发布求助
文献互助 智能选刊 最新文献

Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)最新文献

筛选
英文 中文
DeepBlueAI at TextGraphs 2021 Shared Task: Treating Multi-Hop Inference Explanation Regeneration as A Ranking Problem DeepBlueAI在TextGraphs 2021共享任务:将多跳推理解释再生视为排序问题
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15) Pub Date : 2021-06-01 DOI: 10.18653/V1/11.TEXTGRAPHS-1.18
Chunguang Pan, Bingyan Song, Zhipeng Luo
{"title":"DeepBlueAI at TextGraphs 2021 Shared Task: Treating Multi-Hop Inference Explanation Regeneration as A Ranking Problem","authors":"Chunguang Pan, Bingyan Song, Zhipeng Luo","doi":"10.18653/V1/11.TEXTGRAPHS-1.18","DOIUrl":"https://doi.org/10.18653/V1/11.TEXTGRAPHS-1.18","url":null,"abstract":"This paper describes the winning system for TextGraphs 2021 shared task: Multi-hop inference explanation regeneration. Given a question and its corresponding correct answer, this task aims to select the facts that can explain why the answer is correct for that question and answering (QA) from a large knowledge base. To address this problem and accelerate training as well, our strategy includes two steps. First, fine-tuning pre-trained language models (PLMs) with triplet loss to recall top-K relevant facts for each question and answer pair. Then, adopting the same architecture to train the re-ranking model to rank the top-K candidates. To further improve the performance, we average the results from models based on different PLMs (e.g., RoBERTa) and different parameter settings to make the final predictions. The official evaluation shows that, our system can outperform the second best system by 4.93 points, which proves the effectiveness of our system. Our code has been open source, address is https://github.com/DeepBlueAI/TextGraphs-15","PeriodicalId":332938,"journal":{"name":"Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127112916","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
GENE: Global Event Network Embedding GENE:全局事件网络嵌入
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15) Pub Date : 2021-06-01 DOI: 10.18653/V1/11.TEXTGRAPHS-1.5
Qi Zeng, Manling Li, T. Lai, Heng Ji, Mohit Bansal, Hanghang Tong
{"title":"GENE: Global Event Network Embedding","authors":"Qi Zeng, Manling Li, T. Lai, Heng Ji, Mohit Bansal, Hanghang Tong","doi":"10.18653/V1/11.TEXTGRAPHS-1.5","DOIUrl":"https://doi.org/10.18653/V1/11.TEXTGRAPHS-1.5","url":null,"abstract":"Current methods for event representation ignore related events in a corpus-level global context. For a deep and comprehensive understanding of complex events, we introduce a new task, Event Network Embedding, which aims to represent events by capturing the connections among events. We propose a novel framework, Global Event Network Embedding (GENE), that encodes the event network with a multi-view graph encoder while preserving the graph topology and node semantics. The graph encoder is trained by minimizing both structural and semantic losses. We develop a new series of structured probing tasks, and show that our approach effectively outperforms baseline models on node typing, argument role classification, and event coreference resolution.","PeriodicalId":332938,"journal":{"name":"Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133746522","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
Fine-grained General Entity Typing in German using GermaNet 使用GermaNet在德语中进行细粒度一般实体键入
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15) Pub Date : 2021-06-01 DOI: 10.18653/V1/11.TEXTGRAPHS-1.14
Sabine Weber, Mark Steedman
{"title":"Fine-grained General Entity Typing in German using GermaNet","authors":"Sabine Weber, Mark Steedman","doi":"10.18653/V1/11.TEXTGRAPHS-1.14","DOIUrl":"https://doi.org/10.18653/V1/11.TEXTGRAPHS-1.14","url":null,"abstract":"Fine-grained entity typing is important to tasks like relation extraction and knowledge base construction. We find however, that fine-grained entity typing systems perform poorly on general entities (e.g. “ex-president”) as compared to named entities (e.g. “Barack Obama”). This is due to a lack of general entities in existing training data sets. We show that this problem can be mitigated by automatically generating training data from WordNets. We use a German WordNet equivalent, GermaNet, to automatically generate training data for German general entity typing. We use this data to supplement named entity data to train a neural fine-grained entity typing system. This leads to a 10% improvement in accuracy of the prediction of level 1 FIGER types for German general entities, while decreasing named entity type prediction accuracy by only 1%.","PeriodicalId":332938,"journal":{"name":"Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131061045","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: 1
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs 基于相对位置的知识图文本生成图结构建模
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15) Pub Date : 2021-05-03 DOI: 10.18653/V1/11.TEXTGRAPHS-1.2
Martin Schmitt, Leonardo Ribeiro, Philipp Dufter, Iryna Gurevych, Hinrich Schütze
{"title":"Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs","authors":"Martin Schmitt, Leonardo Ribeiro, Philipp Dufter, Iryna Gurevych, Hinrich Schütze","doi":"10.18653/V1/11.TEXTGRAPHS-1.2","DOIUrl":"https://doi.org/10.18653/V1/11.TEXTGRAPHS-1.2","url":null,"abstract":"We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating the detection of global patterns. We represent the relation between two nodes as the length of the shortest path between them. Graformer learns to weight these node-node relations differently for different attention heads, thus virtually learning differently connected views of the input graph. We evaluate Graformer on two popular graph-to-text generation benchmarks, AGENDA and WebNLG, where it achieves strong performance while using many fewer parameters than other approaches.","PeriodicalId":332938,"journal":{"name":"Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114985380","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: 17
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信