Unsupervised AMR-Dependency Parse Alignment
نویسندگان
چکیده
In this paper, we introduce an Abstract Meaning Representation (AMR) to Dependency Parse aligner. Alignment is a preliminary step for AMR parsing, and our aligner improves current AMR parser performance. Our aligner involves several 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 experimental data, and enhances AMR parsing.
منابع مشابه
Learning to Map Dependency Parses to Abstract Meaning Representations
Abstract Meaning Representation (AMR) is a semantic representation language used to capture the meaning of English sentences. In this work, we propose an AMR parser based on dependency parse rewrite rules. This approach transfers dependency parses into AMRs by integrating the syntactic dependencies, semantic arguments, named entity and co-reference information. A dependency parse to AMR graph a...
متن کاملDependency Treelet Translation: Syntactically Informed Phrasal SMT
We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation. This method requires a source-language dependency parser, target language word segmentation and an unsupervised word alignment component. We align a parallel corpus, project the source dependency parse onto the target sentence, e...
متن کاملSTS-UHH at SemEval-2017 Task 1: Scoring Semantic Textual Similarity Using Supervised and Unsupervised Ensemble
This paper reports the STS-UHH participation in the SemEval 2017 shared Task 1 of Semantic Textual Similarity (STS). Overall, we submitted 3 runs covering monolingual and cross-lingual STS tracks. Our participation involves two approaches: unsupervised approach, which estimates a word alignment-based similarity score, and supervised approach, which combines dependency graph similarity and cover...
متن کاملSupervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphs
As alignment links are not given between English sentences and Abstract Meaning Representation (AMR) graphs in the AMR annotation, automatic alignment becomes indispensable for training an AMR parser. Previous studies formalize it as a string-to-string problem, and solve it in an unsupervised way. In this paper, we formalize it as a syntax-based alignment problem, and solve it in a supervised m...
متن کاملParser Adaptation and Projection with Quasi-Synchronous Grammar Features
We connect two scenarios in structured learning: adapting a parser trained on one corpus to another annotation style, and projecting syntactic annotations from one language to another. We propose quasisynchronous grammar (QG) features for these structured learning tasks. That is, we score a aligned pair of source and target trees based on local features of the trees and the alignment. Our quasi...
متن کامل