Related papers: Enhancing LLM Language Adaption through Cross-ling…

Large Language Models (LLMs) have demonstrated exceptional natural language understanding abilities and have excelled in a variety of natural language processing (NLP)tasks in recent years. Despite the fact that most LLMs are trained…

Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…

Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential…

Code translation aims to convert a program from one programming language (PL) to another. This long-standing software engineering task is crucial for modernizing legacy systems, ensuring cross-platform compatibility, enhancing performance,…

Although LLMs have attained significant success in high-resource languages, their capacity in low-resource linguistic environments like Kannada and Arabic is not yet fully understood. This work benchmarking the performance of multilingual…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monolingual, trained exclusively on a large amount of labeled data.…

The capacity and effectiveness of pre-trained multilingual models (MLMs) for zero-shot cross-lingual transfer is well established. However, phenomena of positive or negative transfer, and the effect of language choice still need to be fully…

This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages,…

Cross-lingual Machine Reading Comprehension (xMRC) is challenging due to the lack of training data in low-resource languages. The recent approaches use training data only in a resource-rich language like English to fine-tune large-scale…

Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…

Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in…

Pretrained contextualized representations offer great success for many downstream tasks, including document ranking. The multilingual versions of such pretrained representations provide a possibility of jointly learning many languages with…

Multilingual large language models (MLLMs) are jointly trained on data from many different languages such that representation of individual languages can benefit from other languages' data. Impressive performance on zero-shot cross-lingual…

Recently, multilingual BERT works remarkably well on cross-lingual transfer tasks, superior to static non-contextualized word embeddings. In this work, we provide an in-depth experimental study to supplement the existing literature of…

This paper discusses the methods that we used for our submissions to the WMT 2023 Terminology Shared Task for German-to-English (DE-EN), English-to-Czech (EN-CS), and Chinese-to-English (ZH-EN) language pairs. The task aims to advance…

With the increasing accessibility and utilization of multilingual documents, Cross-Lingual Information Retrieval (CLIR) has emerged as an important research area. Conventionally, CLIR tasks have been conducted under settings where the…

While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…

Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the…

Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…