Theodorus Fransen


2023

pdf
Temporal Domain Adaptation for Historical Irish
Oksana Dereza | Theodorus Fransen | John P. Mccrae
Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)

The digitisation of historical texts has provided new horizons for NLP research, but such data also presents a set of challenges, including scarcity and inconsistency. The lack of editorial standard during digitisation exacerbates these difficulties. This study explores the potential for temporal domain adaptation in Early Modern Irish and pre-reform Modern Irish data. We describe two experiments carried out on the book subcorpus of the Historical Irish Corpus, which includes Early Modern Irish and pre-reform Modern Irish texts from 1581 to 1926. We also propose a simple orthographic normalisation method for historical Irish that reduces the type-token ratio by 21.43% on average in our data. The results demonstrate that the use of out-of-domain data significantly improves a language model’s performance. Providing a model with additional input from another historical stage of the language improves its quality by 12.49% on average on non-normalised texts and by 27.02% on average on normalised (demutated) texts. Most notably, using only out-of-domain data for both pre-training and training stages allowed for up to 86.81% of the baseline model quality on non-normalised texts and up to 95.68% on normalised texts without any target domain data. Additionally, we investigate the effect of temporal distance between the training and test data. The hypothesis that there is a positive correlation between performance and temporal proximity of training and test data has been validated, which manifests best in normalised data. Expanding this approach even further back, to Middle and Old Irish, and testing it on other languages is a further research direction.

pdf
Findings of the SIGTYP 2023 Shared task on Cognate and Derivative Detection For Low-Resourced Languages
Priya Rani | Koustava Goswami | Adrian Doyle | Theodorus Fransen | Bernardo Stearns | John P. McCrae
Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP

This paper describes the structure and findings of the SIGTYP 2023 shared task on cognate and derivative detection for low-resourced languages, broken down into a supervised and unsupervised sub-task. The participants were asked to submit the test data’s final prediction. A total of nine teams registered for the shared task where seven teams registered for both sub-tasks. Only two participants ended up submitting system descriptions, with only one submitting systems for both sub-tasks. While all systems show a rather promising performance, all could be within the baseline score for the supervised sub-task. However, the system submitted for the unsupervised sub-task outperforms the baseline score.

pdf
The Cardamom Workbench for Historical and Under-Resourced Languages
Adrian Doyle | Theodorus Fransen | Bernardo Stearns | John P. McCrae | Oksana Dereza | Priya Rani
Proceedings of the 4th Conference on Language, Data and Knowledge

pdf
Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languages
Koustava Goswami | Priya Rani | Theodorus Fransen | John McCrae
Findings of the Association for Computational Linguistics: EMNLP 2023

Exploiting cognates for transfer learning in under-resourced languages is an exciting opportunity for language understanding tasks, including unsupervised machine translation, named entity recognition and information retrieval. Previous approaches mainly focused on supervised cognate detection tasks based on orthographic, phonetic or state-of-the-art contextual language models, which under-perform for most under-resourced languages. This paper proposes a novel language-agnostic weakly-supervised deep cognate detection framework for under-resourced languages using morphological knowledge from closely related languages. We train an encoder to gain morphological knowledge of a language and transfer the knowledge to perform unsupervised and weakly-supervised cognate detection tasks with and without the pivot language for the closely-related languages. While unsupervised, it overcomes the need for hand-crafted annotation of cognates. We performed experiments on different published cognate detection datasets across language families and observed not only significant improvement over the state-of-the-art but also our method outperformed the state-of-the-art supervised and unsupervised methods. Our model can be extended to a wide range of languages from any language family as it overcomes the requirement of the annotation of the cognate pairs for training.

pdf
Do not Trust the Experts: How the Lack of Standard Complicates NLP for Historical Irish
Oksana Dereza | Theodorus Fransen | John P. Mccrae
The Fourth Workshop on Insights from Negative Results in NLP

In this paper, we describe how we unearthed some fundamental problems while building an analogy dataset modelled on BATS (Gladkova et al., 2016) to evaluate historical Irish embeddings on their ability to detect orthographic, morphological and semantic similarity. The performance of our models in the analogy task was extremely poor regardless of the architecture, hyperparameters and evaluation metrics, while the qualitative evaluation revealed positive tendencies. We argue that low agreement between field experts on fundamental lexical and orthographic issues, and the lack of a unified editorial standard in available resources make it impossible to build reliable evaluation datasets for computational models and obtain interpretable results. We emphasise the need for such a standard, particularly for NLP applications, and prompt Celticists and historical linguists to engage in further discussion. We would also like to draw NLP scholars’ attention to the role of data and its (extra)linguistic properties in testing new models, technologies and evaluation scenarios.

2022

pdf bib
Proceedings of the 4th Celtic Language Technology Workshop within LREC2022
Theodorus Fransen | William Lamb | Delyth Prys
Proceedings of the 4th Celtic Language Technology Workshop within LREC2022

pdf
MHE: Code-Mixed Corpora for Similar Language Identification
Priya Rani | John P. McCrae | Theodorus Fransen
Proceedings of the Thirteenth Language Resources and Evaluation Conference

This paper introduces a new Magahi-Hindi-English (MHE) code-mixed data-set for similar language identification (SMLID), where Magahi is a less-resourced minority language. This corpus provides a language id at two levels: word and sentence. This data-set is the first Magahi-Hindi-English code-mixed data-set for similar language identification task. Furthermore, we will discuss the complexity of the data-set and provide a few baselines for the language identification task.

2021

pdf
Cross-lingual Sentence Embedding using Multi-Task Learning
Koustava Goswami | Sourav Dutta | Haytham Assem | Theodorus Fransen | John P. McCrae
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Multilingual sentence embeddings capture rich semantic information not only for measuring similarity between texts but also for catering to a broad range of downstream cross-lingual NLP tasks. State-of-the-art multilingual sentence embedding models require large parallel corpora to learn efficiently, which confines the scope of these models. In this paper, we propose a novel sentence embedding framework based on an unsupervised loss function for generating effective multilingual sentence embeddings, eliminating the need for parallel corpora. We capture semantic similarity and relatedness between sentences using a multi-task loss function for training a dual encoder model mapping different languages onto the same vector space. We demonstrate the efficacy of an unsupervised as well as a weakly supervised variant of our framework on STS, BUCC and Tatoeba benchmark tasks. The proposed unsupervised sentence embedding framework outperforms even supervised state-of-the-art methods for certain under-resourced languages on the Tatoeba dataset and on a monolingual benchmark. Further, we show enhanced zero-shot learning capabilities for more than 30 languages, with the model being trained on only 13 languages. Our model can be extended to a wide range of languages from any language family, as it overcomes the requirement of parallel corpora for training.

pdf
Findings of the LoResMT 2021 Shared Task on COVID and Sign Language for Low-resource Languages
Atul Kr. Ojha | Chao-Hong Liu | Katharina Kann | John Ortega | Sheetal Shatam | Theodorus Fransen
Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)

We present the findings of the LoResMT 2021 shared task which focuses on machine translation (MT) of COVID-19 data for both low-resource spoken and sign languages. The organization of this task was conducted as part of the fourth workshop on technologies for machine translation of low resource languages (LoResMT). Parallel corpora is presented and publicly available which includes the following directions: English↔Irish, English↔Marathi, and Taiwanese Sign language↔Traditional Chinese. Training data consists of 8112, 20933 and 128608 segments, respectively. There are additional monolingual data sets for Marathi and English that consist of 21901 segments. The results presented here are based on entries from a total of eight teams. Three teams submitted systems for English↔Irish while five teams submitted systems for English↔Marathi. Unfortunately, there were no systems submissions for the Taiwanese Sign language↔Traditional Chinese task. Maximum system performance was computed using BLEU and follow as 36.0 for English–Irish, 34.6 for Irish–English, 24.2 for English–Marathi, and 31.3 for Marathi–English.

2020

pdf
A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment
Sina Ahmadi | John Philip McCrae | Sanni Nimb | Fahad Khan | Monica Monachini | Bolette Pedersen | Thierry Declerck | Tanja Wissik | Andrea Bellandi | Irene Pisani | Thomas Troelsgård | Sussi Olsen | Simon Krek | Veronika Lipp | Tamás Váradi | László Simon | András Gyorffy | Carole Tiberius | Tanneke Schoonheim | Yifat Ben Moshe | Maya Rudich | Raya Abu Ahmad | Dorielle Lonke | Kira Kovalenko | Margit Langemets | Jelena Kallas | Oksana Dereza | Theodorus Fransen | David Cillessen | David Lindemann | Mikel Alonso | Ana Salgado | José Luis Sancho | Rafael-J. Ureña-Ruiz | Jordi Porta Zamorano | Kiril Simov | Petya Osenova | Zara Kancheva | Ivaylo Radev | Ranka Stanković | Andrej Perdih | Dejan Gabrovsek
Proceedings of the Twelfth Language Resources and Evaluation Conference

Aligning senses across resources and languages is a challenging task with beneficial applications in the field of natural language processing and electronic lexicography. In this paper, we describe our efforts in manually aligning monolingual dictionaries. The alignment is carried out at sense-level for various resources in 15 languages. Moreover, senses are annotated with possible semantic relationships such as broadness, narrowness, relatedness, and equivalence. In comparison to previous datasets for this task, this dataset covers a wide range of languages and resources and focuses on the more challenging task of linking general-purpose language. We believe that our data will pave the way for further advances in alignment and evaluation of word senses by creating new solutions, particularly those notoriously requiring data such as neural networks. Our resources are publicly available at https://github.com/elexis-eu/MWSA.

pdf
A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data
Priya Rani | Shardul Suryawanshi | Koustava Goswami | Bharathi Raja Chakravarthi | Theodorus Fransen | John Philip McCrae
Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying

Hate speech detection in social media communication has become one of the primary concerns to avoid conflicts and curb undesired activities. In an environment where multilingual speakers switch among multiple languages, hate speech detection becomes a challenging task using methods that are designed for monolingual corpora. In our work, we attempt to analyze, detect and provide a comparative study of hate speech in a code-mixed social media text. We also provide a Hindi-English code-mixed data set consisting of Facebook and Twitter posts and comments. Our experiments show that deep learning models trained on this code-mixed corpus perform better.

pdf
Unsupervised Deep Language and Dialect Identification for Short Texts
Koustava Goswami | Rajdeep Sarkar | Bharathi Raja Chakravarthi | Theodorus Fransen | John P. McCrae
Proceedings of the 28th International Conference on Computational Linguistics

Automatic Language Identification (LI) or Dialect Identification (DI) of short texts of closely related languages or dialects, is one of the primary steps in many natural language processing pipelines. Language identification is considered a solved task in many cases; however, in the case of very closely related languages, or in an unsupervised scenario (where the languages are not known in advance), performance is still poor. In this paper, we propose the Unsupervised Deep Language and Dialect Identification (UDLDI) method, which can simultaneously learn sentence embeddings and cluster assignments from short texts. The UDLDI model understands the sentence constructions of languages by applying attention to character relations which helps to optimize the clustering of languages. We have performed our experiments on three short-text datasets for different language families, each consisting of closely related languages or dialects, with very minimal training sets. Our experimental evaluations on these datasets have shown significant improvement over state-of-the-art unsupervised methods and our model has outperformed state-of-the-art LI and DI systems in supervised settings.

pdf
ULD@NUIG at SemEval-2020 Task 9: Generative Morphemes with an Attention Model for Sentiment Analysis in Code-Mixed Text
Koustava Goswami | Priya Rani | Bharathi Raja Chakravarthi | Theodorus Fransen | John P. McCrae
Proceedings of the Fourteenth Workshop on Semantic Evaluation

Code mixing is a common phenomena in multilingual societies where people switch from one language to another for various reasons. Recent advances in public communication over different social media sites have led to an increase in the frequency of code-mixed usage in written language. In this paper, we present the Generative Morphemes with Attention (GenMA) Model sentiment analysis system contributed to SemEval 2020 Task 9 SentiMix. The system aims to predict the sentiments of the given English-Hindi code-mixed tweets without using word-level language tags instead inferring this automatically using a morphological model. The system is based on a novel deep neural network (DNN) architecture, which has outperformed the baseline F1-score on the test data-set as well as the validation data-set. Our results can be found under the user name “koustava” on the “Sentimix Hindi English” page.