Unsupervised AMR-Dependency Parse Alignment

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 558–567, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics Unsupervised AMR-Dependency Parse Alignment Wei-Te Chen Department of Computer Science University of Colorado Boulder weite.chen@colorado.edu Martha Palmer Department of Linguistics University of Colorado Boulder martha.palmer@colorado.edu Abstract In this paper, we introduce an Abstract Meaning Representation (AMR) to De- pendency Parse aligner. Alignment is a preliminary step for AMR parsing, and our aligner improves current AMR parser performance. Our aligner involves sev- eral different features, including named entity tags and semantic role labels, and uses Expectation-Maximization training. Results show that our aligner reaches an 87.1% F-Score score with the experimen- tal data, and enhances AMR parsing. 1 Introduction Abstract Meaning Representation (AMR) (Ba- narescu et al., 2013) is a semantic representation that expresses the logical meaning of English sen- tences with rooted, directed, acylic graphs. AMR associates semantic concepts with the nodes on a graph, while the relations are the label edges between concept nodes. Meanwhile, AMR re- lies heavily on predicate-argument relations from PropBank (Palmer et al., 2005), which share several edge labels. The representation also en- codes rich information, like semantic roles (all the “ARGN” tags from PropBank), named enti- ties (NE) (“person”, “location”, etc., concepts), wiki-links (“:wiki” tags), and co-reference (reuse of variables, e.g., p). An example AMR in PEN- MAN format (Matthiessen and Bateman, 1991) is shown in Figure 1. The design of an AMR to English sentence aligner is the first step for implementation of an AMR parser, since AMR annotation does not contain links between each AMR concept and the original span of words. The basic alignment strategy is to link the AMR tokens (either con- cepts or edge labels) with their corresponding (j / join-01 :ARG0 (p / person :wiki - :name (p2 / name :op1 "Pierre" :op2 "Vinken") :age (t / temporal-quantity :quant 61 :unit (y / year))) :ARG1 (b / board :ARG1-of (h / have-org-role-91 :ARG0 p :ARG2 (d2 / director :mod (e / executive :polarity -)))) :time (d / date-entity :month 11 :day 29)) Figure 1: The AMR annotation of sentence “Pierre Vinken, 61 years old, will join the board as a nonexecutive director Nov. 29.” in PENMAN for- mat span of words. Another strategy is to find the alignment from an AMR concept to a word node in a dependency parse tree, the goal of this paper. A dependency parse tree is a good structure for attaching more information, e.g. named entity tags, lemma, and semantic role labels, etc., and provides richer syntactic information than the span of words. An alignment between an AMR concept and a dependency node represents a cor- respondence between the meaning of this concept and its child concepts and the phrase governed by the dependency node (i.e., head word). An exam- ple alignment is shown in Figure 2. For example, the word node “Vinken” on the dependency parse side in Figure 2 links to …

Content truncated to 500 words