Towards Understanding Egyptian Arabic Dialogues

TL;DR

This paper presents a machine learning approach for classifying dialogue acts in Egyptian Arabic spontaneous dialogues and instant messages, achieving promising results without relying on specialized lexicons or rules.

Contribution

It introduces a novel ML-based method for Egyptian dialect dialogue act classification without using lexicons, evaluated on a newly created multi-genre corpus.

Findings

Achieved an F1 score of 70.36% across domains

Developed a manually annotated Egyptian dialect dialogue corpus

Demonstrated effectiveness of ML approach without lexicons

Abstract

Labelling of user's utterances to understanding his attends which called Dialogue Act (DA) classification, it is considered the key player for dialogue language understanding layer in automatic dialogue systems. In this paper, we proposed a novel approach to user's utterances labeling for Egyptian spontaneous dialogues and Instant Messages using Machine Learning (ML) approach without relying on any special lexicons, cues, or rules. Due to the lack of Egyptian dialect dialogue corpus, the system evaluated by multi-genre corpus includes 4725 utterances for three domains, which are collected and annotated manually from Egyptian call-centers. The system achieves F1 scores of 70. 36% overall domains.