DynamicPower at SemEval-2016 Task 8: Processing syntactic parse trees with a Dynamic Semantics core

Proceedings of SemEval-2016, pages 1148–1153, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics DynamicPower at SemEval-2016 Task 8: Processing syntactic parse trees with a Dynamic Semantics core Alastair Butler National Institute for Japanese Language and Linguistics ajb129@hotmail.com Abstract This is a system description paper for a sub- mission to Task 8 of SemEval-2016: Meaning Representation Parsing. No use was made of the training data provided by the task. Instead existing components were combined to form a pipeline able to take raw sentences as input and output meaning representations. Compo- nents are a part-of-speech tagger and parser trained on the Penn Parsed Corpus of Mod- ern British English to produce syntactic parse trees, a semantic role labeller and a named en- tity recogniser to supplement obtained parse trees with word sense, functional and named entity information, followed by an adapted Tarskian satisfaction relation for a Dynamic Semantics that is used to transform a syntac- tic parse into a predicate logic based meaning representation, followed by conversion to pen- man/AMR notation required for the task ap- praisal. 1 Introduction This is a system description paper for a submission to Task 8 of SemEval-2016: Meaning Representa- tion Parsing. Syntactic structures are first obtained by parsing raw language input, from which mean- ing representations are derived by printing off infor- mation accumulated with an adapted Tarskian satis- faction relation for a Dynamic Semantics (Dekker, 2012). This is akin to compositional approaches of formal semantics that view the task of reaching a semantic value as being rooted in first obtaining a syntactic parse. Key advantages are modularity and domain independence. This paper is structured as follows. Section 2 sketches the method used to obtain a syntactic parse. Section 3 covers reaching a semantic representation. Section 4 outlines conversion to penman/AMR no- tation. Section 5 reports experiment results. Section 6 is a conclusion. An appendix details how to run the available implementation. 2 Obtaining a syntactic parse The approach first needs a way to obtain syntactic parse trees. Major components used were the Stan- ford Log-linear Part-Of-Speech Tagger1 (Toutanova et al., 2003) and the Berkeley Parser2 (Petrov and Klein, 2003), both trained on data from the years of 1840–1908 of the Penn Parsed Corpus of Mod- ern British English3 (Kroch et al., 2010). The par- ticular setup followed suggestions of pre-processing and post-processing made by Kulick et al. (2014) and used tools, notably create_stripped, from the system of Fang, Butler and Yoshimoto (2014).4 Dating from over one hundred years ago, train- ing data for the syntactic parser was not chosen for suitability to a potential task domain, but instead for the practical benefit that parse results would con- form to the scheme proposed in the Annotation man- ual for the Penn Historical Corpora and the Parsed Corpus of Early English Correspondence (PCEEC) (Santorini, 2010). This scheme is exceptionally con- sistent, especially with regards to facilitating identi- 1http://nlp.stanford.edu/software/tagger.html 2https://github.com/slavpetrov/berkeleyparser 3http://www.ling.upenn.edu/hist-corpora/PPCMBE- RELEASE-1/index.html 4http://www.compling.jp/haruniwa/index.html 1148 fication of construction types (small clause, compar- ative, cleft, etc.) and …

Content truncated to 500 words