On Text Tiling for Documents: A Neural-Network Approach
2021
Segmenting documents or conversation threads into semantically coherent segments have been one of the challenging tasks in natural language processing. In this work, we introduce three new text segmentation models that employ BERT for post-training. Extensive experiments are conducted based on benchmark datasets to demonstrate that our BERT-based models show significant improvements over the state-of-the-art text segmentation algorithms.
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
16
References
0
Citations
NaN
KQI