Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics
Prafulla Kumar Choubey, Ruihong Huang
Abstract
We present an actor-critic framework to induce subtopical structures in a news article for news discourse profiling. The model uses multiple critics that act according to known subtopic structures while the actor aims to outperform them. The content structures constitute sentences that represent latent subtopic boundaries. Then, we introduce a hierarchical neural network that uses the identified subtopic boundary sentences to model multi-level interaction between sentences, subtopics, and the document. Experimental results and analyses on the NewsDiscourse corpus show that the actor model learns to effectively segment a document into subtopics and improves the performance of the hierarchical model on the news discourse profiling task.
BibTeX
@inproceedings{choubey-huang-2021-profiling-news,
title = "{P}rofiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics",
author = "Choubey, Prafulla Kumar and
Huang, Ruihong",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.137/",
doi = "10.18653/v1/2021.findings-emnlp.137",
pages = "1594--1605"
}