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

We present the contribution of Universitat Pompeu Fabra’s NLP group to the SemEval Task 9.2 (AMR-to-English Generation). The proposed generation pipeline comprises: (i) a series of rule-based graphtransducers for the syntacticization of the input graphs and the resolution of morphological agreements, and (ii) an off-theshelf statistical linearization component. 1 Setup of the system The generator we presented for Task 9.2 of SemEval 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 considered an extended rule-based version of (Ballesteros et al., 2015). The current generator has been mainly developed on the dependency Penn Treebank (Johansson and Nugues, 2007) automatically converted to predicate-argument structures, and adapted to the AMR inputs using SemEval’s training 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 contain all the morphological features needed to retrieve the final forms of all the words. The syntactic structures are then linearized with an off-theshelf tool, and finally the final forms of the words are retrieved. Our generator follows the theoretical model of the Meaning-Text Theory (Mel’čuk, 1988); the names of the intermediate layers used in Table 1 come from the MTT terminology. A 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 (Hajič et al., 2009). We assume 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 defined by a relation name preceded by a colon. 2 Generation from AMRs There are 932 activated graph-transduction rules in the pipeline; Steps 0 and 1 are AMR-specific, while in the rest of the grammars, only one rule is AMR-specific rule (at Step 3). 2.1 Mapping of AMRs onto predicate-argument graphs The mapping produces graphs that contain linguistic information only, which includes meaning bearing units and the following types of roles: