Reading The Web with Learned Syntactic-Semantic Inference Rules

Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1017–1026, Jeju Island, Korea, 12–14 July 2012. c⃝2012 Association for Computational Linguistics Reading The Web with Learned Syntactic-Semantic Inference Rules Ni Lao1∗, Amarnag Subramanya2, Fernando Pereira2, William W. Cohen1 1Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA 2Google Research, 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA nlao@cs.cmu.edu, {asubram, pereira}@google.com, wcohen@cs.cmu.edu Abstract We study how to extend a large knowledge base (Freebase) by reading relational informa- tion from a large Web text corpus. Previous studies on extracting relational knowledge from text show the potential of syntactic patterns for extraction, but they do not exploit background knowledge of other relations in the knowledge base. We describe a distributed, Web-scale implementation of a path-constrained random walk model that learns syntactic-semantic inference rules for binary relations from a graph representation of the parsed text and the knowledge base. Experiments show significant accuracy im- provements in binary relation prediction over methods that consider only text, or only the existing knowledge base. 1 Introduction Manually-created knowledge bases (KBs) often lack basic information about some entities and their relationships, either because the information was missing in the initial sources used to create the KB, or because human curators were not confident about the status of some putative fact, and so they excluded it from the KB. For instance, as we will see in more detail later, many person entries in Freebase (Bollacker et al., 2008) lack nationality information. To fill those KB gaps, we might use general rules, ideally automatically learned, such as “if person was born in town and town is in country ∗This research was carried out during an internship at Google Research then the person is a national of the country.” Of course, rules like this may be defeasible, in this case for example because of naturalization or political changes. Nevertheless, many such imperfect rules can be learned and combined to yield useful KB completions, as demonstrated in particular with the Path-Ranking Algorithm (PRA) (Lao and Cohen, 2010; Lao et al., 2011), which learns such rules on heterogenous graphs for link prediction tasks. Alternatively, we may attempt to fill KB gaps by applying relation extraction rules to free text. For instance, Snow et al. (2005) and Suchanek et al. (2006) showed the value of syntactic patterns in extracting specific relations. In those approaches, KB tuples of the relation to be extracted serve as positive training examples to the extraction rule induction algorithm. However, the KB contains much more knowledge about other relations that could potentially be helpful in improving relation extraction accuracy and coverage, but that is not used in such purely text-based approaches. In this work, we use PRA to learn weighted rules (represented as graph path patterns) that combine both semantic (KB) and syntactic infor- mation encoded respectively as edges in a graph- structured KB, and as syntactic dependency edges in dependency-parsed Web text. Our approach can easily incorporate existing …

Content truncated to 500 words