Related papers: Code Switching Language Model Using Monolingual Tr…
Code-switching is a pervasive linguistic phenomenon in global communication, yet modern information retrieval systems remain predominantly designed for, and evaluated within, monolingual contexts. To bridge this critical disconnect, we…
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without…
Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…
In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech. We focus on the recognition of Frisian-Dutch radio…
Many-to-one neural machine translation systems improve over one-to-one systems when training data is scarce. In this paper, we design and test a novel algorithm for selecting the language of minibatches when training such systems. The…
Dual-encoder structure successfully utilizes two language-specific encoders (LSEs) for code-switching speech recognition. Because LSEs are initialized by two pre-trained language-specific models (LSMs), the dual-encoder structure can…
Multilingual large language models achieve impressive cross-lingual performance despite largely monolingual pretraining. While bilingual data in pretraining corpora is widely believed to enable these abilities, details of its contributions…
Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have…
Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining. We…
Neural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, is used in these two paradigms.…
While monolingual data has been shown to be useful in improving bilingual neural machine translation (NMT), effectively and efficiently leveraging monolingual data for Multilingual NMT (MNMT) systems is a less explored area. In this work,…
Code-switching is a common phenomenon among people with diverse lingual background and is widely used on the internet for communication purposes. In this paper, we present a Recurrent Neural Network combined with the Attention Model for…
Cross-lingual named entity recognition (NER) suffers from data scarcity in the target languages, especially under zero-shot settings. Existing translate-train or knowledge distillation methods attempt to bridge the language gap, but often…
While recent benchmarks have spurred a lot of new work on improving the generalization of pretrained multilingual language models on multilingual tasks, techniques to improve code-switched natural language understanding tasks have been far…
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…
A popular approach to creating a zero-shot cross-language retrieval model is to substitute a monolingual pretrained language model in the retrieval model with a multilingual pretrained language model such as Multilingual BERT. This…
Building cross-lingual voice conversion (VC) systems for multiple speakers and multiple languages has been a challenging task for a long time. This paper describes a parallel non-autoregressive network to achieve bilingual and code-switched…
We find that existing language modeling datasets contain many near-duplicate examples and long repetitive substrings. As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the…
Despite the known limitations, most machine translation systems today still operate on the sentence-level. One reason for this is, that most parallel training data is only sentence-level aligned, without document-level meta information…
The use of multilingualism in the new generation is widespread in the form of code-mixed data on social media, and therefore a robust translation system is required for catering to the monolingual users, as well as for easier comprehension…