Corpus-level Fine-grained Entity Typing Using Contextual Information

Abstract

This paper addresses the problem of corpus-level entity typing, i.e., inferring from a large corpus that an entity is a member of a class such as "food" or "artist". The application of entity typing we are interested in is knowledge base completion, specifically, to learn which classes an entity is a member of. We propose FIGMENT to tackle this problem. FIGMENT is embedding-based and combines (i) a global model that scores based on aggregated contextual information of an entity and (ii) a context model that first scores the individual occurrences of an entity and then aggregates the scores. In our evaluation, FIGMENT strongly outperforms an approach to entity typing that relies on relations obtained by an open information extraction system.

Multi-source named entity typing for social media

“…We represent ReVerb distributional patterns as features in our framework. Similarly to previous researchers (Yaghoobzadeh and Schütze, 2015), we find ReVerb triplets to perform poorly when used as a standalone information source. We discuss the reasons for this in detail below.…”

“…We discuss the reasons for this in detail below. Yaghoobzadeh and Schütze (2015) presented an embedding based approach for the typing of named entities. They compute embedding vectors for words, entities and semantic types using an annotated version of the ClueWeb Web corpus, in which entity mentions have been tagged with their Freebase IDs.…”

“…Similarly to previous works (Lin et al, 2012;Yaghoobzadeh and Schütze, 2015), we consider here lexico-syntactic contexts in the form of <subject,relation,object> triplets extracted from Web documents using the ReVerb algorithm (Fader et al, 2011).…”

“…Previously, researchers have proposed to infer the semantic types of entity names based on local distributional evidence harvested from Web documents (Lin et al, 2012;Yaghoobzadeh and Schütze, 2015), however such distributional evidence is sparse and costly to obtain for long tail names. We claim that in order to infer the semantic types of infrequent entity names, it is neces-sary to model global, semi-structured, contextual evidence of the respective name mentions.…”

Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning

“…Moreover, Yaghoobzadeh and Schutze (Yaghoobzadeh and Schütze, 2015) addressed an entity typing task by building an embedding of words and entities on a corpus with annotated entities (i.e., FACC1 (Gabrilovich et al, 2013)) using the skip-gram model. Compared to our method, in addition to the significant difference between their task and NED, their embedding does not incorporate the link graph data of KB, which is known to be highly important for NED.…”