Výsledky vyhledávání

Report

Autor: Inoue, Katsuma, Ohara, Soh, Kuniyoshi, Yasuo, Nakajima, Kohei

Language is an outcome of our complex and dynamic human-interactions and the technique of natural language processing (NLP) is hence built on human linguistic activities. Bidirectional Encoder Representations from Transformers (BERT) has recently gai

Externí odkaz: http://arxiv.org/abs/2106.03181

Zobrazit plný text záznamu

Report

Hierarchical Multitask Learning with Dependency Parsing for Japanese Semantic Role Labeling Improves Performance of Argument Identification

Autor: Nakamura, Tomohiro, Miyashita, Tomoya, Ohara, Soh

With the advent of FrameNet and PropBank, many semantic role labeling (SRL) systems have been proposed in English. Although research on Japanese predicate argument structure analysis (PASA) has been conducted, most studies focused on surface cases. T

Externí odkaz: http://arxiv.org/abs/2101.06071

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání