Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences. Efforts thus far have focused on improving extraction accuracy but little is known about their explainability. In this work we annotate a test set with ground-truth sentence-level explanations to evaluate the quality of explanations afforded by the relation extraction models. We demonstrate that replacing the entity mentions in the sentences with their fine-grained entity types not only enhances extraction accuracy but also improves explanation. We also propose to automatically generate "distractor" sentences to augment the bags and train the model to ignore the distractors. Evaluations on the widely used FB-NYT dataset show that our methods achieve new state-of-the-art accuracy while improving model explainability.
A Lay User Explainable Food Recommendation System Based on Hybrid Feature Importance Extraction and Large Language Models
Ecole Nationale Supérieure d’Informatique d’Alger, ESI ex-INI Alger(阿尔及尔国立高等信息学院);Centre de Recherche Panafricain en Management pour le Développement(CERPAMAD)(非洲管理发展研究中心);Umeå University(于默奥大学);Devoteam(德沃泰姆);University of Luxembourg(卢森堡大学);Luxembourg Institute of Science and Technology(卢森堡科学与技术研究所)
A Hierarchical Framework for Relation Extraction with Reinforcement Learning
Tsinghua University(清华大学);Institute for Artificial Intelligence, Tsinghua University (THUAI)(清华大学人工智能研究院);Beijing National Research Center for Information Science & Technology(北京信息科学与技术国家研究中心)
Active Testing: An Unbiased Evaluation Method for Distantly Supervised Relation Extraction
Shanghai Jiao Tong University(上海交通大学);ByteDance AI Lab(字节跳动人工智能实验室);Beijing Normal University (Zhuhai) & UIC(北京师范大学(珠海)与UIC);American University of Sharjah(沙迦美国大学)
Automatic Concept Extraction for Concept Bottleneck-based Video Classification
University of California Los Angeles(加州大学洛杉矶分校);University College London(伦敦大学学院);USC Information Sciences Institute(南加州大学信息科学研究所);Imperial College London(帝国理工学院);U.S. Army Research Laboratory(美国陆军研究实验室);U.S. Air Force Research Lab(美国空军研究实验室)
Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network
Toyota Technological Institute(丰田工业大学);Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST)(产业技术综合研究所人工智能研究中心)
Analyzing the Influence of Knowledge Graph Information on Relation Extraction
Universität Hamburg, Department of Informatics, Semantic Systems, Germany(汉堡大学信息学院语义系统研究所,德国);Leuphana Universität Lüneburg, Institute for Information Systems, Artificial Intelligence(吕贝克大学信息学院人工智能研究所)