This paper presents our contribution to the IWSLT Low Resource Track 2: ‘Training and Evaluation Data Track’. We share a human-evaluated Urdu-English speech-to-text corpus based on Common Voice 13.0 Urdu speech corpus. We followed a three-tier validation scheme which involves an initial automatic translation with corrections from native reviewers, full review by evaluators followed by final validation from a bilingual expert ensuring reliable corpus for subsequent NLP tasks. Our contribution, CV-UrEnST corpus, enriches Urdu speech resources by contributing the first Urdu-English speech-to-text corpus. When evaluated with Whisper-medium, the corpus yielded a significant improvement to the vanilla model in terms of BLEU, chrF++, and COMET scores, demonstrating its effectiveness for speech translation tasks.

Idiomatic expressions pose difficulties for Natural Language Processing (NLP) because they are noncompositional. In this paper, we propose the Idiom Visual Understanding Dataset (IVUD), a multimodal dataset for idiom understanding using visual and textual representation. For SemEval-2025 Task 1 (AdMIRe), we specifically addressed dataset augmentation using AI-synthesized images and human-directed prompt engineering. We compared the efficacy of vision- and text-based models in ranking images aligned with idiomatic phrases. The results identify the advantages of using multimodal context for enhanced idiom understanding, showcasing how vision-language models perform better than text-only approaches in the detection of idiomaticity.

In this paper, we present our methodology and findings from participating in the FIGNEWS 2024 shared task on annotating news fragments on the Gaza-Israel war for bias and propaganda detection. The task aimed to refine the FIGNEWS 2024 annotation guidelines and to contribute to the creation of a comprehensive dataset to advance research in this field. Our team employed a multi-faceted approach to ensure high accuracy in data annotations. Our results highlight key challenges in detecting bias and propaganda, such as the need for more comprehensive guidelines. Our team ranked first in all tracks for propaganda annotation. For Bias, the team stood in first place for the Guidelines and IAA tracks, and in second place for the Quantity and Consistency tracks.

Despite the abundance of monolingual corpora accessible online, there remains a scarcity of domain specific parallel corpora. This scarcity poses a challenge in the development of robust translation systems tailored for such specialized domains. Addressing this gap, we have developed a parallel religious domain corpus for Urdu-English. This corpus consists of 18,426 parallel sentences from Sunan Daud, carefully curated to capture the unique linguistic and contextual aspects of religious texts. The developed corpus is then used to train Urdu-English religious domain Neural Machine Translation (NMT) systems, the best system scored 27.9 BLEU points

We have explored the effect of in domain knowledge during parallel sentence filtering from in domain corpora. Models built with sentences mined from in domain corpora without domain knowledge performed poorly, whereas model performance improved by more than 2.3 BLEU points on average with further domain centric filtering. We have used Large Language Models for selecting similar and domain aligned sentences. Our experiments show the importance of inclusion of domain knowledge in sentence selection methodologies even if the initial comparable corpora are in domain.

Neural methods in Text to Speech synthesis (TTS) have demonstrated momentous advancement in terms of the naturalness and intelligibility of the synthesized speech. In this paper we present neural speech synthesis system for Urdu language, a low resource language. The main challenge faced for this study was the non-availability of any publicly available Urdu speech synthesis corpora. Urdu speech corpus was created using audio books and synthetic speech generation. To leverage the low resource scenario we adopted transfer learning for our experiments where knowledge extracted is further used to train the model using a relatively smaller Urdu training data set. The results from this model show satisfactory results, though a good margin for improvement exists and we are working to improve it further.

To build automated simplification systems, corpora of complex sentences and their simplified versions is the first step to understand sentence complexity and enable the development of automatic text simplification systems. We present a lexical and syntactically simplified Urdu simplification corpus with a detailed analysis of the various simplification operations and human evaluation of corpus quality. We further analyze our corpora using text readability measures and present a comparison of the original, lexical simplified and syntactically simplified corpora. In addition, we compare our corpus with other existing simplification corpora by building simplification systems and evaluating these systems using BLEU and SARI scores. Our system achieves the highest BLEU score and comparable SARI score in comparison to other systems. We release our simplification corpora for the benefit of the research community.

This paper describes LISN’s submissions to two shared tasks at WMT’21. For the biomedical translation task, we have developed resource-heavy systems for the English-French language pair, using both out-of-domain and in-domain corpora. The target genre for this task (scientific abstracts) corresponds to texts that often have a standardized structure. Our systems attempt to take this structure into account using a hierarchical system of sentence-level tags. Translation systems were also prepared for the News task for the French-German language pair. The challenge was to perform unsupervised adaptation to the target domain (financial news). For this, we explored the potential of retrieval-based strategies, where sentences that are similar to test instances are used to prime the decoder.

In this paper we present the FJWU’s system submitted to the biomedical shared task at WMT21. We prepared state-of-the-art multilingual neural machine translation systems for three languages (i.e. German, Spanish and French) with English as target language. Our NMT systems based on Transformer architecture, were trained on combination of in-domain and out-domain parallel corpora developed using Information Retrieval (IR) and domain adaptation techniques.

La simplification de textes a émergé comme un sous-domaine actif du traitement automatique des langues, du fait des problèmes pratiques et théoriques qu’elle permet d’aborder, ainsi que de ses nombreuses applications pratiques. Des corpus de simplification sont nécessaires pour entrainer des systèmes de simplification automatique ; ces ressources sont toutefois rares et n’existent que pour un petit nombre de langues. Nous montrons ici que dans un contexte où les ressources pour la simplification sont rares, il reste néanmoins possible de construire des systèmes de simplification, en ayant recours à des corpus synthétiques, par exemple obtenus par traduction automatique, et nous évaluons diverses manières de les constituer.

Recent studies have shown that translation quality of NMT systems can be improved by providing document-level contextual information. In general sentence-based NMT models are extended to capture contextual information from large-scale document-level corpora which are difficult to acquire. Domain adaptation on the other hand promises adapting components of already developed systems by exploiting limited in-domain data. This paper presents FJWU’s system submission at WNGT, we specifically participated in Document level MT task for German-English translation. Our system is based on context-aware Transformer model developed on top of original NMT architecture by integrating contextual information using attention networks. Our experimental results show providing previous sentences as context significantly improves the BLEU score as compared to a strong NMT baseline. We also studied the impact of domain adaptation on document level translationand were able to improve results by adaptingthe systems according to the testing domain.

Machine Translation is the inevitable technology to reduce communication barriers in today’s world. It has made substantial progress in recent years and is being widely used in commercial as well as non-profit sectors. Such is only the case for European and other high resource languages. For English-Urdu language pair, the technology is in its infancy stage due to scarcity of resources. Present research is an important milestone in English-Urdu machine translation, as we present results for four major domains including Biomedical, Religious, Technological and General using Statistical and Neural Machine Translation. We performed series of experiments in attempts to optimize the performance of each system and also to study the impact of data sources on the systems. Finally, we established a comparison of the data sources and the effect of language model size on statistical machine translation performance.

Complex sentences are a hurdle in the learning process of language learners. Sentence simplification aims to convert a complex sentence into its simpler form such that it is easily comprehensible. To build such automated simplification systems, corpora of complex sentences and their simplified versions is the first step to understand sentence complexity and enable the development of automatic text simplification systems. No such corpus has yet been developed for Urdu and we fill this gap by developing one such corpus to help start readability and automatic sentence simplification research. We present a lexical and syntactically simplified Urdu simplification corpus and a detailed analysis of the various simplification operations. We further analyze our corpora using text readability measures and present a comparison of the original, lexical simplified, and syntactically simplified corpora.

This paper describes our system submission to WMT20 shared task on similar language translation. We examined the use of documentlevel neural machine translation (NMT) systems for low-resource, similar language pair Marathi−Hindi. Our system is an extension of state-of-the-art Transformer architecture with hierarchical attention networks to incorporate contextual information. Since, NMT requires large amount of parallel data which is not available for this task, our approach is focused on utilizing monolingual data with back translation to train our models. Our experiments reveal that document-level NMT can be a reasonable alternative to sentence-level NMT for improving translation quality of low resourced languages even when used with synthetic data.

This paper describes LIMSI’s submissions to the translation shared tasks at WMT’20. This year we have focused our efforts on the biomedical translation task, developing a resource-heavy system for the translation of medical abstracts from English into French, using back-translated texts, terminological resources as well as multiple pre-processing pipelines, including pre-trained representations. Systems were also prepared for the robustness task for translating from English into German; for this large-scale task we developed multi-domain, noise-robust, translation systems aim to handle the two test conditions: zero-shot and few-shot domain adaptation.

This paper reports system descriptions for FJWU-NRPU team for participation in the WMT20 Biomedical shared translation task. We focused our submission on exploring the effects of adding in-domain corpora extracted from various out-of-domain sources. Systems were built for French to English using in-domain corpora through fine tuning and selective data training. We further explored BERT based models specifically with focus on effect of domain adaptive subword units.

Transfer Learning and Selective data training are two of the many approaches being extensively investigated to improve the quality of Neural Machine Translation systems. This paper presents a series of experiments by applying transfer learning and selective data training for participation in the Bio-medical shared task of WMT19. We have used Information Retrieval to selectively choose related sentences from out-of-domain data and used them as additional training data using transfer learning. We also report the effect of tokenization on translation model performance.

This paper describes the system developed by the LIUM laboratory for the 2008 IWSLT evaluation. We only participated in the Arabic/English BTEC task. We developed a statistical phrase-based system using the Moses toolkit and SYSTRAN’s rule-based translation system to perform a morphological decomposition of the Arabic words. A continuous space language model was deployed to improve the modeling of the target language. Both approaches achieved significant improvements in the BLEU score. The system achieves a score of 49.4 on the test set of the 2008 IWSLT evaluation.