DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection

Gessler, Luke; Behzad, Shabnam; Liu, Yang Janet; Peng, Siyao; Zhu, Yilun; Zeldes, Amir

doi:10.18653/v1/2021.disrpt-1.6

Cited by 12 publications

(16 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adapted the discourse parser DisCoDisCo [17] to the clause segmentation task and conducted an ablation study on different features, e.g., lemma, syntactic dependency, parts-of-speech, and static word embedding fastText, to explore which contributed more to the performances. The experimental results of the clause segmentation task are reported in Table 10, as well as the performances of previous works on the discourse segmentation task for comparison.…”

Section: Results Of Clause Segmentationmentioning

confidence: 99%

“…The RST-parsing task generally requires breaking the text into EDUs (i.e., the discourse segmentation task) and linking the EDUs into a DT (i.e., the discourse parsing task). For discourse segmentation, Gessler et al [17] proposed a Transformer-based neural classifier that enhances contextualized word embeddings with hand-crafted features and achieved the current state-of-the-art performance in the DISRPT 2021 Shared Task on Discourse Unit Segmentation (https://sites.google.com/georgetown.edu/disrpt2021?pli=1, accessed on 1 April 2023). For discourse parsing, Kobayashi et al [18] explored a strong baseline by integrating previous simple parsing strategies, top-down and bottom-up, with various Transformer-based pretrained language models (PLMs).…”

Section: Rst Parsingmentioning

confidence: 99%

“…As discussed in Section 2.1, the HCA and RST parsing tasks aim to extract the clause/EDU hierarchy from texts. Thus, the evaluation metrics of the discourse segmentation [17] and discourse parsing [18] subtasks in RST parsing were adopted as the IAA metrics in evaluating the annotation quality of the HCA corpus:…”

Section: Quality Assurancementioning

confidence: 99%

“…Note that y i is binary, i.e., y i = 1 if x i is the head word token for a clause, and otherwise, y i = 0. Therefore, we encountered the clause segmentation task with a sequence-tagging model, DisCoDisCo [17], used in the discourse segmentation task: embed the input sentence; encode with a single Bi-LSTM; decode with a linear projection layer; indicate the first token of each clause in the output tag sequence.…”

Section: Clause Segmentationmentioning

confidence: 99%

“…Inspired by the similarities among the HCA tree, AMR graph, and SDG, we annotated the first HCA corpus with the guidance in previous works of crowdsourcing annotation [15,16]. Furthermore, we adapted the state-of-the-art models [17,18] of the discourse segmentation and parsing tasks for training the baseline models to generate HCA annotations automatically.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Hierarchical Clause Annotation: Building a Clause-Level Corpus for Semantic Parsing with Complex Sentences

Fan,

Li,

Sataer

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Most natural-language-processing (NLP) tasks suffer performance degradation when encountering long complex sentences, such as semantic parsing, syntactic parsing, machine translation, and text summarization. Previous works addressed the issue with the intuition of decomposing complex sentences and linking simple ones, such as rhetorical-structure-theory (RST)-style discourse parsing, split-and-rephrase (SPRP), text simplification (TS), simple sentence decomposition (SSD), etc. However, these works are not applicable for semantic parsing such as abstract meaning representation (AMR) parsing and semantic dependency parsing due to misalignments with semantic relations and unavailabilities to preserve the original semantics. Following the same intuition and avoiding the deficiencies of previous works, we propose a novel framework, hierarchical clause annotation (HCA), for capturing clausal structures of complex sentences, based on the linguistic research of clause hierarchy. With the HCA framework, we annotated a large HCA corpus to explore the potentialities of integrating HCA structural features into semantic parsing with complex sentences. Moreover, we decomposed HCA into two subtasks, i.e., clause segmentation and clause parsing, and provide neural baseline models for more-silver annotations. In evaluating the proposed models on our manually annotated HCA dataset, the performances of clause segmentation and parsing resulted in 91.3% F1-scores and 88.5% Parseval scores, respectively. Due to the same model architectures employed, the performance differences of the clause/discourse segmentation and parsing subtasks was reflected in our HCA corpus and compared discourse corpora, where our sentences contained more segment units and fewer interrelations than those in the compared corpora.

show abstract

Section: Results Of Clause Segmentationmentioning

confidence: 99%

Section: Rst Parsingmentioning

confidence: 99%

Section: Quality Assurancementioning

confidence: 99%

Section: Clause Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Hierarchical Clause Annotation: Building a Clause-Level Corpus for Semantic Parsing with Complex Sentences

Fan,

Li,

Sataer

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

A BERT-Based Approach for Multilingual Discourse Connective Detection

Muermans

Kosseim

2022

Natural Language Processing and Information Systems

View full text Add to dashboard Cite

A survey on narrative extraction from textual data

et al. 2023

View full text Add to dashboard Cite

Narratives are present in many forms of human expression and can be understood as a fundamental way of communication between people. Computational understanding of the underlying story of a narrative, however, may be a rather complex task for both linguists and computational linguistics. Such task can be approached using natural language processing techniques to automatically extract narratives from texts. In this paper, we present an in depth survey of narrative extraction from text, providing a establishing a basis/framework for the study roadmap to the study of this area as a whole as a means to consolidate a view on this line of research. We aim to fulfill the current gap by identifying important research efforts at the crossroad between linguists and computer scientists. In particular, we highlight the importance and complexity of the annotation process, as a crucial step for the training stage. Next, we detail methods and approaches regarding the identification and extraction of narrative components, their linkage and understanding of likely inherent relationships, before detailing formal narrative representation structures as an intermediate step for visualization and data exploration purposes. We then move into the narrative evaluation task aspects, and conclude this survey by highlighting important open issues under the domain of narratives extraction from texts that are yet to be explored.

show abstract

DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection

Cited by 12 publications

References 48 publications

Hierarchical Clause Annotation: Building a Clause-Level Corpus for Semantic Parsing with Complex Sentences

Hierarchical Clause Annotation: Building a Clause-Level Corpus for Semantic Parsing with Complex Sentences

A BERT-Based Approach for Multilingual Discourse Connective Detection

A survey on narrative extraction from textual data

Contact Info

Product

Resources

About