Related papers: Multitask Finetuning for Improving Neural Machine …

In this study, we present an analysis regarding the performance of the state-of-art Phrase-based Statistical Machine Translation (SMT) on multiple Indian languages. We report baseline systems on several language pairs. The motivation of…

In this paper, we propose two novel methods for domain adaptation for the attention-only neural machine translation (NMT) model, i.e., the Transformer. Our methods focus on training a single translation model for multiple domains by either…

Machine Translation (MT) is a zone of concentrate in Natural Language processing which manages the programmed interpretation of human language, starting with one language then onto the next by the PC. Having a rich research history…

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of…

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

Machine Translation (MT) system generally aims at automatic representation of source language into target language retaining the originality of context using various Natural Language Processing (NLP) techniques. Among various NLP methods,…

We propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning. Pre-finetuning is massively multi-task learning (around 50 datasets, over 4.8 million total labeled examples), and is…

We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages we consider. Besides,…

An all-too-present bottleneck for text classification model development is the need to annotate training data and this need is multiplied for multilingual classifiers. Fortunately, contemporary machine translation models are both easily…

Neural Machine Translation (NMT) models are typically trained on datasets with limited exposure to Scientific, Technical and Educational domains. Translation models thus, in general, struggle with tasks that involve scientific understanding…

Neural Machine Translation (NMT) is a predominant machine translation technology nowadays because of its end-to-end trainable flexibility. However, NMT still struggles to translate properly in low-resource settings specifically on distant…

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…

We present a simple, yet effective, Neural Machine Translation system for Indian languages. We demonstrate the feasibility for multiple language pairs, and establish a strong baseline for further research.

This paper describes CIC NLP's submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas. We present the system descriptions for three methods. We used two multilingual models,…

Data quality and its effective selection are fundamental to improving the performance of machine translation models, serving as cornerstones for achieving robust and reliable translation systems. This paper presents a data selection…

We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach…

Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that…

Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…

In this paper we explore various parameter settings of the state-of-art Statistical Machine Translation system to improve the quality of the translation for a `distant' language pair like English-Hindi. We proposed new techniques for…

When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…