Elena-Simona Apostol


2024

pdf bib
MultiLexBATS: Multilingual Dataset of Lexical Semantic Relations
Dagmar Gromann | Hugo Goncalo Oliveira | Lucia Pitarch | Elena-Simona Apostol | Jordi Bernad | Eliot Bytyçi | Chiara Cantone | Sara Carvalho | Francesca Frontini | Radovan Garabik | Jorge Gracia | Letizia Granata | Fahad Khan | Timotej Knez | Penny Labropoulou | Chaya Liebeskind | Maria Pia Di Buono | Ana Ostroški Anić | Sigita Rackevičienė | Ricardo Rodrigues | Gilles Sérasset | Linas Selmistraitis | Mahammadou Sidibé | Purificação Silvano | Blerina Spahiu | Enriketa Sogutlu | Ranka Stanković | Ciprian-Octavian Truică | Giedre Valunaite Oleskeviciene | Slavko Zitnik | Katerina Zdravkova
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Understanding the relation between the meanings of words is an important part of comprehending natural language. Prior work has either focused on analysing lexical semantic relations in word embeddings or probing pretrained language models (PLMs), with some exceptions. Given the rarity of highly multilingual benchmarks, it is unclear to what extent PLMs capture relational knowledge and are able to transfer it across languages. To start addressing this question, we propose MultiLexBATS, a multilingual parallel dataset of lexical semantic relations adapted from BATS in 15 languages including low-resource languages, such as Bambara, Lithuanian, and Albanian. As experiment on cross-lingual transfer of relational knowledge, we test the PLMs’ ability to (1) capture analogies across languages, and (2) predict translation targets. We find considerable differences across relation types and languages with a clear preference for hypernymy and antonymy as well as romance languages.

pdf bib
LLODIA: A Linguistic Linked Open Data Model for Diachronic Analysis
Florentina Armaselu | Chaya Liebeskind | Paola Marongiu | Barbara McGillivray | Giedre Valunaite Oleskeviciene | Elena-Simona Apostol | Ciprian-Octavian Truica | Daniela Gifu
Proceedings of the 9th Workshop on Linked Data in Linguistics @ LREC-COLING 2024

This article proposes a linguistic linked open data model for diachronic analysis (LLODIA) that combines data derived from diachronic analysis of multilingual corpora with dictionary-based evidence. A humanities use case was devised as a proof of concept that includes examples in five languages (French, Hebrew, Latin, Lithuanian and Romanian) related to various meanings of the term “revolution” considered at different time intervals. The examples were compiled through diachronic word embedding and dictionary alignment.

2023

pdf bib
Towards a Conversational Web? A Benchmark for Analysing Semantic Change with Conversational Knowledge Bots and Linked Open Data
Florentina Armaselu | Elena-Simona Apostol | Christian Chiarcos | Anas Fahad Khan | Chaya Liebeskind | Barbara McGillivray | Ciprian-Octavian Truica | Andrius Utka | Giedrė Valūnaitė-Oleškevičienė
Proceedings of the 4th Conference on Language, Data and Knowledge

pdf bib
Workflow Reversal and Data Wrangling in Multilingual Diachronic Analysis and Linguistic Linked Open Data Modelling
Florentina Armaselu | Barbara McGillivray | Chaya Liebeskind | Giedrė Valūnaitė Oleškevičienė | Andrius Utka | Daniela Gifu | Anas Fahad Khan | Elena-Simona Apostol | Ciprian-Octavian Truica
Proceedings of the 4th Conference on Language, Data and Knowledge

pdf bib
Validation of Language Agnostic Models for Discourse Marker Detection
Mariana Damova | Kostadin Mishev | Giedrė Valūnaitė-Oleškevičienė | Chaya Liebeskind | Purificação Silvano | Dimitar Trajanov | Ciprian-Octavian Truica | Elena-Simona Apostol | Christian Chiarcos | Anna Baczkowska
Proceedings of the 4th Conference on Language, Data and Knowledge

2022

pdf bib
Cross-Lingual Link Discovery for Under-Resourced Languages
Michael Rosner | Sina Ahmadi | Elena-Simona Apostol | Julia Bosque-Gil | Christian Chiarcos | Milan Dojchinovski | Katerina Gkirtzou | Jorge Gracia | Dagmar Gromann | Chaya Liebeskind | Giedrė Valūnaitė Oleškevičienė | Gilles Sérasset | Ciprian-Octavian Truică
Proceedings of the Thirteenth Language Resources and Evaluation Conference

In this paper, we provide an overview of current technologies for cross-lingual link discovery, and we discuss challenges, experiences and prospects of their application to under-resourced languages. We rst introduce the goals of cross-lingual linking and associated technologies, and in particular, the role that the Linked Data paradigm (Bizer et al., 2011) applied to language data can play in this context. We de ne under-resourced languages with a speci c focus on languages actively used on the internet, i.e., languages with a digitally versatile speaker community, but limited support in terms of language technology. We argue that languages for which considerable amounts of textual data and (at least) a bilingual word list are available, techniques for cross-lingual linking can be readily applied, and that these enable the implementation of downstream applications for under-resourced languages via the localisation and adaptation of existing technologies and resources.

pdf bib
ISO-based Annotated Multilingual Parallel Corpus for Discourse Markers
Purificação Silvano | Mariana Damova | Giedrė Valūnaitė Oleškevičienė | Chaya Liebeskind | Christian Chiarcos | Dimitar Trajanov | Ciprian-Octavian Truică | Elena-Simona Apostol | Anna Baczkowska
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Discourse markers carry information about the discourse structure and organization, and also signal local dependencies or epistemological stance of speaker. They provide instructions on how to interpret the discourse, and their study is paramount to understand the mechanism underlying discourse organization. This paper presents a new language resource, an ISO-based annotated multilingual parallel corpus for discourse markers. The corpus comprises nine languages, Bulgarian, Lithuanian, German, European Portuguese, Hebrew, Romanian, Polish, and Macedonian, with English as a pivot language. In order to represent the meaning of the discourse markers, we propose an annotation scheme of discourse relations from ISO 24617-8 with a plug-in to ISO 24617-2 for communicative functions. We describe an experiment in which we applied the annotation scheme to assess its validity. The results reveal that, although some extensions are required to cover all the multilingual data, it provides a proper representation of discourse markers value. Additionally, we report some relevant contrastive phenomena concerning discourse markers interpretation and role in discourse. This first step will allow us to develop deep learning methods to identify and extract discourse relations and communicative functions, and to represent that information as Linguistic Linked Open Data (LLOD).

pdf bib
Modelling Frequency, Attestation, and Corpus-Based Information with OntoLex-FrAC
Christian Chiarcos | Elena-Simona Apostol | Besim Kabashi | Ciprian-Octavian Truică
Proceedings of the 29th International Conference on Computational Linguistics

OntoLex-Lemon has become a de facto standard for lexical resources in the web of data. This paper provides the first overall description of the emerging OntoLex module for Frequency, Attestations, and Corpus-Based Information (OntoLex-FrAC) that is intended to complement OntoLex-Lemon with the necessary vocabulary to represent major types of information found in or automatically derived from corpora, for applications in both language technology and the language sciences.

2020

pdf bib
Neural Approaches for Natural Language Interfaces to Databases: A Survey
Radu Cristian Alexandru Iacob | Florin Brad | Elena-Simona Apostol | Ciprian-Octavian Truică | Ionel Alexandru Hosu | Traian Rebedea
Proceedings of the 28th International Conference on Computational Linguistics

A natural language interface to databases (NLIDB) enables users without technical expertise to easily access information from relational databases. Interest in NLIDBs has resurged in the past years due to the availability of large datasets and improvements to neural sequence-to-sequence models. In this survey we focus on the key design decisions behind current state of the art neural approaches, which we group into encoder and decoder improvements. We highlight the three most important directions, namely linking question tokens to database schema elements (schema linking), better architectures for encoding the textual query taking into account the schema (schema encoding), and improved generation of structured queries using autoregressive neural models (grammar-based decoders). To foster future research, we also present an overview of the most important NLIDB datasets, together with a comparison of the top performing neural models and a short insight into recent non deep learning solutions.