Joint Inference for Knowledge Extraction from Biomedical Literature

Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the ACL, pages 813–821, Los Angeles, California, June 2010. c⃝2010 Association for Computational Linguistics Joint Inference for Knowledge Extraction from Biomedical Literature Hoifung Poon∗ Dept. of Computer Sci. & Eng. University of Washington Seattle, WA 98195 hoifung@cs.washington.edu Lucy Vanderwende Microsoft Research Redmond, WA 98052 Lucy.Vanderwende@microsoft.com Abstract Knowledge extraction from online reposito- ries such as PubMed holds the promise of dramatically speeding up biomedical research and drug design. After initially focusing on recognizing proteins and binary interactions, the community has recently shifted their at- tention to the more ambitious task of recogniz- ing complex, nested event structures. State-of- the-art systems use a pipeline architecture in which the candidate events are identified first, and subsequently the arguments. This fails to leverage joint inference among events and arguments for mutual disambiguation. Some joint approaches have been proposed, but they still lag much behind in accuracy. In this pa- per, we present the first joint approach for bio- event extraction that obtains state-of-the-art results. Our system is based on Markov logic and adopts a novel formulation by jointly pre- dicting events and arguments, as well as indi- vidual dependency edges that compose the ar- gument paths. On the BioNLP’09 Shared Task dataset, it reduced F1 errors by more than 10% compared to the previous best joint approach. 1 Introduction Extracting knowledge from unstructured text has been a long-standing goal of NLP and AI. The ad- vent of the World Wide Web further increases its importance and urgency by making available an as- tronomical number of online documents containing virtually unlimited amount of knowledge (Craven et ∗ This research was conducted during the author’s intern- ship at Microsoft Research. al., 1999). A salient example domain is biomedical literature: the PubMed1 online repository contains over 18 million abstracts on biomedical research, with more than two thousand new abstracts added each day; the abstracts are written in grammatical English, which enables the use of advanced NLP tools such as syntactic and semantic parsers. Traditionally, research on knowledge extraction from text is primarily pursued in the field of in- formation extraction with a rather confined goal of extracting instances for flat relational schemas with no nested structures (e.g, recognizing protein names and protein-protein interaction (PPI)). This restric- tion mainly stems from limitations in available re- sources and algorithms. The BioNLP’09 Shared Task (Kim et al., 2009) is one of the first that faced squarely information needs that are complex and highly structured. It aims to extract nested bio-molecular events from research abstracts, where an event may have variable number of arguments and may contain other events as arguments. Such nested events are ubiquitous in biomedical literature and can effectively represent complex biomedical knowledge and subsequently support reasoning and automated discovery. The task has generated much interest, with twenty-four teams having submitted their results. The top system by UTurku (Bjorne et al., 2009) attained the state-of-the-art F1 of 52.0%. The nested event structures make this task …

Content truncated to 500 words