Multi-level Representations for Fine-Grained Typing of Knowledge Base Entities

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 578–589, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics Multi-level Representations for Fine-Grained Typing of Knowledge Base Entities Yadollah Yaghoobzadeh and Hinrich Sch¨utze Center for Information and Language Processing LMU Munich, Germany yadollah@cis.lmu.de Abstract Entities are essential elements of natu- ral language. In this paper, we present methods for learning multi-level represen- tations of entities on three complemen- tary levels: character (character patterns in entity names extracted, e.g., by neural networks), word (embeddings of words in entity names) and entity (entity em- beddings). We investigate state-of-the- art learning methods on each level and find large differences, e.g., for deep learn- ing models, traditional ngram features and the subword model of fasttext (Bo- janowski et al., 2016) on the character level; for word2vec (Mikolov et al., 2013) on the word level; and for the order-aware model wang2vec (Ling et al., 2015a) on the entity level. We confirm experimentally that each level of representation contributes complemen- tary information and a joint representation of all three levels improves the existing embedding based baseline for fine-grained entity typing by a large margin. Addi- tionally, we show that adding information from entity descriptions further improves multi-level representations of entities. 1 Introduction Knowledge about entities is essential for under- standing human language. This knowledge can be attributional (e.g., canFly, isEdible), type-based (e.g., isFood, isPolitician, isDisease) or relational (e.g, marriedTo, bornIn). Knowledge bases (KBs) are designed to store this information in a struc- tured way, so that it can be queried easily. Exam- ples of such KBs are Freebase (Bollacker et al., 2008), Wikipedia, Google knowledge graph and YAGO (Suchanek et al., 2007). For automatic up- dating and completing the entity knowledge, text resources such as news, user forums, textbooks or any other data in the form of text are important sources. Therefore, information extraction meth- ods have been introduced to extract knowledge about entities from text. In this paper, we focus on the extraction of entity types, i.e., assigning types to – or typing – entities. Type information can help extraction of relations by applying constraints on relation arguments. We address a problem setting in which the fol- lowing are given: a KB with a set of entities E, a set of types T and a membership function m : E × T �→ {0, 1} such that m(e, t) = 1 iff entity e has type t; and a large corpus C in which mentions of E are annotated. In this setting, we address the task of fine-grained entity typing: we want to learn a probability function S(e, t) for a pair of entity e and type t and based on S(e, t) in- fer whether m(e, t) = 1 holds, i.e., whether entity e is a member of type t. We address this problem by learning a multi- level representation for an entity that contains the information necessary for typing it. One …

Content truncated to 500 words