Encoding Semantic Resources in Syntactic Structures for Passage Reranking

Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pages 664–672, Gothenburg, Sweden, April 26-30 2014. c⃝2014 Association for Computational Linguistics Encoding Semantic Resources in Syntactic Structures for Passage Reranking Kateryna Tymoshenko Trento RISE 38123 Povo (TN), Italy k.tymoshenko@trentorise.eu Alessandro Moschitti Qatar Computing Research Instit. 5825 Doha, Qatar amoschitti@qf.org.qa Aliaksei Severyn University of Trento 38123 Povo (TN), Italy severyn@disi.unitn.it Abstract In this paper, we propose to use seman- tic knowledge from Wikipedia and large- scale structured knowledge datasets avail- able as Linked Open Data (LOD) for the answer passage reranking task. We represent question and candidate answer passages with pairs of shallow syntac- tic/semantic trees, whose constituents are connected using LOD. The trees are pro- cessed by SVMs and tree kernels, which can automatically exploit tree fragments. The experiments with our SVM rank algo- rithm on the TREC Question Answering (QA) corpus show that the added relational information highly improves over the state of the art, e.g., about 15.4% of relative im- provement in P@1. 1 Introduction Past work in TREC QA, e.g. (Voorhees, 2001), and more recent work (Ferrucci et al., 2010) in QA has shown that, to achieve human perfor- mance, semantic resources, e.g., Wikipedia1, must be utilized by QA systems. This requires the design of rules or machine learning features that exploit such knowledge by also satisfying syntactic constraints, e.g., the semantic type of the answer must match the question focus words. The engineering of such rules for open domain QA is typically very costly. For instance, for automatically deriving the correctness of the answer passage in the following question/answer passage (Q/AP) pair (from the TREC corpus2): Q: What company owns the soft drink brand “Gatorade”? A: Stokely-Van Camp bought the formula and started marketing the drink as Gatorade in 1967. Quaker Oats Co. took over Stokely-Van Camp in 1983. 1http://www.wikipedia.org 2It will be our a running example for the rest of the paper. we would need to write the following complex rules: is(Quaker Oats Co.,company), own(Stokely-Van Camp,Gatorade), took over(Quaker Oats Co.,Stokely-Van Camp), took over(Y, Z)→own(Z,Y), and carry out logic unification and resolution. Therefore, approaches that can automatically generate patterns (i.e., features) from syntactic and semantic representations of the Q/AP are needed. In this respect, our previous work, e.g., (Moschitti et al., 2007; Moschitti and Quarteroni, 2008; Moschitti, 2009), has shown that tree kernels for NLP, e.g., (Moschitti, 2006), can exploit syntactic patterns for answer passage reranking significantly improving search engine baselines. Our more recent work, (Severyn and Moschitti, 2012; Severyn et al., 2013b; Severyn et al., 2013a), has shown that using automatically produced semantic labels in shallow syntactic trees, such as question category and question focus, can further improve passage reranking and answer extraction (Severyn and Moschitti, 2013). However, such methods cannot solve the class of examples above as they do not use background knowledge, which is essential to answer com- plex questions. On the other hand, Kalyanpur et al. (2011) and Murdock et al. (2012) showed that semantic match …

Content truncated to 500 words