相关论文: A Data Selection Approach for Enhancing Low Resour…

When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…

Transfer learning for extremely low resource languages is a challenging task as there is no large scale monolingual corpora for pre training or sufficient annotated data for fine tuning. We follow the work of MetaXL which suggests using…

Plagiarism involves using another person's work or concepts without proper attribution, presenting them as original creations. With the growing amount of data communicated in regional languages such as Marathi -- one of India's regional…

Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level…

Evaluating machine translation (MT) for low-resource languages poses a persistent challenge, primarily due to the limited availability of high quality reference translations. This issue is further exacerbated in languages with multiple…

We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was…

Neural Machine translation is a challenging task due to the inherent complex nature and the fluidity that natural languages bring. Nonetheless, in recent years, it has achieved state-of-the-art performance in several language pairs.…

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

With the surge in digital content in low-resource languages, there is an escalating demand for advanced Natural Language Processing (NLP) techniques tailored to these languages. BERT (Bidirectional Encoder Representations from…

Unlike mainstream languages (such as English and French), low-resource languages often suffer from a lack of expert-annotated corpora and benchmark resources that make it hard to apply state-of-the-art techniques directly. In this paper, we…

Code-switching, or alternating between languages within a single conversation, presents challenges for multilingual language models on NLP tasks. This research investigates if pre-training Multilingual BERT (mBERT) on code-switched datasets…

Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining data sizes, there is a…

We present research towards bridging the language gap between migrant workers in Qatar and medical staff. In particular, we present the first steps towards the development of a real-world Hindi-English machine translation system for…

Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods…

In this paper, we propose a novel approach for generating document embeddings using a combination of Sentence-BERT (SBERT) and RoBERTa, two state-of-the-art natural language processing models. Our approach treats sentences as tokens and…

The BERT family of neural language models have become highly popular due to their ability to provide sequences of text with rich context-sensitive token encodings which are able to generalise well to many NLP tasks. We introduce gaBERT, a…

The term "Code Mixed" refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount of adaptation as time goes on. It is critical to detect…

While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate…

Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-resource languages.…