Dialogue Term Extraction using Transfer Learning and Topological Data Analysis

TL;DR

This paper explores a data-driven approach to automatically extract domain, slot, and value terms from dialogues using features from word embeddings, language models, and topological data analysis, improving over previous methods.

Contribution

It introduces a novel combination of features, including topological data analysis, for term extraction in dialogue systems, demonstrating improved performance and diverse content discovery.

Findings

Outperforms previous embedding-only methods

Different features capture different content types

Applicable across different dialogue datasets

Abstract

Goal oriented dialogue systems were originally designed as a natural language interface to a fixed data-set of entities that users might inquire about, further described by domain, slots, and values. As we move towards adaptable dialogue systems where knowledge about domains, slots, and values may change, there is an increasing need to automatically extract these terms from raw dialogues or related non-dialogue data on a large scale. In this paper, we take an important step in this direction by exploring different features that can enable systems to discover realizations of domains, slots, and values in dialogues in a purely data-driven fashion. The features that we examine stem from word embeddings, language modelling features, as well as topological features of the word embedding space. To examine the utility of each feature set, we train a seed model based on the widely used MultiWOZ data-set. Then, we apply this model to a different corpus, the Schema-Guided Dialogue data-set. Our method outperforms the previously proposed approach that relies solely on word embeddings. We also demonstrate that each of the features is responsible for discovering different kinds of content. We believe our results warrant further research towards ontology induction, and continued harnessing of topological data analysis for dialogue and natural language processing research.