Learning Typed Entailment Graphs with Global Soft Constraints

Learning Typed Entailment Graphs with Global Soft Constraints Mohammad Javad Hosseini⋆§ Nathanael Chambers⋆⋆ Siva Reddy† Xavier R. Holt‡ Shay B. Cohen⋆ Mark Johnson‡ and Mark Steedman⋆ ⋆University of Edinburgh §The Alan Turing Institute, UK ⋆⋆United States Naval Academy †Stanford University ‡Macquarie University javad.hosseini@ed.ac.uk, nchamber@usna.edu, sivar@stanford.edu {xavier.ricketts-holt,mark.johnson}@mq.edu.au {scohen,steedman}@inf.ed.ac.uk Abstract This paper presents a new method for learn- ing typed entailment graphs from text. We extract predicate-argument structures from multiple-source news corpora, and compute local distributional similarity scores to learn entailments between predicates with typed arguments (e.g., person contracted disease). Previous work has used transitivity con- straints to improve local decisions, but these constraints are intractable on large graphs. We instead propose a scalable method that learns globally consistent similarity scores based on new soft constraints that consider both the structures across typed entailment graphs and inside each graph. Learning takes only a few hours to run over 100K predicates, and our results show large improvements over local similarity scores on two entailment data sets. We further show improvements over paraphrases and entailments from the Paraphrase Database and prior state-of-the-art entailment graphs. We show that the entailment graphs improve performance in a downstream task. 1 Introduction Recognizing textual entailment and paraphrasing is critical to many core natural language process- ing applications such as question answering and semantic parsing. The surface form of a sentence that answers a question such as “Does Verizon own Yahoo?” frequently does not directly corre- spond to the form of the question, but is rather a paraphrase or an expression such as “Verizon bought Yahoo,” that entails the answer. The lack of a well-established form-independent semantic representation for natural language is the most im- portant single obstacle to bridging the gap between queries and text resources. This paper seeks to learn meaning postulates (e.g., buying entails owning) that can be used to augment the standard form-dependent semantics. Our immediate goal is to learn entailment rules be- tween typed predicates with two arguments, where the type of each predicate is determined by the types of its arguments. We construct typed entail- ment graphs, with typed predicates as nodes and entailment rules as edges. Figure 1 shows simple examples of such graphs with arguments of types company,company and person,location. Entailment relations are detected computing a similarity score between the typed predicates based on the distributional inclusion hypothesis, which states that a word (predicate) u entails another word (predicate) v if in any context that u can be used, v can be used in its place (Dagan et al., 1999; Geffet and Dagan, 2005; Herbelot and Ganesalingam, 2013; Kartsaklis and Sadrzadeh, 2016). Most previous work has taken a “local learning” approach (Lin, 1998; Weeds and Weir, 2003; Szpektor and Dagan, 2008; Schoenmackers et al., 2010), namely, learning entailment rules in- dependently from each other. One problem facing local learning approaches is that many correct edges are not identified be- cause of data sparsity and many wrong edges are spuriously identified as valid entailments. A “global learning” approach, where dependencies between entailment …

Content truncated to 500 words