We develop a weak supervision approach to adapt, using minimal annotation, a state of the art discourse segmenter trained on written text to French conversation ...

A weak supervision approach to adapt, using minimal annotation, a state of the art discourse segmenter trained on written text to French conversation ...

This paper is shaped by the post structuralist ideas of governmentality and disciplinary power. It uses these ideas to trace the detail of a supervision ...

We develop a weak supervision approach to adapt, using minimal annotation, a state of the art discourse segmenter trained on written text to French conversation ...

We propose a complete probabilistic discriminative framework for performing sentence-level discourse analysis. Our framework comprises a discourse segmenter, ...

On-demand video platform giving you access to lectures from conferences worldwide.

Weakly supervised discourse segmentation for multiparty oral conversations. open-access-img. Details. Cite Export. Add to list.

Highlight: In this paper, we propose a novel three-stage learning framework based on weakly supervised learning which benefits from large scale ungrounded ...

Jun 26, 2024 · Weakly supervised discourse segmentation for multiparty oral conversations. In 2021 Conference on Empirical Methods in. Natural Language ...

This segmentation algorithm uses automatically induced decision rules to combine the different features. The embedded text-based algorithm builds on lexical ...