What can we learn from Semantic Tagging?

Autor:	Abdou, Mostafa, Kulmizev, Artur, Ravishankar, Vinit, Abzianidze, Lasha, Bos, Johan
Rok vydání:	2018
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	We investigate the effects of multi-task learning using the recently introduced task of semantic tagging. We employ semantic tagging as an auxiliary task for three different NLP tasks: part-of-speech tagging, Universal Dependency parsing, and Natural Language Inference. We compare full neural network sharing, partial neural network sharing, and what we term the learning what to share setting where negative transfer between tasks is less likely. Our findings show considerable improvements for all tasks, particularly in the learning what to share setting, which shows consistent gains across all tasks. Comment: 9 pages with references and appendixes. EMNLP 2018 camera ready
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1808.09716 Zobrazit plný text záznamu View this record from Arxiv