ESURF, a simple random forest with lexical and character n-gram features, reaches state-of-the-art EDU segmentation on RST-DT and modestly improves RST parsing.
Toward Fast and Accurate Neural Discourse Segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Discourse segmentation, which segments texts into Elementary Discourse Units, is a fundamental step in discourse analysis. Previous discourse segmenters rely on complicated hand-crafted features and are not practical in actual use. In this paper, we propose an end-to-end neural segmenter based on BiLSTM-CRF framework. To improve its accuracy, we address the problem of data insufficiency by transferring a word representation model that is trained on a large corpus. We also propose a restricted self-attention mechanism in order to capture useful information within a neighborhood. Experiments on the RST-DT corpus show that our model is significantly faster than previous methods, while achieving new state-of-the-art performance.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ESURF: Simple and Effective EDU Segmentation
ESURF, a simple random forest with lexical and character n-gram features, reaches state-of-the-art EDU segmentation on RST-DT and modestly improves RST parsing.