Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs

Yin, Wenpeng; Yaghoobzadeh, Yadollah; Schütze, Hinrich (August 2018): Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs. The 27th International Conference on Computational Linguistics; COLING2018, 20. - 26. August 2018, Santa Fe, New Mexico, USA.

Abstract

Large scale knowledge graphs (KGs) such as Freebase are generally incomplete. Reasoning over multi-hop (mh) KG paths is thus an important capability that is needed for question answering or other NLP tasks that require knowledge about the world. mh-KG reasoning includes diverse scenarios, e.g., given a head entity and a relation path, predict the tail entity; or given two enti- ties connected by some relation paths, predict the unknown relation between them. We present ROPs, recurrent one-hop predictors, that predict entities at each step of mh-KB paths by using recurrent neural networks and vector representations of entities and relations, with two benefits: (i) modeling mh-paths of arbitrary lengths while updating the entity and relation representations by the training signal at each step; (ii) handling different types of mh-KG reasoning in a unified framework. Our models show state-of-the-art for two important multi-hop KG reasoning tasks: Knowledge Base Completion and Path Query Answering

• Item Type: Conference or Workshop Item (Paper)
• EU-FP7/Horizon 2020 Grant Agreement Number: info:eu-repo/grantAgreement/EC/H2020/740516
• EU Projects: Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement
• Published in: Bender, Emily M. and Derczynski, Leon and Isabelle, Pierre (eds.) . Proceedings of the 27th International Conference on Computational Linguistics. Stroudsburg, PA: Association for Computational Linguistics, pp. 2369-2378
• Research Centers: Center for Information and Language Processing (CIS)
• Subjects: 000 Computer science, information and general works > 000 Computer science, knowledge, and systems; 000 Computer science, information and general works > 004 Data processing computer science; 400 Language > 400 Language; 400 Language > 410 Linguistics
• Place of Publication: Stroudsburg, PA
• Annotation: ISBN 978-1-948087-64-3
• Language: English