Challenge: Discourse dependency parsing is a task that requires a large amount of training data, but there is little research on it.
Approach: They propose to adapt unsupervised syntactic dependency parsing methods for unsupervised discourse dependency parses using unlabeled training data.
Outcome: The proposed methods outperform existing methods in semi-supervised and supervised settings and outperformed existing methods.

Similar Papers

A Survey of Unsupervised Dependency Parsing (2020.coling-main)

Copied to clipboard

Challenge: Syntactic dependency parsing is an important task in natural language processing . unsupervised learning of dependency parses requires training sentences to be manually annotated with their correct parse trees.
Approach: They propose to survey existing approaches to unsupervised dependency parsing . they identify two major classes of approaches and discuss recent trends .
Outcome: The proposed methods can be used in semantic parsing, machine translation, relation extraction, and many other tasks.
Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation (2022.tacl-1)

Copied to clipboard

Challenge: Discourse parsing accuracy degrades significantly on out-of-domain text.
Approach: They propose to use bootstrapping methods to adapt modern discourse dependency parsers to out-of-domain text without additional human supervision.
Outcome: The proposed methods are significantly and consistently effective for unsupervised domain adaptation of discourse dependency parsing, but the low coverage of accurately predicted pseudo labels is a bottleneck for further improvement.
Semi-supervised Domain Adaptation for Dependency Parsing (P19-1)

Copied to clipboard

Challenge: Currently, most studies on cross-domain parsing focus on unsupervised domain adaptation . however, unsupervised approaches make limited progress due to the intrinsic difficulty of both domain adaptation and parse.
Approach: They propose a semi-supervised domain adaptation problem for Chinese dependency parsing by using newly-annotated large-scale domain-aware datasets.
Outcome: The proposed method is more effective than direct corpus concatenation and multi-task learning.
Unsupervised Cross-Lingual Adaptation of Dependency Parsers Using CRF Autoencoders (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing work on cross-lingual adaptation of dependency parsers without annotated target corpora focuses on discriminative source parser ignoring unannotated corporata .
Approach: They propose to use unsupervised discriminative parsers to adapt dependency parser to unannotated target corpora without a supervised generative parsing method.
Outcome: The proposed method significantly outperforms previous methods.
Enhancing Discourse Dependency Parsing with Sentence Dependency Parsing: A Unified Generative Method Based on Code Representation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing annotation resources for Discourse Dependency Parsing tasks are limited due to their complexity and annotation schema differences.
Approach: They propose a code-based unified dependency parsing method that uses code to model dependency parses under different annotation schemas.
Outcome: The proposed method improves on two Chinese DDP tasks.
Rule Augmented Unsupervised Constituency Parsing (2021.findings-acl)

Copied to clipboard

Challenge: Recent studies have shown that unsupervised parsing methods do not learn meaningful semantics (not even simple grammar)
Approach: They propose an approach that utilizes very generic linguistic knowledge of the language present in the form of syntactic grammar rules and is independent of the base system.
Outcome: The proposed model is independent of the base system and takes advantage of syntactic grammar rules.
Unsupervised Natural Language Parsing (Introductory Tutorial) (2021.eacl-tutorials)

Copied to clipboard

Challenge: Unsupervised parsing learns a syntactic parser from training sentences without parse tree annotations.
Approach: This tutorial will introduce what unsupervised parsing does and how it can be useful for and beyond syntactic parse.
Outcome: This paper will provide an overview of major approaches to unsupervised parsing and analyze their strengths and weaknesses.
Unsupervised Discourse Constituency Parsing Using Viterbi EM (2020.tacl-1)

Copied to clipboard

Challenge: Existing studies on unsupervised discourse parsing have shown that it is expensive, time-consuming, and sometimes highly ambiguous.
Approach: They propose an unsupervised parsing algorithm using Viterbi EM with a margin-based criterion and initialization methods for Viterbia training of discourse constituents based on prior knowledge of text structures.
Outcome: The proposed method outperforms fully supervised parsers in terms of performance and learning of discourse constituents.
Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for dependency parsing are often of the pseudo-annotation type, but they fail to consider the change of model structure for domain adaptation.
Approach: They propose a method that accomplishes unsupervised cross-domain dependency parsing without using labeled data.
Outcome: The proposed method achieves consistent performance improvement on CODT1 and CTB9 domains.
Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations (2022.coling-1)

Copied to clipboard

Challenge: Existing semantic parsers are based on deep learning, but rule-based approaches offer advantages . a drawback of neural semantic parses is that their output lacks explainability .
Approach: They propose a method that maps a syntactic dependency tree to a formal meaning representation using a series of graph transformations.
Outcome: The proposed method outperforms neural parsers in English, German, Italian and Dutch.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations