Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling

Hai Yu, Chong Deng, Qinglin Zhang, Jiaqing Liu, Qian Chen, Wen Wang

Submission Type: Regular Long Paper

Submission Track: Discourse and Pragmatics

Submission Track 2: Machine Learning for NLP

Keywords: topic segmentation, text coherence, semantic similarity, sentence structure, contrastive learning

Abstract: Topic segmentation is critical for obtaining structured documents and improving down- stream tasks such as information retrieval. Due to its ability of automatically exploring clues of topic shift from abundant labeled data, recent supervised neural models have greatly promoted the development of long document topic segmentation, but leaving the deeper relationship between coherence and topic segmentation underexplored. Therefore, this paper enhances the ability of supervised models to capture coherence from both logical structure and semantic similarity perspectives to further improve the topic segmentation performance, proposing Topic-aware Sentence Structure Prediction (TSSP) and Contrastive Semantic Similarity Learning (CSSL). Specifically, the TSSP task is proposed to force the model to comprehend structural information by learning the original relations between adjacent sentences in a disarrayed document, which is constructed by jointly disrupting the original document at topic and sentence levels. Moreover, we utilize inter- and intra-topic information to construct contrastive samples and design the CSSL objective to ensure that the sentences representations in the same topic have higher similarity, while those in different topics are less similar. Extensive experiments show that the Longformer with our approach significantly outperforms old state-of-the-art (SOTA) methods. Our approach improve $F_{1}$ of old SOTA by 3.42 (73.74 → 77.16) and reduces $P_{k}$ by 1.11 points (15.0 → 13.89) on WIKI-727K and achieves an average relative reduction of 4.3\% on $P_{k}$ on WikiSection. The average relative $P_{k}$ drop of 8.38\% on two out-of-domain datasets also demonstrates the robustness of our approach.

Submission Number: 927