A Study on Dialog Act Recognition using Character-Level Tokenization

TL;DR

This paper investigates character-level tokenization for dialog act recognition, demonstrating that it outperforms word-level methods and that combining both yields the best results.

Contribution

It introduces character-level tokenization and context window exploration for dialog act recognition, showing improved performance over traditional word-level approaches.

Findings

Character-level tokenization improves accuracy.

Combining character and word-level tokenization yields best results.

Character-level approach captures sub-word information like affixes.

Abstract

Dialog act recognition is an important step for dialog systems since it reveals the intention behind the uttered words. Most approaches on the task use word-level tokenization. In contrast, this paper explores the use of character-level tokenization. This is relevant since there is information at the sub-word level that is related to the function of the words and, thus, their intention. We also explore the use of different context windows around each token, which are able to capture important elements, such as affixes. Furthermore, we assess the importance of punctuation and capitalization. We performed experiments on both the Switchboard Dialog Act Corpus and the DIHANA Corpus. In both cases, the experiments not only show that character-level tokenization leads to better performance than the typical word-level approaches, but also that both approaches are able to capture complementary information. Thus, the best results are achieved by combining tokenization at both levels.