Quantitative Aspects of PDTB-Style Discourse Relations across Languages

Sun, Kun; Zhang, Lili

doi:10.1080/09296174.2017.1390934

Cited by 6 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the data on the frequencies, we can calculate implicitness for each discourse relation, as shown in Table 2. Note that the annotations in the PDTB3.0 are different from the PDTB2.0 (Sun & Zhang, 2018). Our study is based on the PDTB3.0.…”

Section: Discussion and Concluding Remarksmentioning

confidence: 97%

Diachronic Changes of Frequencies in Discourse Connectives in English: Evidence from COHA

Sun¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recent studies claim that discourse connectives or discourse markers have risen in multiple languages. However, comprehensive empirical data evidence has seldom been used to support this idea. This study investigates the historical changes of frequencies of discourse connectives in English in the late two hundred years. We find that the frequencies of the majority of discourse connectives decreased markedly. Only a few types of discourse connectives showed an opposing trend in frequency changes. This result shows that the frequencies of discourse markers in English have not increased in late two centuries. We analyze the possible reasons for the decline. However, this result implies that English language users tend to use explicit discourse connectives less frequently, and this fining may pose a slight challenge to this current formulation of a rise of discourse connectives (markers).

show abstract

Section: Discussion and Concluding Remarksmentioning

confidence: 97%

Diachronic Changes of Frequencies in Discourse Connectives in English: Evidence from COHA

Sun¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most studies to date have investigated the meanings and functions of discourse connectives in various languages (Gonzalez, 2005;Zufferey & Degand, 2017), translations of connectives and relations between connective lexicons for different languages (e.g., Bourgonje et al, 2017;Hoek & Zufferey, 2015;Knott & Sanders, 1998), and annotations of multilingual parallel corpora (e.g., Cunha & Iruskieta, 2010;Zeyrek et al, 2020;Zufferey & Degand, 2017). Less is known about different relational distinctions and the effects of relational distributions on processing and acquisition in different languages (but see Köhne-Fuetterer et al, 2021;Mak et al, 2013;Sun & Zhang, 2018;Zufferey et al, 2018). Studying crosslinguistic differences can provide insight into the feasibility of a universal cognitive theory of coherence relations.…”

Section: Crosslinguistic Evidencementioning

confidence: 99%

Descriptively Adequate and Cognitively Plausible? Validating Distinctions between Types of Coherence Relations

Scholman¹,

Demberg²,

Sanders³

2022

discours

View full text Add to dashboard Cite

“…A few of articles on the IDRR performance comparison can be found [9,50,64,73,78,128]. Braud and Denis (2015) [9] presented a comparative framework for assessing the usefulness of various word representations in the IDRR task.…”

Section: Summary Of This Surveymentioning

confidence: 99%

A Survey of Implicit Discourse Relation Recognition

Wang¹,

Wang²

2022

Preprint

View full text Add to dashboard Cite

A discourse containing one or more sentences describes daily issues and events for people to communicate their thoughts and opinions. As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments. Although sometimes a connective exists in raw texts for conveying relations, it is more often the cases that no connective exists in between two text segments but some implicit relation does exist in between them. The task of implicit discourse relation recognition (IDRR) is to detect implicit relation and classify its sense between two text segments without a connective. Indeed, the IDRR task is important to diverse downstream natural language processing tasks, such as text summarization, machine translation and so on. This article provides a comprehensive and up-to-date survey for the IDRR task. We first summarize the task definition and data sources widely used in the field. We categorize the main solution approaches for the IDRR task from the viewpoint of its development history. In each solution category, we present and analyze the most representative methods, including their origins, ideas, strengths and weaknesses. We also present performance comparisons for those solutions experimented on a public corpus with standard data processing procedures. Finally, we discuss future research directions for discourse relation analysis.

show abstract

Quantitative Aspects of PDTB-Style Discourse Relations across Languages

Cited by 6 publications

References 44 publications

Diachronic Changes of Frequencies in Discourse Connectives in English: Evidence from COHA

Diachronic Changes of Frequencies in Discourse Connectives in English: Evidence from COHA

Descriptively Adequate and Cognitively Plausible? Validating Distinctions between Types of Coherence Relations

A Survey of Implicit Discourse Relation Recognition

Contact Info

Product

Resources

About