Unsupervised Person Slot Filling based on Graph Mining

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 44–53, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Unsupervised Person Slot Filling based on Graph Mining Dian Yu Heng Ji Computer Science Department Rensselaer Polytechnic Institute Troy, NY 12180, USA {yud2,jih}@rpi.edu Abstract Slot filling aims to extract the values (slot fillers) of specific attributes (slots types) for a given entity (query) from a large- scale corpus. Slot filling remains very challenging over the past seven years. We propose a simple yet effective unsuper- vised approach to extract slot fillers based on the following two observations: (1) a trigger is usually a salient node relative to the query and filler nodes in the depen- dency graph of a context sentence; (2) a relation is likely to exist if the query and candidate filler nodes are strongly con- nected by a relation-specific trigger. Thus we design a graph-based algorithm to au- tomatically identify triggers based on per- sonalized PageRank and Affinity Prop- agation for a given (query, filler) pair and then label the slot type based on the identified triggers. Our approach achieves 11.6%-25% higher F-score over state-of- the-art English slot filling methods. Our experiments also demonstrate that as long as a few trigger seeds, name tagging and dependency parsing capabilities exist, this approach can be quickly adapted to any language and new slot types. Our promis- ing results on Chinese slot filling can serve as a new benchmark. 1 Introduction The goal of the Text Analysis Conference Knowl- edge Base Population (TAC-KBP) Slot Filling (SF) task (McNamee and Dang, 2009; Ji et al., 2010; Ji et al., 2011; Surdeanu and Ji, 2014) is to extract the values (fillers) of specific attributes (slot types) for a given entity (query) from a large- scale corpus and provide justification sentences to support these slot fillers. KBP defines 25 slot types for persons (e.g., spouse) and 16 slots for organizations (e.g., founder). For example, given a person query “Dominich Dunne” and slot type spouse, a SF system may extract a slot filler “Ellen Griffin” and its justification sentence E1 as shown in Figure 1. E1: Ellen Griffin Dunne, from whom he was divorced in 1965, died in 1997. Ellen Griffin Dunne whom in he was 1965 Dominick Dunne in 1997 from case nmod nsubjpass auxpass nmod case coreference case Person Person | Query Year Year died divorced Figure 1: Extended dependency tree for E1. Slot filling remains a very challenging task. The two most successful state-of-the-art techniques are as follows. (1) Supervised classification. Considering any pair of query and candidate slot filler as an instance, these approaches train a classifier from manually labeled data through active learning (Angeli et al., 2014b) or noisy labeled data through distant supervision (Angeli et al., 2014a; Surdeanu et al., 2010) to predict the existence of a specific relation between them. (2) Pattern matching. These approaches extract and generalize lexical and syntactic patterns auto- matically or semi-automatically (Sun et al., 2011; Li et al., …

Content truncated to 500 words