Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence

Kelvin Lo, Yuan Jin, Weicong Tan, Ming Liu, Lan Du, Wray Buntine


Abstract
This paper proposes a transformer over transformer framework, called Transformerˆ2, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level transformer-based segmentation model based on the sentence embeddings. The bottom-level component transfers the pre-trained knowledge learnt from large external corpora under both single and pair-wise supervised NLP tasks to model the sentence embeddings for the documents. Given the sentence embeddings, the upper-level transformer is trained to recover the segmentation boundaries as well as the topic labels of each sentence. Equipped with a multi-task loss and the pre-trained knowledge, Transformerˆ2 can better capture the semantic coherence within the same segments. Our experiments show that (1) Transformerˆ2$manages to surpass state-of-the-art text segmentation models in terms of a commonly-used semantic coherence measure; (2) in most cases, both single and pair-wise pre-trained knowledge contribute to the model performance; (3) bottom-level sentence encoders pre-trained on specific languages yield better performance than those pre-trained on specific domains.
Anthology ID:
2021.findings-emnlp.283
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3334–3340
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.283
DOI:
10.18653/v1/2021.findings-emnlp.283
Bibkey:
Cite (ACL):
Kelvin Lo, Yuan Jin, Weicong Tan, Ming Liu, Lan Du, and Wray Buntine. 2021. Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3334–3340, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence (Lo et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.283.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.283.mp4
Data
WikiSection