Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)最新文献

Explanation Regeneration via Multi-Hop ILP Inference over Knowledge Base 基于知识库的多跳ILP推理解释再生

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.13

Aayushee Gupta, G. Srinivasaraghavan

引用次数: 3

Graph-based Aspect Representation Learning for Entity Resolution 面向实体解析的基于图的方面表示学习

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.2

Zhenqiang Zhao, Yuchen Guo, Dingxian Wang, Yufang Huang, Xiangnan He, Bin Gu

{"title":"Graph-based Aspect Representation Learning for Entity Resolution","authors":"Zhenqiang Zhao, Yuchen Guo, Dingxian Wang, Yufang Huang, Xiangnan He, Bin Gu","doi":"10.18653/v1/2020.textgraphs-1.2","DOIUrl":"https://doi.org/10.18653/v1/2020.textgraphs-1.2","url":null,"abstract":"Entity Resolution (ER) identifies records that refer to the same real-world entity. Deep learning approaches improved the generalization ability of entity matching models, but hardly overcame the impact of noisy or incomplete data sources. In real scenes, an entity usually consists of multiple semantic facets, called aspects. In this paper, we focus on entity augmentation, namely retrieving the values of missing aspects. The relationship between aspects is naturally suitable to be represented by a knowledge graph, where entity augmentation can be modeled as a link prediction problem. Our paper proposes a novel graph-based approach to solve entity augmentation. Specifically, we apply a dedicated random walk algorithm, which uses node types to limit the traversal length, and encodes graph structure into low-dimensional embeddings. Thus, the missing aspects could be retrieved by a link prediction model. Furthermore, the augmented aspects with fixed orders are served as the input of a deep Siamese BiLSTM network for entity matching. We compared our method with state-of-the-art methods through extensive experiments on downstream ER tasks. According to the experiment results, our model outperforms other methods on evaluation metrics (accuracy, precision, recall, and f1-score) to a large extent, which demonstrates the effectiveness of our method.","PeriodicalId":282839,"journal":{"name":"Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)","volume":"231 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114656318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semi-supervised Word Sense Disambiguation Using Example Similarity Graph 基于实例相似图的半监督词义消歧

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.6

Rie Yatabe, Minoru Sasaki

引用次数: 1

TextGraphs 2020 Shared Task on Multi-Hop Inference for Explanation Regeneration TextGraphs 2020多跳推理解释再生共享任务

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.10

Peter Alexander Jansen, Dmitry Ustalov

{"title":"TextGraphs 2020 Shared Task on Multi-Hop Inference for Explanation Regeneration","authors":"Peter Alexander Jansen, Dmitry Ustalov","doi":"10.18653/v1/2020.textgraphs-1.10","DOIUrl":"https://doi.org/10.18653/v1/2020.textgraphs-1.10","url":null,"abstract":"The 2020 Shared Task on Multi-Hop Inference for Explanation Regeneration tasks participants with regenerating large detailed multi-fact explanations for standardized science exam questions. Given a question, correct answer, and knowledge base, models must rank each fact in the knowledge base such that facts most likely to appear in the explanation are ranked highest. Explanations consist of an average of 6 (and as many as 16) facts that span both core scientific knowledge and world knowledge, and form an explicit lexically-connected “explanation graph” describing how the facts interrelate. In this second iteration of the explanation regeneration shared task, participants are supplied with more than double the training and evaluation data of the first shared task, as well as a knowledge base nearly double in size, both of which expand into more challenging scientific topics that increase the difficulty of the task. In total 10 teams participated, and 5 teams submitted system description papers. The best-performing teams significantly increased state-of-the-art performance both in terms of ranking (mean average precision) and inference speed on this challenge task.","PeriodicalId":282839,"journal":{"name":"Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115604932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

ChiSquareX at TextGraphs 2020 Shared Task: Leveraging Pretrained Language Models for Explanation Regeneration 共享任务:利用预训练语言模型进行解释再生

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.12

Aditya Girish Pawate, Varun Madhavan, Devansh Chandak

{"title":"ChiSquareX at TextGraphs 2020 Shared Task: Leveraging Pretrained Language Models for Explanation Regeneration","authors":"Aditya Girish Pawate, Varun Madhavan, Devansh Chandak","doi":"10.18653/v1/2020.textgraphs-1.12","DOIUrl":"https://doi.org/10.18653/v1/2020.textgraphs-1.12","url":null,"abstract":"In this work, we describe the system developed by a group of undergraduates from the Indian Institutes of Technology for the Shared Task at TextGraphs-14 on Multi-Hop Inference Explanation Regeneration (Jansen and Ustalov, 2020). The shared task required participants to develop methods to reconstruct gold explanations for elementary science questions from the WorldTreeCorpus (Xie et al., 2020). Although our research was not funded by any organization and all the models were trained on freely available tools like Google Colab, which restricted our computational capabilities, we have managed to achieve noteworthy results, placing ourselves in 4th place with a MAPscore of 0.49021in the evaluation leaderboard and 0.5062 MAPscore on the post-evaluation-phase leaderboard using RoBERTa. We incorporated some of the methods proposed in the previous edition of Textgraphs-13 (Chia et al., 2019), which proved to be very effective, improved upon them, and built a model on top of it using powerful state-of-the-art pre-trained language models like RoBERTa (Liu et al., 2019), BART (Lewis et al., 2020), SciB-ERT (Beltagy et al., 2019) among others. Further optimization of our work can be done with the availability of better computational resources.","PeriodicalId":282839,"journal":{"name":"Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123172118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

A survey of embedding models of entities and relationships for knowledge graph completion 知识图谱补全中实体和关系的嵌入模型综述

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.1

Dat Quoc Nguyen

引用次数: 18

PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods PGL在TextGraphs 2020共享任务:使用语言和图形学习方法的解释再生

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.11

Weibin Li, Yuxiang Lu, Zhengjie Huang, Weiyue Su, Jiaxiang Liu, Shikun Feng, Yu Sun

引用次数: 4

Graph-based Syntactic Word Embeddings 基于图的句法词嵌入

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.8

Ragheb Al-Ghezi, M. Kurimo

引用次数: 3

Relation Specific Transformations for Open World Knowledge Graph Completion 面向开放世界知识图谱补全的关系特定转换

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.9

Haseeb Shah, Johannes Villmow, A. Ulges

引用次数: 6

Merge and Recognize: A Geometry and 2D Context Aware Graph Model for Named Entity Recognition from Visual Documents 合并与识别:一种用于可视化文档命名实体识别的几何和2D上下文感知图形模型

Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) Pub Date : 1900-01-01 DOI: 10.18653/v1/2020.textgraphs-1.3

Chuwei Luo, Yongpan Wang, Qi Zheng, Liangcheng Li, Feiyu Gao, Shiyu Zhang

{"title":"Merge and Recognize: A Geometry and 2D Context Aware Graph Model for Named Entity Recognition from Visual Documents","authors":"Chuwei Luo, Yongpan Wang, Qi Zheng, Liangcheng Li, Feiyu Gao, Shiyu Zhang","doi":"10.18653/v1/2020.textgraphs-1.3","DOIUrl":"https://doi.org/10.18653/v1/2020.textgraphs-1.3","url":null,"abstract":"Named entity recognition (NER) from visual documents, such as invoices, receipts or business cards, is a critical task for visual document understanding. Most classical approaches use a sequence-based model (typically BiLSTM-CRF framework) without considering document structure. Recent work on graph-based model using graph convolutional networks to encode visual and textual features have achieved promising performance on the task. However, few attempts take geometry information of text segments (text in bounding box) in visual documents into account. Meanwhile, existing methods do not consider that related text segments which need to be merged to form a complete entity in many real-world situations. In this paper, we present GraphNEMR, a graph-based model that uses graph convolutional networks to jointly merge text segments and recognize named entities. By incorporating geometry information from visual documents into our model, richer 2D context information is generated to improve document representations. To merge text segments, we introduce a novel mechanism that captures both geometry information as well as semantic information based on pre-trained language model. Experimental results show that the proposed GraphNEMR model outperforms both sequence-based and graph-based SOTA methods significantly.","PeriodicalId":282839,"journal":{"name":"Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122893222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7