14 papers with code • 0 benchmarks • 4 datasets
These leaderboards are used to track progress in Discourse Segmentation
Most implemented papers
Two-pass Discourse Segmentation with Pairing and Global Features
Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token.
Cross-lingual and cross-domain discourse segmentation of entire documents
Discourse segmentation is a crucial step in building end-to-end discourse parsers.
Does syntax help discourse segmentation? Not so much
Discourse segmentation is the first step in building discourse parsers.
Toward Fast and Accurate Neural Discourse Segmentation
Discourse segmentation, which segments texts into Elementary Discourse Units, is a fundamental step in discourse analysis.
From News to Medical: Cross-domain Discourse Segmentation
The first step in discourse analysis involves dividing a text into segments.
GumDrop at the DISRPT2019 Shared Task: A Model Stacking Approach to Discourse Unit Segmentation and Connective Detection
In this paper we present GumDrop, Georgetown University's entry at the DISRPT 2019 Shared Task on automatic discourse unit segmentation and connective detection.
Text Segmentation by Cross Segment Attention
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.
Joint Learning of Syntactic Features Helps Discourse Segmentation
This paper describes an accurate framework for carrying out multi-lingual discourse segmentation with BERT (Devlin et al., 2019).
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
Based on the learned EDU and entailment representations, we either reply to the user our final decision "yes/no/irrelevant" of the initial question, or generate a follow-up question to inquiry more information.
Open-Retrieval Conversational Machine Reading
On our created OR-ShARC dataset, MUDERN achieves the state-of-the-art performance, outperforming existing single-passage conversational machine reading models as well as a new multi-passage conversational machine reading baseline by a large margin.