Analysing Rhetorical Structure as a Key Feature of Summary Coherence

Šnajder, Jan; Sladoljev-Agejev, Tamara; Vehovec, Svjetlana Kolić

doi:10.18653/v1/w19-4405

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Fine-grained and comprehensive evaluation of student texts, especially longer essays, remains a challenging task. Several studies we reviewed use elaborate systems to evaluate a single aspect of essays, such as discourse structure ( Šnajder et al, 2019; and organisation . This points to the difficulty of developing a holistic model that provides detailed evaluation from multiple relevant perspectives.…”

Section: Discussionmentioning

confidence: 99%

A Survey of Current Machine Learning Approaches to Student Free-Text Evaluation for Intelligent Tutoring

Bai

Stede

2022

Int J Artif Intell Educ

View full text Add to dashboard Cite

Recent years have seen increased interests in applying the latest technological innovations, including artificial intelligence (AI) and machine learning (ML), to the field of education. One of the main areas of interest to researchers is the use of ML to assist teachers in assessing students’ work on the one hand and to promote effective self-tutoring on the other hand. In this paper, we present a survey of the latest ML approaches to the automated evaluation of students’ natural language free-text, including both short answers to questions and full essays. Existing systematic literature reviews on the subject often emphasise an exhaustive and methodical study selection process and do not provide much detail on individual studies or a technical background to the task. In contrast, we present an accessible survey of the current state-of-the-art in student free-text evaluation and target a wider audience that is not necessarily familiar with the task or with ML-based text analysis in natural language processing (NLP). We motivate and contextualise the task from an application perspective, illustrate popular feature-based and neural model architectures and present a selection of the latest work in the area. We also remark on trends and challenges in the field.

show abstract

Section: Discussionmentioning

confidence: 99%

A Survey of Current Machine Learning Approaches to Student Free-Text Evaluation for Intelligent Tutoring

Bai

Stede

2022

Int J Artif Intell Educ

View full text Add to dashboard Cite

show abstract

“…The minimum consistency of those aspects shows that the respective verdicts have minimum significant improvement over the baseline of averaged expert standard. Snajder et al (2019) state that a model that uses rhetorical structure scores as features yields a statistically significant improvement over the baseline of averaged expert-assigned scores.…”

Section: Findings and Discussionmentioning

confidence: 99%

The construction of victim of defamation in court's written verdict

Zifana

Lukmana

Sudana

2022

Indonesian J. Appl. Linguist.

View full text Add to dashboard Cite

Most countries in the world consider defamation case as a civil domain. Indonesia is still one of the few countries in the world, which classify defamation case as a criminal act. The issue of defamation in Indonesia becomes more complex since there are various regulations governing defamation. Initially, the Indonesian Criminal Code (KUHP) is the only law that regulates the act of defamation. The establishment of the Law Number 11 of 2008 concerning Electronic Information Transactions (the EIT Law) has resulted in a complex situation since it also covers the act of defamation. After the EIT Law came into force in 2009, up until 2014, there have been 71 people charged in court for alleged defamation. Current research is a linguistic study in the context of law to discuss the construction of victims in copies of court decision. The data of the study were taken from two copy-texts of court decisions, which were the result of defamation cases in 2014 and 2015. Data are in the form of texts explaining the position of victims in relation to one of the grounds for judge’s decision. As explained by Coulthard Johnson (2007), Forensic Linguistics includes several levels such as acoustic phonetics, discourse analysis, and semantics. On this basis, data analysis in this study uses a critical discourse analysis (CDA) framework by Fairclough (1997) used with the consideration that the framework features dialectical-relational approaches which can map the patterns of social relations to explain the construction of a party in a discourse. Data interpretation and final conclusions of this study reveal the reproductions of logic of certain parties in a copy of criminal justice decisions; marginalization of victims to balance justice retributively and restoratively; and the establishment of role and position of victims in defamation discourses by ignoring institutional aspects and powerlessness. Thus, it appears that victims are not the center of discourse in the text copies of court decisions. Besides, the victim is the most important part of the defamation case considering that the case was classified as a criminal complaint.

show abstract

Effects of searching for rhetorical relations on university-level text comprehension in L2

Sladoljev-Agejev

Kolić‐Vehovec

2021

Read Writ

View full text Add to dashboard Cite

Analysing Rhetorical Structure as a Key Feature of Summary Coherence

Cited by 3 publications

References 19 publications

A Survey of Current Machine Learning Approaches to Student Free-Text Evaluation for Intelligent Tutoring

A Survey of Current Machine Learning Approaches to Student Free-Text Evaluation for Intelligent Tutoring

The construction of victim of defamation in court's written verdict

Effects of searching for rhetorical relations on university-level text comprehension in L2

Contact Info

Product

Resources

About