检索结果-内蒙古大学图书馆

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Luo, Zhongyu Luo, Man Wang, Aiguo Foshan University Guangdong Foshan China Guangzhou City University of Technology Guangdong Guangzhou China

The task of text detoxification aims to re-write toxic text into non-toxic text. Though existing methods have achieved impressive detoxification performance in monolingual settings, multilingual text detoxification remains challenging due to the complexity of natural languages and the lack of sufficient data for training accurate models for minor languages. In this study, we propose a cross-lingual text detoxification model, named GCTP, utilizing Google Cloud Translation and post-processing for the PAN@CLEF 2024 multilingual text detoxification task. Specifically, GCTP first translates minor language text into English for detoxification with a pretrained English model, and then translates it back to remove toxic keywords with predefined dictionaries of the original language. Extensive comparative experiments on competition datasets show that GCTP achieves the highest J score for Amharic text and ranks the 5th place for Chinese text, demonstrating the effectiveness of GCTP. © 2024 Copyright for this paper by its authors.

关键词： Detoxification

来源：评论

学校读者我要写书评

暂无评论

Schema-adaptable Knowledge graph Construction

Schema-adaptable Knowledge Graph Construction

引用

Conference on Empirical methods in natural language processing (EMNLP)

作者： Ye, Hongbin Gui, Honghao Xu, Xin Chen, Xi Chen, Huajun Zhang, Ningyu Zhejiang Univ Hangzhou Peoples R China Zhejiang Lab Hangzhou Peoples R China Tencent Platform & Content Grp Shanghai Peoples R China Zhejiang Univ Ant Grp Joint Lab Knowledge Graph Hangzhou Peoples R China

ISBN: (纸本)9798891760615

Conventional Knowledge graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. As a result, such approaches fall short when applied to dynamic scenarios or domains, whereas a new type of knowledge emerges. This necessitates a system that can handle evolving schema automatically to extract information for KGC. To address this need, we propose a new task called schema-adaptable KGC, which aims to continually extract entity, relation, and event based on a dynamically changing schema graph without re-training. We first split and convert existing datasets based on three principles to build a benchmark, i.e., horizontal schema expansion, vertical schema expansion, and hybrid schema expansion;then investigate the schema-adaptable performance of several well-known approaches such as Text2Event, TANL, UIE and GPT-3.5. We further propose a simple yet effective baseline dubbed ADAKGC, which contains schema-enriched prefix instructor and schema-conditioned dynamic decoding to better handle evolving schema. Comprehensive experimental results illustrate that ADAKGC can outperform baselines but still have room for improvement. We hope the proposed work can deliver benefits to the community(1).

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Multilevel Hypernode graphs for Effective and Efficient Entity Linking 16

Multilevel Hypernode Graphs for Effective and Efficient Enti...

引用

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： Montero, David Martinez, Javier Yebes, J. Javier NielsenIQ

Information extraction on documents still remains a challenge, especially when dealing with unstructured documents with complex and variable layouts. graph Neural Networks seem to be a promising approach to overcome these difficulties due to their flexible and sparse nature, but they have not been exploited yet. In this work, we present a multi-level graph-based model that performs entity building and linking on unstructured documents, purely based on GNNs, and extremely light (0.3 million parameters). We also propose a novel strategy for an optimal propagation of the information between the graph levels based on hypernodes. The conducted experiments on public and private datasets demonstrate that our model is suitable for solving the tasks, and that the proposed propagation strategy is optimal and outperforms other approaches. © 2022 proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： graph neural networks

来源：评论

学校读者我要写书评

暂无评论

EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop

EMNLP-IJCNLP 2019 - Graph-Based Methods for Natural Language...

引用

13th workshop on graph-based methods for natural language processing, Textgraphs 2019, in conjunction with the 2019 Conference on Empirical methods in natural language processing and 9th International Joint Conference on natural language processing, EMNLP-IJCNLP 2019

ISBN: (纸本)9781950737864

The proceedings contain 23 papers. The topics discussed include: graph-based and graph-supported machine learning and deep learning methods;graph-based and graph-supported deep learning (e.g., graph-based recurrent and recursive networks);exploration of capabilities and limitations of graph-based methods being applied to neural networks;graph-based techniques for text summarization, simplification, and paraphrasing;graph-based techniques for document navigation and visualization;and using graphs-based methods to populate ontologies using textual data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Word Sense Disambiguation of French Lexicographical Examples Using Lexical Networks 16

Word Sense Disambiguation of French Lexicographical Examples...

引用

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： Sinha, Aman Ollinger, Sandrine Constant, Mathieu ATILF Université de Lorraine Nancy France

This paper focuses on the task of word sense disambiguation (WSD) on lexicographic examples relying on the French Lexical Network (fr-LN). For this purpose, we exploit the lexical and relational properties of the network, that we integrated in a feedforward neural WSD model on top of pretrained French BERT embeddings. We provide a comparative study with various models and further show the impact of our approach regarding polysemic units. © 2022 proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

GRADA: graph Generative Data Augmentation for Commonsense Reasoning 2

GRADA: Graph Generative Data Augmentation for Commonsense Re...

引用

2nd workshop on Deep Learning on graphs for natural language processing, DLG4NLP 2022

作者： Maharana, Adyasha Bansal, Mohit Department of Computer Science University of North Carolina Chapel Hill United States

ISBN: (纸本)9781955917704

Recent advances in commonsense reasoning have been fueled by the availability of large-scale human annotated datasets. Manual annotation of such datasets, many of which are based on existing knowledge bases, is expensive and not scalable. Moreover, it is challenging to build augmentation data for commonsense reasoning because the synthetic questions need to adhere to real-world scenarios. Hence, we present GRADA, a graph-generative data augmentation framework to synthesize factual data samples from knowledge graphs for commonsense reasoning datasets. first, we train a graph-to-text model for conditional generation of questions from graph entities and relations. Then, we train a generator with GAN loss to generate distractors for synthetic questions. Our approach improves performance for SocialIQA, CODAH, HellaSwag and CommonsenseQA, and works well for generative tasks like ProtoQA. We show improvement in robustness to semantic adversaries after training with GRADA and provide human evaluation of the quality of synthetic datasets in terms of factuality and answerability. Our work provides evidence and encourages future research into graph-based generative data augmentation. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Transformer for Skeleton-based action recognition: A review of recent advances

引用

NEUROCOMPUTING 2023年第1期537卷 164-186页

作者： Xin, Wentian Liu, Ruyi Liu, Yi Chen, Yu Yu, Wenxin Miao, Qiguang Xian Key Lab Big Data & Intelligent Vis Xian 710071 Shaanxi Peoples R China Xidian Univ Sch Comp Sci & Technol 2 Taibainan Rd Xian 710071 Shaanxi Peoples R China

Skeleton-based action recognition has rapidly become one of the most popular and essential research topics in computer vision. The task is to analyze the characteristics of human joints and accurately clas-sify their behaviors through deep learning technology. Skeleton provides numerous unique advantages over other data modalities, such as robustness, compactness, noise immunity, etc. In particular, the skele-ton modality is extremely lightweight, which is especially beneficial for deep learning research in low -resource environments. Due to the non-European nature of skeleton data, graph Convolution Network (GCN) has become mainstream in the past few years, leveraging the benefits of processing topological information. However, with the explosive development of transformer methods in natural language pro-cessing and computer vision, many works have applied transformer into the field of skeleton action recognition, breaking the accuracy monopoly of GCN. Therefore, we conduct a survey using transformer method for skeleton-based action recognition, forming of a taxonomy on existing works. This paper gives a comprehensive overview of the recent transformer techniques for skeleton action recognition, proposes a taxonomy of transformer-style techniques for action recognition, conducts a detailed study on bench-mark datasets, compares the algorithm accuracy of standard methods, and finally discusses the future research directions and trends. To the best of our knowledge, this study is the first to describe skeleton-based action recognition techniques in the style of transformers and to suggest novel recogni-tion taxonomies in a review. We are confident that Transformer-based action recognition technology will become mainstream in the near future, so this survey aims to help researchers systematically learn core tasks, select appropriate datasets, understand current challenges, and select promising future directions.(c) 2023 Elsevier B.V. All rights reserved.

关键词： Transformer graph convolution network Skeleton -based action recognition Spatial temporal structure Survey

来源：评论

学校读者我要写书评

暂无评论

WalkLM: A Uniform language Model Fine-tuning Framework for Attributed graph Embedding 37

WalkLM: A Uniform Language Model Fine-tuning Framework for A...

引用

37th Conference on Neural Information processing Systems (NeurIPS)

作者： Tan, Yanchao Zhou, Zihao Lv, Hang Liu, Weiming Yang, Carl Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China Zhejiang Univ Coll Comp Sci Hangzhou Peoples R China Emory Univ Dept Comp Sci Atlanta GA 30322 USA

ISBN: (纸本)9781713899921

graphs are widely used to model interconnected entities and improve downstream predictions in various real-world applications. However, real-world graphs nowadays are often associated with complex attributes on multiple types of nodes and even links that are hard to model uniformly, while the widely used graph neural networks (GNNs) often require sufficient training toward specific downstream predictions to achieve strong performance. In this work, we take a fundamentally different approach than GNNs, to simultaneously achieve deep joint modeling of complex attributes and flexible structures of real-world graphs and obtain unsupervised generic graph representations that are not limited to specific downstream predictions. Our framework, built on a natural integration of language models (LMs) and random walks (RWs), is straightforward, powerful and data-efficient. Specifically, we first perform attributed RWs on the graph and design an automated program to compose roughly meaningful textual sequences directly from the attributed RWs;then we fine-tune an LM using the RW-based textual sequences and extract embedding vectors from the LM, which encapsulates both attribute semantics and graph structures. In our experiments, we evaluate the learned node embeddings towards different downstream prediction tasks on multiple real-world attributed graph datasets and observe significant improvements over a comprehensive set of state-of-the-art unsupervised node embedding methods. We believe this work opens a door for more sophisticated technical designs and empirical evaluations toward the leverage of LMs for the modeling of real-world graphs.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Automatic Medical Knowledge graph Construction 7

Automatic Medical Knowledge Graph Construction

引用

7th Doctoral Symposium on natural language processing, NLP-DS 2024

作者： Pardo-Ferrera, Joel Madrid Spain

Knowledge graphs are crucial for structuring and integrating large amounts of data, improving decision-making and data interoperability, especially in the healthcare domain. This PhD thesis aims to implement a unified end-to-end framework for building a cross-lingual KG for English and Spanish in the healthcare sector using NLP techniques. Addressing the reliance on traditional methods in KG construction and the limited non-English language resources, this work seeks to refine the information extraction process within unstructured medical texts and facilitate the (re)use of existent ontologies (schema to represent the real-world). © 2024 Copyright for this paper by its authors.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

GUSUM: graph-based Unsupervised Summarization using Sentence Features Scoring and Sentence-BERT 16

GUSUM: Graph-Based Unsupervised Summarization using Sentence...

引用

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： Gokhan, Tuba Smith, Phillip Lee, Mark School of Computer Science University of Birmingham United Kingdom

Unsupervised extractive document summarization aims to extract salient sentences from a document without requiring a labelled corpus. In existing graph-based methods, vertex and edge weights are usually created by calculating sentence similarities. In this paper, we develop a graph-based Unsupervised Summarization(GUSUM) method for extractive text summarization based on the principle of including the most important sentences while excluding sentences with similar meanings in the summary. We modify traditional graph ranking algorithms with recent sentence embedding models and sentence features and modify how sentence centrality is computed. We first define the sentence feature scores represented at the vertices, indicating the importance of each sentence in the document. After this stage, we use Sentence-BERT for obtaining sentence embeddings to better capture the sentence meaning. In this way, we define the edges of a graph where semantic similarities are represented. Next we create an undirected graph that includes sentence significance and similarities between sentences. In the last stage, we determine the most important sentences in the document with the ranking method we suggested on the graph created. Experiments on CNN/Daily Mail, New York Times, arXiv, and PubMed datasets show our approach achieves high performance on unsupervised graph-based summarization when evaluated both automatically and by humans. © 2022 proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Embeddings

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：