Related papers: Multilingual Code-Switching for Zero-Shot Cross-Li…

Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for…

Spoken dialog systems need to be able to handle both multiple languages and multilinguality inside a conversation (\textit{e.g} in case of code-switching). In this work, we introduce new pretraining losses tailored to learn multilingual…

Natural Language Understanding (NLU) is a core component of dialog systems. It typically involves two tasks - intent classification (IC) and slot labeling (SL), which are then followed by a dialogue management (DM) component. Such NLU…

This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah's Ark Lab. We use a unified transformer architecture for our MultiST model, so that the data from different…

To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018). However, it is…

Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bilingual systems.…

Using task-specific pre-training and leveraging cross-lingual transfer are two of the most popular ways to handle code-switched data. In this paper, we aim to compare the effects of both for the task of sentiment analysis. We work with two…

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…

Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during…

Pretrained multilingual models are able to perform cross-lingual transfer in a zero-shot setting, even for languages unseen during pretraining. However, prior work evaluating performance on unseen languages has largely been limited to…

There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a…

Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be able to jointly represent many different languages, their training data is dominated by English, potentially limiting…

Adapter modules, additional trainable parameters that enable efficient fine-tuning of pretrained transformers, have recently been used for language specialization of multilingual transformers, improving downstream zero-shot cross-lingual…

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…

Both grammatical error correction and text style transfer can be viewed as monolingual sequence-to-sequence transformation tasks, but the scarcity of directly annotated data for either task makes them unfeasible for most languages. We…

Recent work in cross-lingual semantic parsing has successfully applied machine translation to localize parsers to new languages. However, these advances assume access to high-quality machine translation systems and word alignment tools. We…

Languages usually switch within a multilingual speech signal, especially in a bilingual society. This phenomenon is referred to as code-switching (CS), making automatic speech recognition (ASR) challenging under a multilingual scenario. We…

With the recent explosion in popularity of voice assistant devices, there is a growing interest in making them available to user populations in additional countries and languages. However, to provide the highest accuracy and best…

Low-resource African languages have not fully benefited from the progress in neural machine translation because of a lack of data. Motivated by this challenge we compare zero-shot learning, transfer learning and multilingual learning on…

In this work, we seek to build effective code-switched (CS) automatic speech recognition systems (ASR) under the zero-shot setting where no transcribed CS speech data is available for training. Previously proposed frameworks which…