paper-with-me

Papers

Robust Incremental Neural Semantic Graph Parsing

2017-04-24 · ACL 2017 7 · Jan Buys, Phil Blunsom

Parsing sentences to linguistically-expressive semantic representations is a key goal of Natural Language Processing. Yet statistical parsing has focused almost exclusively on bilexical dependencies or domain-specific logical forms. We propose a neural encoder-decoder transition-based parser which is the first full-coverage semantic graph parser for Minimal Recursion Semantics (MRS). The model architecture uses stack-based embedding features, predicting graphs jointly with unlexicalized predicates and their token alignments. Our parser is more accurate than attention-based baselines on MRS, and on an additional Abstract Meaning Representation (AMR) benchmark, and GPU batch processing makes it an order of magnitude faster than a high-precision grammar-based parser. Further, the 86.69% Smatch score of our MRS parser is higher than the upper-bound on AMR parsing, making MRS an attractive choice as a semantic representation.

📄 PDF Abstract BibTeX arXiv:1704.07092

Code (1)

janmbuys/DeepDeepParser 공식 구현 tf

Tasks

Abstract Meaning RepresentationAMR ParsingDecoderGPU

Similar Papers 제목 키워드 기반

A Double-Graph Based Framework for Frame Semantic Parsing

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Frame semantic parsing is a fundamental NLP task, which consists of three subtasks: frame identification, argument identification and role classification. Most previous studies tend to neglect relations between different…

graph constructionSemantic Parsing

A Double-Graph Based Framework for Frame Semantic Parsing

2022-06-18 · NAACL 2022 7 · Ce Zheng, Xudong Chen, Runxin Xu, Baobao Chang

Frame semantic parsing is a fundamental NLP task, which consists of three subtasks: frame identification, argument identification and role classification. Most previous studies tend to neglect relations between different…

graph constructionSemantic Parsing

Core Semantic First: A Top-down Approach for AMR Parsing

2019-09-10 · IJCNLP 2019 11 · Deng Cai, Wai Lam

We introduce a novel scheme for parsing a piece of text into its Abstract Meaning Representation (AMR): Graph Spanning based Parsing (GSP). One novel characteristic of GSP is that it constructs a parse graph incrementall…

Abstract Meaning RepresentationAMR ParsingSentence

Type-Driven Incremental Semantic Parsing with Polymorphism

2014-11-19 · HLT 2015 5 · Kai Zhao, Liang Huang

Semantic parsing has made significant progress, but most current semantic parsers are extremely slow (CKY-based) and rather primitive in representation. We introduce three new techniques to tackle these problems. First, …

Semantic ParsingVocal Bursts Type Prediction

Semantic Role Labeling Improves Incremental Parsing

2015-07-01 · IJCNLP 2015 7 · Ioannis Konstas, Frank Keller
Information RetrievalMachine TranslationSemantic Role LabelingSpeech Recognition