M
Marianna Apidianaki
Researcher at Université Paris-Saclay
Publications - 43
Citations - 1685
Marianna Apidianaki is an academic researcher from Université Paris-Saclay. The author has contributed to research in topics: SemEval & Computer science. The author has an hindex of 13, co-authored 34 publications receiving 1202 citations. Previous affiliations of Marianna Apidianaki include Dublin City University & Centre national de la recherche scientifique.
Papers
More filters
Proceedings ArticleDOI
SemEval-2016 task 5 : aspect based sentiment analysis
Maria Pontiki,Dimitris Galanis,Haris Papageorgiou,Ion Androutsopoulos,Suresh Manandhar,Mohammad AL-Smadi,Mahmoud Al-Ayyoub,Yanyan Zhao,Bing Qin,Orphée De Clercq,Veronique Hoste,Marianna Apidianaki,Xavier Tannier,Natalia V. Loukachevitch,Evgeniy V. Kotelnikov,Núria Bel,Salud María Jiménez-Zafra,Gülşen Eryiğit +17 more
TL;DR: This paper describes the SemEval 2016 shared task on Aspect Based Sentiment Analysis (ABSA), a continuation of the respective tasks of 2014 and 2015, which attracted 245 submissions from 29 teams and provided 19 training and 20 testing datasets.
Proceedings Article
Latent Semantic Word Sense Induction and Disambiguation
TL;DR: A unified model for the automatic induction of word senses from text, and the subsequent disambiguation of particular word instances using the automatically extracted sense inventory is presented.
Proceedings ArticleDOI
Data-Driven Semantic Analysis for Multilingual WSD and Lexical Selection in Translation
TL;DR: An unsupervised WSD method and a lexical selection method that exploit the results of a data-driven sense induction method and it is shown how this automatically acquired information can be exploited for a multilingual WSD and MT evaluation more sensitive to lexical semantics.
Proceedings ArticleDOI
SUM-QE: a BERT-based Summary Quality Estimation Model
TL;DR: The model addresses linguistic quality aspects that are only indirectly captured by content-based approaches to summary evaluation, without involving comparison with human references, and achieves very high correlations with human ratings.
Journal ArticleDOI
Word sense clustering and clusterability
TL;DR: This article proposes to operationalize partitionability as clusterability, a measure of how easy the occurrences of a lemma are to cluster, and test two ways of measuring clusterability: existing measures from the machine learning literature that aim to measure the goodness of optimal k-means clusterings, and the idea that if aLemma is more clusterable, two clusterings based on two different “views” of the same data points will be more congruent.