Sshubam Verma, Mohammed Safi Ur Rahman Khan, Vishwajeet Kumar, Rudra Murthy, Jaydeep Sen. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Arnav Mhaske, Harshit Kedia, Sumanth Doddapaneni, Mitesh M. Khapra, Pratyush Kumar, Rudra Murthy, Anoop Kunchukuttan. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Named Entity Recognition (NER) is a foundational NLP task that aims to provide class labels like Person, Location, Organisation, Time, and Number to words in free text. Named Entities can also be multi-word expressions where the additional I-O-B annotation information helps label them during the NER annotation process. While English and European languages have considerable annotated data for the NER task, Indian languages lack on that front- both in terms of quantity and following annotation standards. This paper releases a significantly sized standard-abiding Hindi NER dataset containing 109,146 sentences and 2,220,856 tokens, annotated with 11 tags. We discuss the dataset statistics in all their essential detail and provide an in-depth analysis of the NER tag-set used with our data. The statistics of tag-set in our dataset shows a healthy per-tag distribution especially for prominent classes like Person, Location and Organisation. Since the proof of resource-effectiveness is in building models with the resource and testing the model on benchmark data and against the leader-board entries in shared tasks, we do the same with the aforesaid data. We use different language models to perform the sequence labelling task for NER and show the efficacy of our data by performing a comparative evaluation with models trained on another dataset available for the Hindi NER task. Our dataset helps achieve a weighted F1 score of 88.78 with all the tags and 92.22 when we collapse the tag-set, as discussed in the paper. To the best of our knowledge, no available dataset meets the standards of volume (amount) and variability (diversity), as far as Hindi NER is concerned. We fill this gap through this work, which we hope will significantly help NLP for Hindi. We release this dataset with our code and models for further research at https://github.com/cfiltnlp/HiNER

We explore the impact of leveraging the relatedness of languages that belong to the same family in NLP models using multilingual fine-tuning.We hypothesize and validate that multilingual fine-tuning of pre-trained language models can yield better performance on downstream NLP applications, compared to models fine-tuned on individual languages.A first of its kind detailed study is presented to track performance change as languages are added to a base language in a graded and greedy (in the sense of best boost of performance) manner; which reveals that careful selection of subset of related languages can significantly improve performance than utilizing all related languages.The Indo-Aryan (IA) language family is chosen for the study, the exact languages being Bengali, Gujarati, Hindi, Marathi, Oriya, Punjabi and Urdu.The script barrier is crossed by simple rule-based transliteration of the text of all languages to Devanagari.Experiments are performed on mBERT, IndicBERT, MuRIL and two RoBERTa-based LMs, the last two being pre-trained by us.Low resource languages, such as Oriya and Punjabi, are found to be the largest beneficiaries of multilingual fine-tuning.Textual Entailment, Entity Classification, Section Title Prediction, tasks of IndicGLUE and POS tagging form our test bed.Compared to monolingual fine tuning we get relative performance improvement of up to 150% in the downstream tasks.The surprise take-away is that for any language there is a particular combination of other languages which yields the best performance, and any additional language is in fact detrimental.

Recent advances in Unsupervised Neural Machine Translation (UNMT) has minimized the gap between supervised and unsupervised machine translation performance for closely related language-pairs. However and the situation is very different for distant language pairs. Lack of overlap in lexicon and low syntactic similarity such as between English and IndoAryan languages leads to poor translation quality in existing UNMT systems. In this paper and we show that initialising the embedding layer of UNMT models with cross-lingual embeddings leads to significant BLEU score improvements over existing UNMT models where the embedding layer weights are randomly initialized. Further and freezing the embedding layer weights leads to better gains compared to updating the embedding layer weights during training. We experimented using Masked Sequence to Sequence (MASS) and Denoising Autoencoder (DAE) UNMT approaches for three distant language pairs. The proposed cross-lingual embedding initialization yields BLEU score improvement of as much as ten times over the baseline for English-Hindi and English-Bengali and English-Gujarati. Our analysis shows that initialising embedding layer with static cross-lingual embedding mapping is essential for training of UNMT models for distant language-pairs.

In this paper and we identify an interesting kind of error in the output of Unsupervised Neural Machine Translation (UNMT) systems like Undreamt1. We refer to this error type as Scrambled Translation problem. We observe that UNMT models which use word shuffle noise (as in case of Undreamt) can generate correct words and but fail to stitch them together to form phrases. As a result and words of the translated sentence look scrambled and resulting in decreased BLEU. We hypothesise that the reason behind scrambled translation problem is ’shuffling noise’ which is introduced in every input sentence as a denoising strategy. To test our hypothesis and we experiment by retraining UNMT models with a simple retraining strategy. We stop the training of the Denoising UNMT model after a pre-decided number of iterations and resume the training for the remaining iterations- which number is also pre-decided- using original sentence as input without adding any noise. Our proposed solution achieves significant performance improvement UNMT models that train conventionally. We demonstrate these performance gains on four language pairs and viz. and English-French and English-German and English-Spanish and Hindi-Punjabi. Our qualitative and quantitative analysis shows that the retraining strategy helps achieve better alignment as observed by attention heatmap and better phrasal translation and leading to statistically significant improvement in BLEU scores.

Existing supervised solutions for Named Entity Recognition (NER) typically rely on a large annotated corpus. Collecting large amounts of NER annotated corpus is time-consuming and requires considerable human effort. However, collecting small amounts of annotated corpus for any language is feasible, but the performance degrades due to data sparsity. We address the data sparsity by borrowing features from the data of a closely related language. We use hierarchical neural networks to train a supervised NER system. The feature borrowing from a closely related language happens via the shared layers of the network. The neural network is trained on the combined dataset of the low-resource language and a closely related language, also termed Multilingual Learning. Unlike existing systems, we share all layers of the network between the two languages. We apply multilingual learning for NER in Indian languages and empirically show the benefits over a monolingual deep learning system and a traditional machine-learning system with some feature engineering. Using multilingual learning, we show that the low-resource language NER performance increases mainly due to (1) increased named entity vocabulary, (2) cross-lingual subword features, and (3) multilingual learning playing the role of regularization.

Sudha Bhingardive, Dhirendra Singh, Rudramurthy V, Hanumant Redkar, Pushpak Bhattacharyya. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.