Michal Lukasik, Boris Dadachev, Kishore Papineni, ¸alo Gonc, Simões
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream tasks such as information retrieval or text summarization. In this work, we propose three transformer-based architectures and provide comprehensive comparisons with previously proposed approaches on three standard datasets. We establish a new state-of-the-art, reducing in particular the error rates by a large margin in all cases. We further analyze model sizes and find that we can build models with many fewer parameters while keeping good performance, thus facilitating real-world applications.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.14535")
get_code_for_paper("2004.14535")
have("2004.14535")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2004.14535.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2004.14535)
Connect an agent — have() is free.