Cue Phrase Classification Using Machine Learning

TL;DR

This paper demonstrates that machine learning techniques effectively classify cue phrases as discourse or sentential, improving accuracy and providing new linguistic insights, which enhances NLP tasks like anaphora resolution.

Contribution

The study introduces machine learning models for cue phrase classification, outperforming manual models and enabling scalable, flexible, and insightful analysis of linguistic features.

Findings

Machine learning models achieve higher accuracy than manual models.

Automated models reveal new linguistic insights.

The approach is scalable and adaptable for different feature sets.

Abstract

Cue phrases may be used in a discourse sense to explicitly signal discourse structure, but also in a sentential sense to convey semantic rather than structural information. Correctly classifying cue phrases as discourse or sentential is critical in natural language processing systems that exploit discourse structure, e.g., for performing tasks such as anaphora resolution and plan recognition. This paper explores the use of machine learning for classifying cue phrases as discourse or sentential. Two machine learning programs (Cgrendel and C4.5) are used to induce classification models from sets of pre-classified cue phrases and their features in text and speech. Machine learning is shown to be an effective technique for not only automating the generation of classification models, but also for improving upon previous results. When compared to manually derived classification models already in the literature, the learned models often perform with higher accuracy and contain new linguistic insights into the data. In addition, the ability to automatically construct classification models makes it easier to comparatively analyze the utility of alternative feature representations of the data. Finally, the ease of retraining makes the learning approach more scalable and flexible than manual methods.