Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Improving Context Modeling in Neural Topic Segmentation (2010.03138v1)

Published 7 Oct 2020 in cs.CL and cs.AI

Abstract: Topic segmentation is critical in key NLP tasks and recent works favor highly effective neural supervised approaches. However, current neural solutions are arguably limited in how they model context. In this paper, we enhance a segmenter based on a hierarchical attention BiLSTM network to better model context, by adding a coherence-related auxiliary task and restricted self-attention. Our optimized segmenter outperforms SOTA approaches when trained and tested on three datasets. We also the robustness of our proposed model in domain transfer setting by training a model on a large-scale dataset and testing it on four challenging real-world benchmarks. Furthermore, we apply our proposed strategy to two other languages (German and Chinese), and show its effectiveness in multilingual scenarios.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Linzi Xing (14 papers)
  2. Brad Hackinen (2 papers)
  3. Giuseppe Carenini (52 papers)
  4. Francesco Trebbi (1 paper)
Citations (29)

Summary

We haven't generated a summary for this paper yet.