FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 920–923, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers Simon Mille 1, Roberto Carlini 1, Alicia Burga 1, Leo Wanner 1,2 1 Universitat Pompeu Fabra, Roc Boronat 138, 08018 Barcelona, Spain 2Instituci´o Catalana de Recerca i Estudis Avanc¸ats (ICREA), Lluis Companys 23, 08010 Barcelona, Spain firstname.lastname@upf.edu Abstract We present the contribution of Universitat Pompeu Fabra’s NLP group to the Sem- Eval Task 9.2 (AMR-to-English Genera- tion). The proposed generation pipeline comprises: (i) a series of rule-based graph- transducers for the syntacticization of the input graphs and the resolution of mor- phological agreements, and (ii) an off-the- shelf statistical linearization component. 1 Setup of the system The generator we presented for Task 9.2 of Sem- Eval is a pipeline of graph transducers called Fabra Open Rule-based Generator (FORGe).1 It is built upon work presented, e.g., in (Bohnet, 2006; Wanner et al., 2010). It can be also con- sidered an extended rule-based version of (Balles- teros et al., 2015). The current generator has been mainly developed on the dependency Penn Tree- bank (Johansson and Nugues, 2007) automatically converted to predicate-argument structures, and adapted to the AMR inputs using SemEval’s train- ing and evaluation sets. 1.1 Overview of the pipeline The core of the generator is rule-based: graph transduction grammars convert, in several steps, abstract AMRs into syntactic structures that con- tain all the morphological features needed to re- trieve the final forms of all the words. The syntac- tic structures are then linearized with an off-the- shelf tool, and finally the final forms of the words are retrieved. Our generator follows the theoreti- cal model of the Meaning-Text Theory (Mel’ˇcuk, 1988); the names of the intermediate layers used in Table 1 come from the MTT terminology. 1A slightly updated version of the submitted system can be found at https://www.upf.edu/web/taln/ resources Step Layermtt #rul. 0 Conversion of AMRs format ConS N/A into CoNLL’09 format 1 Mapping of AMRs onto SemS 190 predicate-argument graphs 2 Assignment of parts SemSpos 96 of speech 3 Derivation of deep syntactic DSyntS 267 structure 4 Introduction of function SSyntS 294 words 5 Resolution of agreements DMorphS 85 6 Linearization SMorphS N/A 7 Retrieval of surface forms Text 1 8 Post-processing Textfinal 4 Table 1: Overview of the AMR-to-text pipeline. 1.2 Input format conversion Since our generator cannot read the provided format, we converted the input AMRs to the CoNLL’09 format (Hajiˇc et al., 2009). We as- sume that each sentence in the original file has two components: a three-line comment with some metadata (id, date, original sentence, etc.) and the AMR tree. In order to map the AMR tree to CoNLL, we assume that: (i) each node of the tree will be defined as either (a) slash-separated variable-value pair, (b) only the variable name, or (c) only the value, and (ii) each branch will be de- fined by …

Content truncated to 500 words