Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding

TL;DR

This paper introduces Profile-based Spoken Language Understanding (ProSLU), a new task that incorporates profile information to improve semantic understanding in complex, ambiguous utterances, supported by a large Chinese dataset.

Contribution

The paper defines the novel ProSLU task, creates a large-scale Chinese dataset with profile info, and proposes a multi-level knowledge adapter to enhance understanding beyond text alone.

Findings

Existing text-based SLU models fail on ambiguous utterances.

Profile information significantly improves intent detection and slot filling.

The proposed framework effectively fuses supporting information for better accuracy.

Abstract

Current researches on spoken language understanding (SLU) heavily are limited to a simple setting: the plain text-based SLU that takes the user utterance as input and generates its corresponding semantic frames (e.g., intent and slots). Unfortunately, such a simple setting may fail to work in complex real-world scenarios when an utterance is semantically ambiguous, which cannot be achieved by the text-based SLU models. In this paper, we first introduce a new and important task, Profile-based Spoken Language Understanding (ProSLU), which requires the model that not only relies on the plain text but also the supporting profile information to predict the correct intents and slots. To this end, we further introduce a large-scale human-annotated Chinese dataset with over 5K utterances and their corresponding supporting profile information (Knowledge Graph (KG), User Profile (UP), Context Awareness (CA)). In addition, we evaluate several state-of-the-art baseline models and explore a multi-level knowledge adapter to effectively incorporate profile information. Experimental results reveal that all existing text-based SLU models fail to work when the utterances are semantically ambiguous and our proposed framework can effectively fuse the supporting information for sentence-level intent detection and token-level slot filling. Finally, we summarize key challenges and provide new points for future directions, which hopes to facilitate the research.