Related papers: Low-Resource Corpus Filtering using Multilingual S…

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…

Due to the scarcity of part-of-speech annotated data, existing studies on low-resource languages typically adopt unsupervised approaches for POS tagging. Among these, POS tag projection with word alignment method transfers POS tags from a…

Multilingual information retrieval (IR) is challenging since annotated training data is costly to obtain in many languages. We present an effective method to train multilingual IR systems when only English IR training data and some parallel…

Quality Estimation (QE) is the task of evaluating the quality of a translation when reference translation is not available. The goal of QE aligns with the task of corpus filtering, where we assign the quality score to the sentence pairs…

The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been…

Large-scale cross-lingual language models (LM), such as mBERT, Unicoder and XLM, have achieved great success in cross-lingual representation learning. However, when applied to zero-shot cross-lingual transfer tasks, most existing methods…

End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural…

Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it…

Morphological modeling in neural machine translation (NMT) is a promising approach to achieving open-vocabulary machine translation for morphologically-rich languages. However, existing methods such as sub-word tokenization and…

There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter…

Quality Estimation (QE) models have the potential to change how we evaluate and maybe even train machine translation models. However, these models still lack the robustness to achieve general adoption. We show that State-of-the-art QE…

Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…

We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of…

This paper presents a multi-way parallel English-Tamil-Sinhala corpus annotated with Named Entities (NEs), where Sinhala and Tamil are low-resource languages. Using pre-trained multilingual Language Models (mLMs), we establish new benchmark…

There have been some works that learn a lexicon together with the corpus to improve the word embeddings. However, they either model the lexicon separately but update the neural networks for both the corpus and the lexicon by the same…

We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. Unlike previous works on speech representation learning, which learns multilingual contextual speech embedding…

The availability of parallel sentence simplification (SS) is scarce for neural SS modelings. We propose an unsupervised method to build SS corpora from large-scale bilingual translation corpora, alleviating the need for SS supervised…

Neural Machine Translation (NMT) is an ongoing technique for Machine Translation (MT) using enormous artificial neural network. It has exhibited promising outcomes and has shown incredible potential in solving challenging machine…

In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN)…

Mining high-quality bitexts for low-resource languages is challenging. This paper shows that sentence representation of language models fine-tuned with multiple negatives ranking loss, a contrastive objective, helps retrieve clean bitexts.…