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.

Similar Papers

Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing (2021.acl-long)

Copied to clipboard

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.
Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations (2020.coling-main)

Copied to clipboard

Challenge: Recent advances in deep neural network models have improved parsing performance on in-domain texts . however, the problem is to improve performance on out-of-domain text data when there is only a small-scale out-domain labeled data.
Approach: They propose to use adversarial learning and fine-tuning BERT to improve contextualized word representations on out-of-domain texts.
Outcome: The proposed models achieve consistent improvement and fine-tune BERT processes boost parsing accuracy by a large margin.
A Complete Shift-Reduce Chinese Discourse Parser with Robust Dynamic Oracle (2020.acl-main)

Copied to clipboard

Challenge: Existing work on hierarchical discourse parsing in English is based on the RST-style one.
Approach: They propose a Chinese discourse parser that integrates pre-trained text encoder and employs novel training strategies to improve rhetorical relation recognition.
Outcome: The proposed system achieves state-of-the-art performance in Chinese discourse parsing.
The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error (2022.findings-acl)

Copied to clipboard

Challenge: Discourse analysis is very low on texts outside of the training distribution’s coverage, diminishing the practical utility of existing models.
Approach: They propose to use a distribution shift statistic to estimate the error-gap of a discourse model and to use it to estimate it.
Outcome: The proposed model can be estimated via distribution shift but does not correlate with change in the observed error of a classifier (i.e. error-gap).
Discourse Parsing Enhanced by Discourse Dependence Perception (2022.aacl-main)

Copied to clipboard

Challenge: Top-down neural models still suffer from the top-down error propagation issue . previous studies gradually switch from feature-based machine learning methods to deep neural models .
Approach: They propose a top-down framework that learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders.
Outcome: The proposed framework learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders on a Chinese discourse corpus.
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.
A Deeper (Autoregressive) Approach to Non-Convergent Discourse Parsing (2023.emnlp-main)

Copied to clipboard

Challenge: Existing frameworks for dialogic discourse parsing are not suitable for contentious discussions . authors propose a model for non-convergent discourse paring that does not require label collocation .
Approach: They propose a multi-label scheme for contentious dialog parsing that uses multiple labels . they propose combining embeddings of the utterance, context and the labels through GRN layers .
Outcome: The proposed model achieves comparable results with SOTA without label collocation and without training a unique architecture/model for each label.
SciDTB: Discourse Dependency TreeBank for Scientific Abstracts (P18-2)

Copied to clipboard

Challenge: Discourse relations are annotated on scientific articles.
Approach: They propose a domain-specific discourse treebank annotated on scientific articles . they use dependency trees to represent discourse structure, which is flexible and simplified .
Outcome: The proposed treebank is a benchmark for evaluating discourse dependency parsers.
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.
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.

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