Improving Topic Segmentation by Injecting Discourse Dependencies
Abstract
Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sampled from Wikipedia. These models may, however, suffer from limited robustness and transferability caused by exploiting simple linguistic cues for prediction, but overlooking more important inter-sentential topical consistency. To address this issue, we present a discourse-aware neural topic segmentation model with the injection of above-sentence discourse dependency structures to encourage the model make topic boundary prediction based more on the topical consistency between sentences. Our empirical study on English evaluation datasets shows that injecting above-sentence discourse structures to a neural topic segmenter with our proposed strategy can substantially improve its performances on intra-domain and out-of-domain data, with little increase of model's complexity.
Cite
@article{arxiv.2209.08626,
title = {Improving Topic Segmentation by Injecting Discourse Dependencies},
author = {Linzi Xing and Patrick Huber and Giuseppe Carenini},
journal= {arXiv preprint arXiv:2209.08626},
year = {2022}
}
Comments
Accepted to the 3rd Workshop on Computational Approaches to Discourse (CODI-2022) at COLING 2022