Modeling Inter-Speaker Relationship in XLNet for Contextual Spoken Language Understanding

TL;DR

This paper introduces two methods to enhance spoken language understanding by modeling inter-speaker relationships, improving accuracy on benchmark datasets when integrated with XLNet.

Contribution

The paper presents novel methods tailored for XLNet to better capture dialogue history and inter-speaker relationships in multi-turn SLU tasks.

Findings

Achieved higher accuracy than state-of-the-art models on benchmark datasets.

Proposed methods effectively improve SLU accuracy by identifying important dialogue history.

Methods help alleviate ambiguity in understanding current utterances.

Abstract

We propose two methods to capture relevant history information in a multi-turn dialogue by modeling inter-speaker relationship for spoken language understanding (SLU). Our methods are tailored for and therefore compatible with XLNet, which is a state-of-the-art pretrained model, so we verified our models built on the top of XLNet. In our experiments, all models achieved higher accuracy than state-of-the-art contextual SLU models on two benchmark datasets. Analysis on the results demonstrated that the proposed methods are effective to improve SLU accuracy of XLNet. These methods to identify important dialogue history will be useful to alleviate ambiguity in SLU of the current utterance.