Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)最新文献

Corpus-Based Task-Specific Relation Discovery 基于语料库的任务特定关系发现

Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.matching-1.5

Karthik Ramanan

{"title":"Corpus-Based Task-Specific Relation Discovery","authors":"Karthik Ramanan","doi":"10.18653/v1/2023.matching-1.5","DOIUrl":"https://doi.org/10.18653/v1/2023.matching-1.5","url":null,"abstract":"Relation extraction is a crucial language processing task for various downstream applications, including knowledge base completion, question answering, and summarization. Traditional relation-extraction techniques, however, rely on a predefined set of relations and model the extraction as a classification task. Consequently, such closed-world extraction methods are insufficient for inducing novel relations from a corpus. Unsupervised techniques like OpenIE, which extract triples, generate relations that are too general for practical information extraction applications. In this work, we contribute the following: 1) We motivate and introduce a new task, corpus-based task-specific relation discovery. 2) We adapt existing data sources to create Wiki-Art, a novel dataset for task-specific relation discovery. 3) We develop a novel framework for relation discovery using zero-shot entity linking, prompting, and type-specific clustering. Our approach effectively connects unstructured text spans to their shared underlying relations, bridging the data-representation gap and significantly outperforming baselines on both quantitative and qualitative metrics. Our code and data are available in our GitHub repository.","PeriodicalId":107861,"journal":{"name":"Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)","volume":"9 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":"122058436","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

Toward Consistent and Informative Event-Event Temporal Relation Extraction 面向一致性和信息性事件-事件时间关系提取

Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.matching-1.3

Xiaomeng Jin, Haoyang Wen, Xinya Du, Heng Ji

{"title":"Toward Consistent and Informative Event-Event Temporal Relation Extraction","authors":"Xiaomeng Jin, Haoyang Wen, Xinya Du, Heng Ji","doi":"10.18653/v1/2023.matching-1.3","DOIUrl":"https://doi.org/10.18653/v1/2023.matching-1.3","url":null,"abstract":"Event-event temporal relation extraction aims to extract the temporal order between a pair of event mentions, which is usually used to construct temporal event graphs. However, event graphs generated by existing methods are usually globally inconsistent (event graphs containing cycles), semantically irrelevant (two unrelated events having temporal links), and context unaware (neglecting neighborhood information of an event node). In this paper, we propose a novel event-event temporal relation extraction method to address these limitations. Our model combines a pretrained language model and a graph neural network to output event embeddings, which captures the contextual information of event graphs. Moreover, to achieve global consistency and semantic relevance, (1) event temporal order should be in accordance with the norm of their embeddings, and (2) two events have temporal relation only if their embeddings are close enough. Experimental results on a real-world event dataset demonstrate that our method achieves state-of-the-art performance and generates high-quality event graphs.","PeriodicalId":107861,"journal":{"name":"Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)","volume":"257 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":"113972165","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

On the Surprising Effectiveness of Name Matching Alone in Autoregressive Entity Linking 关于自回归实体链接中名称匹配的惊人有效性

Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.matching-1.6

Elliot Schumacher, J. Mayfield, Mark Dredze

引用次数: 0

Identifying Quantifiably Verifiable Statements from Text 从文本中识别可量化验证的陈述

Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.matching-1.2

Pegah Jandaghi, J. Pujara

{"title":"Identifying Quantifiably Verifiable Statements from Text","authors":"Pegah Jandaghi, J. Pujara","doi":"10.18653/v1/2023.matching-1.2","DOIUrl":"https://doi.org/10.18653/v1/2023.matching-1.2","url":null,"abstract":"Humans often describe complex quantitative data using trend-based patterns. Trend-based patterns can be interpreted as higher order functions and relations over numerical data such as extreme values, rates of change, or cyclical repetition. One application where trends abound are descriptions of numerical tabular data. Therefore, the alignment of numerical tables and textual description of trends enables easier interpretations of tables. Most existing approaches can align quantities in text with tabular data but are unable to detect and align trend-based patterns about data. In this paper, we introduce the initial steps for aligning trend-based patterns about the data, i.e. the detection of textual description of trends and the alignment of trends with a relevant table. We introduce the problem of identifying quantifiably verifiable statements (QVS) in the text and aligning them with tables and datasets. We define the structure of these statements and implement a structured based detection. In our experiments, we demonstrate our method can detect and align these statements from several domains and compare favorably with traditional sequence labeling methods.","PeriodicalId":107861,"journal":{"name":"Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)","volume":"195 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114008350","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

Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering 零概率知识图问答的知识增强语言模型提示

Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023) Pub Date : 1900-01-01 DOI: 10.18653/v1/2023.matching-1.7

Jinheon Baek, Alham Fikri Aji, Amir Saffari

{"title":"Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering","authors":"Jinheon Baek, Alham Fikri Aji, Amir Saffari","doi":"10.18653/v1/2023.matching-1.7","DOIUrl":"https://doi.org/10.18653/v1/2023.matching-1.7","url":null,"abstract":"Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. However, such internalized knowledge might be insufficient and incorrect, which could lead LLMs to generate factually wrong answers. Furthermore, fine-tuning LLMs to update their knowledge is expensive. To this end, we propose to augment the knowledge directly in the input of LLMs. Specifically, we first retrieve the relevant facts to the input question from the knowledge graph based on semantic similarities between the question and its associated facts. After that, we prepend the retrieved facts to the input question in the form of the prompt, which is then forwarded to LLMs to generate the answer. Our framework, Knowledge-Augmented language model PromptING (KAPING), requires no model training, thus completely zero-shot. We validate the performance of our KAPING framework on the knowledge graph question answering task, that aims to answer the user’s question based on facts over a knowledge graph, on which ours outperforms relevant zero-shot baselines by up to 48% in average, across multiple LLMs of various sizes.","PeriodicalId":107861,"journal":{"name":"Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023)","volume":"4 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":"126490854","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: 6