Workshop on Linked Data in Linguistics (2024)


up

pdf (full)
bib (full)
Proceedings of the 9th Workshop on Linked Data in Linguistics @ LREC-COLING 2024

pdf bib
Proceedings of the 9th Workshop on Linked Data in Linguistics @ LREC-COLING 2024
Christian Chiarcos | Katerina Gkirtzou | Maxim Ionov | Fahad Khan | John P. McCrae | Elena Montiel Ponsoda | Patricia Martín Chozas

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

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.

pdf bib
Cross-Lingual Ontology Matching using Structural and Semantic Similarity
Shubhanker Banerjee | Bharathi Raja Chakravarthi | John Philip McCrae

The development of ontologies in various languages is attracting attention as the amount of multilingual data available on the web increases. Cross-lingual ontology matching facilitates interoperability amongst ontologies in different languages. Although supervised machine learning-based methods have shown good performance on ontology matching, their application to the cross-lingual setting is limited by the availability of training data. Current state-of-the-art unsupervised methods for cross-lingual ontology matching focus on lexical similarity between entities. These approaches follow a two-stage pipeline where the entities are translated into a common language using a translation service in the first step followed by computation of lexical similarity between the translations to match the entities in the second step. In this paper we introduce a novel ontology matching method based on the fusion of structural similarity and cross-lingual semantic similarity. We carry out experiments using 3 language pairs and report substantial improvements on the performance of the lexical methods thus showing the effectiveness of our proposed approach. To the best of our knowledge this is the first work which tackles the problem of unsupervised ontology matching in the cross-lingual setting by leveraging both structural and semantic embeddings.

pdf bib
Querying the Lexicon der indogermanischen Verben in the LiLa Knowledge Base: Two Use Cases
Valeria Irene Boano | Marco Passarotti | Riccardo Ginevra

This paper presents two use cases of the etymological data provided by the *Lexicon der indogermanischen Verben* (LIV) after their publication as Linked Open Data and their linking to the LiLa Knowledge Base (KB) of interoperable linguistic resources for Latin. The first part of the paper briefly describes the LiLa KB and its structure. Then, the LIV and the information it contains are introduced, followed by a short description of the ontologies and the extensions used for modelling the LIV’s data and interlinking them to the LiLa ecosystem. The last section details the two use cases. The first case concerns the inflection types of the Latin verbs that reflect Proto-Indo-European stems, while the second one focusses on the Latin derivatives of the inherited stems. The results of the investigations are put in relation to current research topics in Historical Linguistics, demonstrating their relevance to the discipline.

pdf bib
Defining an Ontology for Museum Critical Cataloguing Terminology Guidelines
Erin Canning

Submission type: Short paper This paper presents the proposed ontology for the project Computational Approaches for Addressing Problematic Terminology (CAAPT). This schema seeks to represent contents and structure of language guideline documents produced by cultural heritage institutions seeking to engage with critical cataloguing or reparative description work, known as terminology guidance documents. It takes the Victoria & Albert Museum’s Terminology Guidance Document as a source for the initial modelling work. Ultimately, CAAPT seeks to expand the knowledge graph beyond the V&A Museum context to incorporate additional terminology guidance documents and linked open data vocabularies. The ontology seeks to bring together scholarly communities in areas relevant to this project, most notably those in cultural heritage and linguistics linked open data, by leveraging existing linked data resources in these areas: as such, OntoLex, CIDOC CRM, and SKOS are used as a foundation for this work, along with a proposed schema from a related project, CULCO. As the CAAPT project is in early stages, this paper presents the preliminary results of work undertaken thus far in order to seek feedback from the linguistics linked open data community.

pdf bib
The MOLOR Lemma Bank: a New LLOD Resource for Old Irish
Theodorus Fransen | Cormac Anderson | Sacha Beniamine | Marco Passarotti

This paper describes the first steps in creating a Lemma Bank for Old Irish (600-900CE) within the Linked Data paradigm, taking inspiration from a similar resource for Latin built as part of the LiLa project (2018–2023). The focus is on the extraction and RDF conversion of nouns from Goidelex, a novel and highly structured morphological resource for Old Irish. The aim is to strike a good balance between retaining a representative level of morphological granularity and at the same time keeping the amount of lemma variants within workable limits, to facilitate straightforward resource interlinking for Old Irish, planned as future work.

pdf bib
CHAMUÇA: Towards a Linked Data Language Resource of Portuguese Borrowings in Asian Languages
Fahad Khan | Ana Salgado | Isuri Anuradha | Rute Costa | Chamila Liyanage | John P. McCrae | Atul Kr. Ojha | Priya Rani | Francesca Frontini

This paper presents the development of CHAMUÇA, a novel lexical resource designed to document the influence of the Portuguese language on various Asian languages, with an initial focus on the languages of South Asia. Through the utilization of linked open data and the OntoLex vocabulary, CHAMUÇA offers structured insights into the linguistic characteristics, and cultural ramifications of Portuguese borrowings across multiple languages. The article outlines CHAMUÇA’s potential contributions to the linguistic linked data community, emphasising its role in addressing the scarcity of resources for lesser-resourced languages and serving as a test case for organising etymological data in a queryable format. CHAMUÇA emerges as an initiative towards the comprehensive catalogization and analysis of Portuguese borrowings, offering valuable insights into language contact dynamics, historical evolution, and cultural exchange in Asia, one that is based on linked data technology.

pdf bib
LODinG: Linked Open Data in the Humanities
Jacek Kudera | Claudia Bamberg | Thomas Burch | Folke Gernert | Maria Hinzmann | Susanne Kabatnik | Claudine Moulin | Benjamin Raue | Achim Rettinger | Jörg Röpke | Ralf Schenkel | Kristin Shi-Kupfer | Doris Schirra | Christof Schöch | Joëlle Weis

We are presenting LODinG – Linked Open Data in the Humanities (abbreviated from Linked Open Data in den Geisteswissenschaften), a recently launched research initiative exploring the intersection of Linked Open Data (LOD) and a range of areas of work within the Humanities. We focus on effective methods of collecting, modeling, linking, releasing and analyzing machine-readable information relevant to (digital) humanities research in the form of LOD. LODinG combines the sources and methods of digital humanities, general and computational linguistics, digital lexicography, German and Romance philology, translatology, cultural and literary studies, media studies, information science and law to explore and expand the potential of the LOD paradigm for such a diverse and multidisciplinary field. The project’s primary objectives are to improve the methods of extracting, modeling and analyzing multilingual data in the LOD paradigm; to demonstrate the application of the linguistic LOD to various methods and domains within and beyond the humanities; and to develop a modular, cross-domain data model for the humanities.

pdf bib
DigItAnt: a platform for creating, linking and exploiting LOD lexica with heterogeneous resources
Michele Mallia | Michela Bandini | Andrea Bellandi | Francesca Murano | Silvia Piccini | Luca Rigobianco | Alessandro Tommasi | Cesare Zavattari | Mariarosaria Zinzi | Valeria Quochi

Over the past few years, the deployment of Linked Open Data (LOD) technologies has witnessed significant advancements across a myriad of sectors, linguistics included. This progression is characterized by an exponential increase in the conversion of resources to adhere to contemporary encoding standards. Such transformations are driven by the objectives outlined in “ecological” methodologies, notably the FAIR data principles, which advocate for the reuse and interoperability of resources. This paper presents the DigItAnt architecture, developed in the context of a national project funded by the Italian Ministry of Research and in the service of a recently started Italian endeavor to realize a federation of infrastructures for the humanities. It details its services, utilities and data types, and shows how it manages to produce, exploit and interlink LLOD and non-LLOD datasets in ways that are meaningful to its intended target disciplinary context, i.e. historical linguistics over epigraphy data. The paper also introduces how DigItAnt services and functionalities will contribute to the empowerment of the H2IOSC Italian infrastructures cluster project, which is devoted to the construction of a nationwide research infrastructure federation for the humanities, and it will possibly contribute to its pilot project towards an authoritative LLOD platform.

pdf bib
Teanga Data Model for Linked Corpora
John P. McCrae | Priya Rani | Adrian Doyle | Bernardo Stearns

Corpus data is the main source of data for natural language processing applications, however no standard or model for corpus data has become predominant in the field. Linguistic linked data aims to provide methods by which data can be made findable, accessible, interoperable and reusable (FAIR). However, current attempts to create a linked data format for corpora have been unsuccessful due to the verbose and specialised formats that they use. In this work, we present the Teanga data model, which uses a layered annotation model to capture all NLP-relevant annotations. We present the YAML serializations of the model, which is concise and uses a widely-deployed format, and we describe how this can be interpreted as RDF. Finally, we demonstrate three examples of the use of the Teanga data model for syntactic annotation, literary analysis and multilingual corpora.

pdf bib
The Services of the LiLa Knowledge Base of Interoperable Linguistic Resources for Latin
Marco Passarotti | Francesco Mambrini | Giovanni Moretti

This paper describes three online services designed to ease the tasks of querying and populating the linguistic resources for Latin made interoperable through their publication as Linked Open Data in the LiLa Knowledge Base. As for querying the KB, we present an interface to search the collection of lemmas that represents the core of the Knowledge Base, and an interactive, graphical platform to run queries on the resources currently interlinked. As for populating the KB with new textual resources, we describe a tool that performs automatic tokenization, lemmatization and Part-of-Speech tagging of a raw text in Latin and links its tokens to LiLa.

pdf bib
An Annotated Dataset for Transformer-based Scholarly Information Extraction and Linguistic Linked Data Generation
Vayianos Pertsas | Marialena Kasapaki | Panos Constantopoulos

We present a manually curated and annotated, multidisciplinary dataset of 15,262 sentences from research articles (abstract and main text) that can be used for transformer-based extraction from scholarly publications of three types of entities: 1) research methods, named entities of variable length, 2) research goals, entities that appear as textual spans of variable length with mostly fixed lexico-syntactic-structure, and 3) research activities, entities that appear as textual spans of variable length with complex lexico-syntactic structure. We explore the capabilities of our dataset by using it for training/fine-tuning various ML and transformer-based models. We compare our finetuned models as well as LLM responses (chatGPT 3.5) based on 10-shot learning, by measuring F1 scores in token-based, entity-based strict and entity-based partial evaluations across interdisciplinary and discipline-specific datasets in order to capture any possible differences in discipline-oriented writing styles. Results show that fine tuning of transformer-based models significantly outperforms the performance of few- shot learning of LLMs such as chatGPT, highlighting the significance of annotation datasets in such tasks. Our dataset can also be used as a source for linguistic linked data by itself. We demonstrate this by presenting indicative queries in SPARQL, executed over such an RDF knowledge graph.

pdf bib
Linguistic LOD for Interoperable Morphological Description
Michael Rosner | Maxim Ionov

Interoperability is a characteristic of a product or system that seamlessly works with another product or system and implies a certain level of independence from the context of use. Turning to language resources, interoperability is frequently cited as one important rationale underlying the use of LLOD representations and is generally regarded as highly desirable. In this paper we further elaborate this theme, distinguishing three different kinds of interoperability providing practical implementations with examples from morphology.

pdf bib
Modeling linking between text and lexicon with OntoLex-Lemon: a case study of computational terminology for the Babylonian Talmud
Flavia Sciolette

This paper illustrates the first steps in the creation of a computational terminology for the Babylonian Talmud. After introducing reasons and the state of the art, the paper exposes the choice of using OntoLex-Lemon and the new FrAC module for encoding the attestations and quantitative data of the terminology extraction. After that, the Talmudic terminology base is introduced and an example entry with the above-mentioned data is shown. The scheme is motivated not only by the rich representation the model allows, but also by the future management of the link between text and lexical entries.

pdf bib
OntoLex Publication Made Easy: A Dataset of Verbal Aspectual Pairs for Bosnian, Croatian and Serbian
Ranka Stanković | Maxim Ionov | Medina Bajtarević | Lorena Ninčević

This paper introduces a novel language resource for retrieving and researching verbal aspectual pairs in BCS (Bosnian, Croatian, and Serbian) created using Linguistic Linked Open Data (LLOD) principles. As there is no resource to help learners of Bosnian, Croatian, and Serbian as foreign languages to recognize the aspect of a verb or its pairs, we have created a new resource that will provide users with information about the aspect, as well as the link to a verb’s aspectual counterparts. This resource also contains external links to monolingual dictionaries, Wordnet, and BabelNet. As this is a work in progress, our resource only includes verbs and their perfective pairs formed with prefixes “pro”, “od”, “ot”, “iz”, “is” and “na”. The goal of this project is to have a complete dataset of all the aspectual pairs in these three languages. We believe it will be useful for research in the field of aspectology, as well as machine translation and other NLP tasks. Using this resource as an example, we also propose a sustainable approach to publishing small to moderate LLOD resources on the Web, both in a user-friendly way and according to the Linked Data principles.

pdf bib
Towards Semantic Interoperability: Parallel Corpora as Linked Data Incorporating Named Entity Linking
Ranka Stanković | Milica Ikonić Nešić | Olja Perisic | Mihailo Škorić | Olivera Kitanović

The paper presents the results of the research related to the preparation of parallel corpora, focusing on transformation into RDF graphs using NLP Interchange Format (NIF) for linguistic annotation. We give an overview of the parallel corpus that was used in this case study, as well as the process of POS tagging, lemmatization, named entity recognition (NER), and named entity linking (NEL), which is implemented using Wikidata. In the first phase of NEL main characters and places mentioned in novels are stored in Wikidata and in the second phase they are linked with the occurrences of previously annotated entities in text. Next, we describe the named entity linking (NEL), data conversion to RDF, and incorporation of NIF annotations. Produced NIF files were evaluated through the exploration of triplestore using SPARQL queries. Finally, the bridging of Linked Data and Digital Humanities research is discussed, as well as some drawbacks related to the verbosity of transformation. Semantic interoperability concept in the context of linked data and parallel corpora ensures that data exchanged between systems carries shared and well-defined meanings, enabling effective communication and understanding.