Related papers: MT6: Multilingual Pretrained Text-to-Text Transfor…
A good evaluation framework should evaluate multimodal machine translation (MMT) models by measuring 1) their use of visual information to aid in the translation task and 2) their ability to translate complex sentences such as done for…
Multilingual pretrained models are effective for machine translation and cross-lingual processing because they contain multiple languages in one model. However, they are pretrained after their tokenizers are fixed; therefore it is difficult…
Translate-test is a popular technique to improve the performance of multilingual language models. This approach works by translating the input into English using an external machine translation system, and running inference over the…
In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides,…
Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…
English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). The same cannot be said for most other languages, as leading LLMs still underperform for non-English languages, likely due to a…
Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an…
How to achieve better end-to-end speech translation (ST) by leveraging (text) machine translation (MT) data? Among various existing techniques, multi-task learning is one of the effective ways to share knowledge between ST and MT in which…
We present a framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework,…
Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…
This paper proposes a textless training method for many-to-many multilingual speech-to-speech translation that can also benefit the transfer of pre-trained knowledge to text-based systems, text-to-speech synthesis and text-to-speech…
Neural Chat Translation (NCT) aims to translate conversational text into different languages. Existing methods mainly focus on modeling the bilingual dialogue characteristics (e.g., coherence) to improve chat translation via multi-task…
Machine translation (MT) involving Indigenous languages, including those possibly endangered, is challenging due to lack of sufficient parallel data. We describe an approach exploiting bilingual and multilingual pretrained MT models in a…
We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker variant effectively using transcripts from a single speaker. ParrotTTS adapts to…
Multilingual pretrained language models (such as multilingual BERT) have achieved impressive results for cross-lingual transfer. However, due to the constant model capacity, multilingual pre-training usually lags behind the monolingual…
The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task.…
This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…
What can pre-trained multilingual sequence-to-sequence models like mBART contribute to translating low-resource languages? We conduct a thorough empirical experiment in 10 languages to ascertain this, considering five factors: (1) the…
Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the number of tasks during pre-training. Towards this goal, this…
Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is under-explored that…