on actual datasets shows that HTSRKG surpasses baseline approaches with respect to text semantic representation, and the results of a recent benchmarking study support this.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Cross-modal multi-relationship aware reasoning for image-text matching

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第9期81卷 12005-12027页

作者： Zhang, Jin He, Xiaohai Qing, Linbo Liu, Luping Luo, Xiaodong Sichuan Univ Coll Elect & Informat Engn Chengdu 610064 Sichuan Peoples R China

Cross-modal image-text matching has attracted considerable interest in both computer vision and natural language processing communities. The main issue of image-text matching is to learn the compact cross-modal representations and the correlation between image and text representations. However, the image-text matching task has two major challenges. first, the current image representation methods focus on the semantic information and disregard the spatial position relations between image regions. Second, most existing methods pay little attention to improving textual representation which plays a significant role in image-text matching. To address these issues, we designed a decipherable cross-modal multi-relationship aware reasoning network (CMRN) for image-text matching. In particular, a new method is proposed to extract multi-relationship and to learn the correlations between image regions, including two kinds of visual relations: the geometric position relation and semantic interaction. In addition, images are processed as graphs, and a novel spatial relation encoder is introduced to perform reasoning on the graphs by employing a graph convolutional network (GCN) with attention mechanism. Thereafter, a contextual text encoder based on Bidirectional Encoder Representations from Transformers is adopted to learn distinctive textual representations. To verify the effectiveness of the proposed model, extensive experiments were conducted on two public datasets, namely MSCOCO and Flickr30K. The experimental results show that CMRN achieved superior performance when compared with state-of-the-art methods. On Flickr30K, the proposed method outperforms state-of-the-art methods more than 7.4% in text retrieval from image query, and 5.0% relatively in image retrieval with text query (based on Recall@1). On MSCOCO, the performance reaches 73.9% for text retrieval and 60.4% for image retrieval (based on Recall@1).

关键词： Image-text matching Visual multi-relationship graph neural network Cross-modal retrieval

来源：评论

学校读者我要写书评

暂无评论

Legal and Political Stance Detection of SCOTUS language 4

Legal and Political Stance Detection of SCOTUS Language

引用

4th natural Legal language processing workshop, NLLP 2022, co-located with the 2022 Conference on Empirical methods in natural language processing, EMNLP 2022

作者： Bergam, Noah Allaway, Emily McKeown, Kathleen Columbia University New YorkNY United States

ISBN: (纸本)9781959429180

We analyze publicly available US Supreme Court documents using automated stance detection. In the first phase of our work, we investigate the extent to which the Court's public-facing language is political. We propose and calculate two distinct ideology metrics of SCOTUS justices using oral argument transcripts. We then compare these language-based metrics to existing social scientific measures of the ideology of the Supreme Court and the public. Through this cross-disciplinary analysis, we find that justices who are more responsive to public opinion tend to express their ideology during oral arguments. This observation provides a new kind of evidence in favor of the attitudinal change hypothesis of Supreme Court justice behavior. As a natural extension of this political stance detection, we propose the more specialized task of legal stance detection with our new dataset SC-stance, which matches written opinions to legal questions. We find competitive performance on this dataset using language adapters trained on legal documents. © 2022 Association for Computational Linguistics.

关键词： Social aspects

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Validity of Word-level Adversarial Attacks with Large language Models 62

Evaluating the Validity of Word-level Adversarial Attacks wi...

引用

62nd Annual Meeting of the Association-for-Computational-Linguistics (ACL) / Student Research workshop (SRW)

作者： Zhou, Huichi Wang, Zhaoyang Wang, Hongtao Chen, Dongping Mu, Wenhan Zhang, Fangyuan North China Elect Power Univ Dept Comp Beijing Peoples R China Sun Yat Sen Univ Guangzhou Peoples R China HUST Wuhan Peoples R China Chongqing Univ Chongqing Peoples R China

ISBN: (纸本)9798891760998

Deep neural networks exhibit vulnerability to word-level adversarial attacks in natural language processing. Most of these attack methods adopt synonymous substitutions to perturb original samples for crafting adversarial examples while attempting to maintain semantic consistency with the originals. Some of them claim that they could achieve over 90% attack success rate, thereby raising serious safety concerns. However, our investigation reveals that many purportedly successful adversarial examples are actually invalid due to significant changes in semantic meanings compared to their originals. Even when equipped with semantic constraints such as BERTScore, existing attack methods can generate up to 87.9% invalid adversarial examples. Building on this insight, we first curate a 13K dataset for adversarial validity evaluation with the help of GPT-4. Then, an open-source large language model is fine-tuned to offer an interpretable validity score for assessing the semantic consistency between original and adversarial examples. Finally, this validity score can serve as a guide for existing adversarial attack methods to generate valid adversarial examples. Comprehensive experiments demonstrate the effectiveness of our method in evaluating and refining the quality of adversarial examples.

关键词： Generative adversarial networks

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：