Abstract
This paper describes our recursive system for SemEval-2019 Task 1: Cross-lingual Semantic Parsing with UCCA. Each recursive step consists of two parts. We first perform semantic parsing using a sequence tagger to estimate the probabilities of the UCCA categories in the sentence. Then, we apply a decoding policy which interprets these probabilities and builds the graph nodes. Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking features that reflects the decisions made in previous steps. Process continues until the terminal nodes are reached. We chose a standard neural tagger and we focus on our recursive parsing strategy and on the cross lingual transfer problem to develop a robust model for the French language, using only few training samples- Anthology ID:
- S19-2015
- Volume:
- Proceedings of the 13th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota, USA
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 107–112
- Language:
- URL:
- https://aclanthology.org/S19-2015
- DOI:
- 10.18653/v1/S19-2015
- Cite (ACL):
- Gabriel Marzinotto, Johannes Heinecke, and Géraldine Damnati. 2019. MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 107–112, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
- Cite (Informal):
- MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging (Marzinotto et al., SemEval 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/S19-2015.pdf
- Data
- Bio, FrameNet