Unsupervised Person Slot Filling based on Graph Mining

Abstract

Slot filling aims to extract the values (slot fillers) of specific attributes (slots types) for a given entity (query) from a largescale corpus. Slot filling remains very challenging over the past seven years. We propose a simple yet effective unsupervised 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 dependency graph of a context sentence; (2) a relation is likely to exist if the query and candidate filler nodes are strongly connected by a relation-specific trigger. Thus we design a graph-based algorithm to automatically identify triggers based on personalized PageRank and Affinity Propagation 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-ofthe-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 promising results on Chinese slot filling can serve as a new benchmark.

Dialogue-Based Relation Extraction

“…However, trigger identification is perhaps as difficult as relation extraction, and it is labor-intensive to annotate large-scale datasets with triggers. Future research may explore how to identify triggers based on a small amount of human-annotated triggers as seeds (Bronstein et al, 2015;Yu and Ji, 2016).…”

Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures

“…One major challenge of SF is the lack of labeled data to generalize a wide range of features and patterns, especially for slot types that are in the long-tail of the quite skewed distribution of slot fills (Ji et al, 2011a). Previous work has mostly focused on compensating the data needs by constructing patterns (Sun et al, 2011;Roth et al, 2014b), automatic annotation by distant supervision (Surdeanu et al, 2011;Roth et al, 2014a;Adel et al, 2016), and constructing trigger lists for unsupervised dependency graph mining (Yu and Ji, 2016). Some work (Rodriguez et al, 2015;4 http://www.geonames.org/ Viswanathan et al, 2015;Rajani and Mooney, 2016a;Yu et al, 2014a;Rajani and Mooney, 2016b;Ma et al, 2015) also attempted to validate slot types by combining results from multiple systems.…”

Semi-Supervised Teacher-Student Architecture for Relation Extraction

“…For example, the verb died is highly indicative of the placeOfDeath relation. There are several ways of finding a candidate trigger such as the PageRank-inspired approach of Yu and Ji (2016). Here, for simplicity, we use the governing head of the two entities within their token interval (i.e., the node in the dependency graph that dominates the two entities) as a proxy for the trigger.…”