Unsupervised Learning of Discourse Structures using a Tree Autoencoder
원문 초록
Discourse information, as postulated by popular discourse theories, such as RST and PDTB, has been shown to improve an increasing number of downstream NLP tasks, showing positive effects and synergies of discourse with important real-world applications. While methods for incorporating discourse become more and more sophisticated, the growing need for robust and general discourse structures has not been sufficiently met by current discourse parsers, usually trained on small scale datasets in a strictly limited number of domains. This makes the prediction for arbitrary tasks noisy and unreliable. The overall resulting lack of high-quality, high-quantity discourse trees poses a severe limitation to further progress. In order the alleviate this shortcoming, we propose a new strategy to generate tree structures in a task-agnostic, unsupervised fashion by extending a latent tree induction framework with an auto-encoding objective. The proposed approach can be applied to any tree-structured objective, such as syntactic parsing, discourse parsing and others. However, due to the especially difficult annotation process to generate discourse trees, we initially develop a method to generate larger and more diverse discourse treebanks. In this paper we are inferring general tree structures of natural text in multiple domains, showing promising results on a diverse set of tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations
GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains
Bilingual Rhetorical Structure Parsing with Large Parallel Annotations
Unsupervised Mutual Learning of Dialogue Discourse Parsing and Topic Segmentation
Can we obtain significant success in RST discourse parsing by using Large Language Models?
Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.