Supersense Tagging with a Combination of Character, Subword, and Word-level Representations

Information

Title Supersense Tagging with a Combination of Character, Subword, and Word-level Representations
Authors Youhyun Shin, Sang-goo Lee
Year 2017 / 09
Keywords
Publication Type International Conference
Publication The 1st Workshop on Subword and Character level models in NLP (SCLeM) at EMNLP 2017

Abstract

Recently, there has been increased interest in utilizing characters or subwords for natural language processing (NLP) tasks. However, the effect of utilizing character, subword, and word-level information simultaneously has not been examined so far. In this paper, we propose a model to leverage various levels of input features to improve on the performance of an supersense tagging task. Detailed analysis of experimental results show that different levels of input representation offer distinct characteristics that explain performance discrepancy among different tasks.