Using Rhetorical Structure Theory and Entity Grids to Automatically Evaluate Local Coherence in Texts

Dias, Márcio de Souza; Feltrim, Valéria Delisandra; Pardo, Thiago Alexandre Salgueiro

doi:10.1007/978-3-319-09761-9_26

Cited by 6 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given this difference, researchers tend to agree that restrictive and nonrestrictive relative clauses are distinguished by their connectedness with the relative head at an information level. Accordingly, non-restrictive relatives are often described as being more IT DEPENDS: OPTIONALITY IN THE PRODUCTION OF FILLER-GAP DEPENDENCIES 13 independent from the relative head as compared to restrictive ones, and as exhibiting the status of a separate segment or information unit (Ariel, 1999, Bache & Jakobsen, 1980Depraetere, 1995;Mann & Thompson, 1988; for reviews see Ariel, 1999). Example (8) demonstrates a restrictive use of a relative clause and (9) demonstrates a non-restrictive use of a similar relative clause.…”

Section: Experiments 1: Restrictiveness and Passivization In Englishmentioning

confidence: 99%

It depends: Optionality in the production of filler-gap dependencies

Fadlon

Morgan

Meltzer‐Asscher

et al. 2019

Journal of Memory and Language

View full text Add to dashboard Cite

This study investigates the language production mechanisms underlying the creation of filler-gap dependencies (e.g., relative clauses: This is the boy that the girl from Norway saw_ yesterday), which require speakers to establish an argument-predicate relationship between a phrase, the 'filler', (the boy) and a further embedded predicate (saw). We show that filler-gap dependency production involves the retention of a representation of the filler until the relevant embedded position. We then report three elicitation experiments examining how English and Hebrew speakers manage and moderate filler retention demands via production choices. In Experiments 1 (English) and 2 (Hebrew), speakers produced restrictive relative clauses and non-restrictive relative clauses with the latter predicted to impede filler retention. In Experiment 3 (Hebrew), speakers produced relative clauses with and without intervening material creating interference for filler retention. We found that English speakers use passivization to moderate filler-retention demands via the creation of shorter dependencies. In Hebrew, impeded filler retention resulted in increased rate of grammatical resumption. We conclude that the production of filler-gap dependencies invokes cognitive strategies that manage the memory burdens that they impose

show abstract

Section: Experiments 1: Restrictiveness and Passivization In Englishmentioning

confidence: 99%

It depends: Optionality in the production of filler-gap dependencies

Fadlon

Morgan

Meltzer‐Asscher

et al. 2019

Journal of Memory and Language

View full text Add to dashboard Cite

show abstract

“…The proposed method calculates the local coherence of the summary using the probability distribution of the entity's transitions. Many other researches like [13] and [14], explored the entity grid model to evaluate local coherence. In addition, [15] dealt with the assessment of grammaticality and coherence in the summary.…”

Section: Linguistic Quality Evaluationmentioning

confidence: 99%

Mix Multiple Features to Evaluate the Content and the Linguistic Quality of Text Summaries

Ellouze

Jaoua

Belguith

2017

CIT

View full text Add to dashboard Cite

In this article, we propose a method of text summary's content and linguistic quality evaluation that is based on a machine learning approach. This method operates by combining multiple features to build predictive models that evaluate the content and the linguistic quality of new summaries (unseen) constructed from the same source documents as the summaries used in the training and the validation of models. To obtain the best model, many single and ensemble learning classifiers are tested. Using the constructed models, we have achieved a good performance in predicting the content and the linguistic quality scores. In order to evaluate the summarization systems, we calculated the system score as the average of the score of summaries that are built from the same system. Then, we evaluated the correlation of the system score with the manual system score. The obtained correlation indicates that the system score outperforms the baseline scores.

show abstract

Towards an Arabic Text Summaries Evaluation Based on AraBERT Model

Ellouze

Jaoua

2022

Research Challenges in Information Science

View full text Add to dashboard Cite

Using Rhetorical Structure Theory and Entity Grids to Automatically Evaluate Local Coherence in Texts

Cited by 6 publications

References 14 publications

It depends: Optionality in the production of filler-gap dependencies

It depends: Optionality in the production of filler-gap dependencies

Mix Multiple Features to Evaluate the Content and the Linguistic Quality of Text Summaries

Towards an Arabic Text Summaries Evaluation Based on AraBERT Model

Contact Info

Product

Resources

About