Enhancing Discourse Dependency Parsing with Sentence Dependency Parsing: A Unified Generative Method Based on Code Representation

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.

Similar Papers

Overview

Challenge

Approach

Outcome

Discourse Representation Parsing for Sentences and Documents (P19-1)

Copied to clipboard

Jiangming Liu, Shay B. Cohen, Mirella Lapata

Semantic Text Processing

Challenge:	Experimental results show that our model outperforms competitive baselines by a wide margin.
Approach:	They propose a neural model which parses discourse structures of arbitrary length and granularity.
Outcome:	The proposed model outperforms baseline models on sentence- and document-level benchmarks.

Dependency Parsing via Sequence Generation (2022.findings-emnlp)

Copied to clipboard

Boda Lin, Zijun Yao, Jiaxin Shi, Shulin Cao, Binghao Tang, Si Li, Yong Luo, Juanzi Li, Lei Hou

Syntactic Text Processing

Challenge:	Existing methods for dependency parsing are transition-based, graph-based and sequence-to-sequence method.
Approach:	They propose to achieve dependency parsing (DP) via Sequence Generation (SG) by utilizing only the pre-trained language model without any auxiliary structures.
Outcome:	The proposed method performs well on DP benchmarks including PTB, UD2.2, SDP15 and SemEval16.

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

Copied to clipboard

Liwen Zhang, Ge Wang, Wenjuan Han, Kewei Tu

Responsible & Trustworthy NLP

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 Semantic Dependency Parsing Using CRF Autoencoders (2020.acl-main)

Copied to clipboard

Zixia Jia, Youmi Ma, Jiong Cai, Kewei Tu

Language Models

Challenge:	Semantic dependency parsing allows words to have multiple dependency heads, resulting in graph-structured representations.
Approach:	They propose an approach to semi-supervised learning of semantic dependency parsers based on the CRF autoencoder framework.
Outcome:	The proposed model improves over the baseline model and is arc-factored.

Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation (2022.tacl-1)

Copied to clipboard

Noriki Nishida, Yuji Matsumoto

Semantic Text Processing

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.

Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies (2020.emnlp-main)

Copied to clipboard

Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab

Multilinguality

Challenge:	Existing methods for developing broad-coverage semantic dependency parsers for languages without semantically annotated data are limited to English, Czech and Chinese.
Approach:	They propose a multitask learning framework coupled with annotation projection to build broad-coverage semantic dependency parsers for languages without annotated resources.
Outcome:	The proposed model improves labeled F1 score on multitask tasks from English to Czech compared to baseline models .

Enhancing Unsupervised Generative Dependency Parser with Contextual Information (P19-1)

Copied to clipboard

Wenjuan Han, Yong Jiang, Kewei Tu

Responsible & Trustworthy NLP

Challenge:	Existing approaches to unsupervised dependency parsing are based on probabilistic generative models that learn the joint distribution of the given sentence and its parse.
Approach:	They propose a probabilistic model that generates a sentence and its parse from a latent representation, which encodes global contextual information of the generated sentence.
Outcome:	The proposed model achieves competitive accuracy compared with state-of-the-art models.

Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations (2022.naacl-main)

Copied to clipboard

Daniela Brook Weiss, Paul Roit, Ori Ernst, Ido Dagan

Challenge:	Existing datasets for sentence fusion tasks are limited in size and scope . despite recent advances, cross-document tasks such as multi-document summarization have not progressed with the same pace.
Approach:	They propose to extend a sentence fusion dataset by almost four times its original size . they relabel the dataset and employ more data sources to improve model performance .
Outcome:	The proposed dataset triples the size of an earlier dataset and improves performance . it also includes more complex training instances better reflecting those found in "the wild"

A Language Model-based Generative Classifier for Sentence-level Discourse Parsing (2021.emnlp-main)

Copied to clipboard

Ying Zhang, Hidetaka Kamigaito, Manabu Okumura

Semantic Text Processing

Challenge:	Existing methods to consider textual coherence are limited in labeled data.
Approach:	They propose a language model-based generative classifier that uses labels as input and embeds labels into their representations.
Outcome:	The proposed classifier achieves state-of-the-art in discourse segmentation and relation F1 scores with gold boundaries and automatically segmented boundaries.

Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification (2021.eacl-main)

Copied to clipboard

Yi Zhu, Ehsan Shareghi, Yingzhen Li, Roi Reichart, Anna Korhonen

Information Extraction & Text Mining

Challenge:	Semi-supervised learning and multilingual pretraining have been shown to be effective for task-specific labelled data shortages.
Approach:	They propose to combine semi-supervised deep generative models and multi-lingual pretraining to form a pipeline for document classification task.
Outcome:	The proposed method outperforms state-of-the-art models in low-resource settings across several languages and outperformed existing models in English.