The First Shared Task on Discourse Representation Structure Parsing
- Lasha Abzianidze, Rik van Noord, Hessel Haagsma, Johan Bos
- Computer ScienceProceedings of the IWCS Shared Task on Semantic…
- 1 May 2019
The paper presents the IWCS 2019 shared task on semantic parsing where the goal is to produce Discourse Representation Structures (DRSs) for English sentences and displayed improvements over the existing state-of-the-art parser.
Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT
- Rik van Noord, Antonio Toral, Johan Bos
- Computer ScienceConference on Empirical Methods in Natural…
- 1 November 2020
A new method of analysis based on semantic tags demonstrates that the character-level representations improve performance across a subset of selected semantic phenomena.
Dealing with Co-reference in Neural Semantic Parsing
- Rik van Noord, J. Bos
- Computer ScienceSemDeep@IWCS
- 19 October 2017
Three different methods for dealing with co-indexed variables in the output of neural semantic parsing of abstract meaning representations are reviewed: copying concepts during training and restoring co- Indexation in a post-processing step; explicit indexing of co- indexation; and using absolute paths to designate co-Indexing.
Character-based Neural Semantic Parsing
- Rik van Noord
- Computer Science
- 2021
Proceedings of the IWCS Shared Task on Semantic Parsing
- May, Lasha Abzianidze, Rik van Noord, Hessel Haagsma, Johan Bos
- Computer Science
- 2019
The paper presents the IWCS 2019 shared task on semantic parsing where the goal is to produce Discourse Representation Structures (DRSs) for English sentences and displayed improvements over the existing state-of-the-art parser.
Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese
- Chunliu Wang, Rik van Noord, Arianna Bisazza, Johan Bos
- Computer ScienceAnnual Meeting of the Association for…
- 2021
Overall, characters are preferred as input, both for English and Chinese, and even with DRSs based on English, good results for Chinese are obtained.
Automatic Discrimination of Human and Neural Machine Translation: A Study with Multiple Pre-Trained Models and Longer Context
- Tobias van der Werff, Rik van Noord, Antonio Toral
- Computer ScienceEuropean Association for Machine Translation…
- 2022
This work uses state-of-the-art pre-trained LMs, as well as the test sets of the WMT news shared tasks as training data, to ensure the sentences were not seen during training of the MT system itself.