5 Hits in 3.8 sec

Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing

Yuta Koreeda, Gaku Morio, Terufumi Morishita, Hiroaki Ozaki, Kohsuke Yanai
2019 Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning  
This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task.  ...  We proposed a unified encoder-to-biaffine network for all five frameworks, which effectively incorporates a shared encoder to extract rich input features, decoder networks to generate anchorless nodes  ...  Figure 1 : 1 The overview of the proposed unified encoder-to-biaffine network for cross-framework meaning representation parsing.  ... 
doi:10.18653/v1/k19-2011 dblp:conf/conll/KoreedaMMOY19 fatcat:v3hssjmstna5hpijvopc6fjgli

MRP 2019: Cross-Framework Meaning Representation Parsing

Stephan Oepen, Omri Abend, Jan Hajic, Daniel Hershcovich, Marco Kuhlmann, Tim O'Gorman, Nianwen Xue, Jayeol Chun, Milan Straka, Zdenka Uresova
2019 Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning  
The 2019 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks.  ...  Five distinct approaches to the representation of sentence meaning in the form of directed graphs were represented in the training and evaluation data for the task, packaged in a uniform graph abstraction  ...  We are grateful to the Nordic e-Infrastructure Collaboration for their support to the Nordic Language Processing Laboratory (NLPL), which has provided technical infrastructure for the MRP 2019 task.  ... 
doi:10.18653/v1/k19-2001 dblp:conf/conll/OepenAHHKOXCSU19 fatcat:o2apo53amnhpvfzcdfmq52fyki

Hitachi at MRP 2020: Text-to-Graph-Notation Transducer

Hiroaki Ozaki, Gaku Morio, Yuta Koreeda, Terufumi Morishita, Toshinori Miyoshi
2020 Proceedings of the CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing   unpublished
This paper presents our proposed parser for the shared task on Meaning Representation Parsing (MRP 2020) at CoNLL, where participant systems were required to parse five types of graphs in different languages  ...  As a result, ensemble versions of the parser tied for 1st place in both cross-framework and cross-lingual tracks.  ...  We would like to thank the anonymous reviewers for their helpful comments. We also thank Dr. Masaaki Shimizu for the convenience of the computational resources.  ... 
doi:10.18653/v1/2020.conll-shared.4 fatcat:5ae2xrao65erfmkcqgnm3xob2i

Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing [article]

Necva Bölücü, Burcu Can
2021 arXiv   pre-print
The paper not only presents the existing approaches proposed for UCCA representation, but also proposes a novel self-attentive neural parsing model for the UCCA representation.  ...  We present the results for both single-lingual and cross-lingual tasks using zero-shot and few-shot learning for low-resource languages.  ...  Hitachi [51] is a unified encoder-to-biaffine network with a shared architecture, and JBNU [52] is a unified parsing model that is based on a biaffine attention with a BiLSTM encoder and a biaffine-attention  ... 
arXiv:2110.00621v1 fatcat:5maoxftntbbpvj4umfxrnf5ibm

Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing

Hiroaki Ozaki, Gaku Morio, Terufumi Morishita, Toshinori Miyoshi
2021 Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   unpublished
This paper describes the first report on crosslingual transfer for semantic dependency parsing.  ...  We present the insight that there are two different kinds of cross-linguality, namely surface level and semantic level, and try to capture both kinds of cross-linguality by combining annotation projection  ...  Hitachi at MRP 2019: Unified encoder-to-biaffine network for cross-framework meaning representation pars- ing.  ... 
doi:10.18653/v1/2021.eacl-main.221 fatcat:ehw7omqgfvhdtkoxuyqpxtay5y