Skip to main navigation Skip to search Skip to main content

HIT-SCIR at MRP 2019: A unified pipeline for meaning representation parsing via efficient training and effective encoding

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes our system (HIT-SCIR) for the CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. We extended the basic transition-based parser with two improvements: a) Efficient Training by realizing stack LSTM parallel training; b) Effective Encoding via adopting deep contextualized word embeddings BERT (Devlin et al., 2019). Generally, we proposed a unified pipeline to meaning representation parsing, including framework-specific transition-based parsers, BERT-enhanced word representation, and post-processing. In the final evaluation, our system was ranked first according to ALL-F1 (86.2%) and especially ranked first in UCCA framework (81.67%).

Original languageEnglish
Title of host publicationCoNLL 2019 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
PublisherAssociation for Computational Linguistics
Pages76-85
Number of pages10
ISBN (Electronic)9781950737604
DOIs
StatePublished - 2020
Event2019 Shared Task on Cross-Framework Meaning Representation Parsing, MRP 2019 at the 23rd Conference for Computational Language Learning, CoNLL 2019 - Hong Kong, China
Duration: 3 Nov 2019 → …

Publication series

NameCoNLL 2019 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning

Conference

Conference2019 Shared Task on Cross-Framework Meaning Representation Parsing, MRP 2019 at the 23rd Conference for Computational Language Learning, CoNLL 2019
Country/TerritoryChina
CityHong Kong
Period3/11/19 → …

Fingerprint

Dive into the research topics of 'HIT-SCIR at MRP 2019: A unified pipeline for meaning representation parsing via efficient training and effective encoding'. Together they form a unique fingerprint.

Cite this