Related papers: End-to-end Training and Decoding for Pivot-based C…
Recent fast style transfer methods use a pre-trained convolutional neural network as a feature encoder and a perceptual loss network. Although the pre-trained network is used to generate responses of receptive fields effective for…
Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…
We demonstrate the potential of few-shot translation systems, trained with unpaired language data, for both high and low-resource language pairs. We show that with only 5 examples of high-quality translation data shown at inference, a…
A cascade-based speech-to-speech translation has been considered a benchmark for a very long time, but it is plagued by many issues, like the time taken to translate a speech from one language to another and compound errors. These issues…
Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree structures by training…
We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series…
This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source…
We present eCat, a novel end-to-end multispeaker model capable of: a) generating long-context speech with expressive and contextually appropriate prosody, and b) performing fine-grained prosody transfer between any pair of seen speakers.…
We propose a) a Language Agnostic end-to-end Speech Translation model (LAST), and b) a data augmentation strategy to increase code-switching (CS) performance. With increasing globalization, multiple languages are increasingly used…
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:…
This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer…
We present an interactive machine translation (MT) system designed for users who are not proficient in the target language. It aims to improve trustworthiness and explainability by identifying potentially mistranslated words and allowing…
In this paper, we offer a preliminary investigation into the task of in-image machine translation: transforming an image containing text in one language into an image containing the same text in another language. We propose an end-to-end…
Beam search is a desirable choice of test-time decoding algorithm for neural sequence models because it potentially avoids search errors made by simpler greedy methods. However, typical cross entropy training procedures for these models do…
Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…
In this paper, we propose an effective way for biasing the attention mechanism of a sequence-to-sequence neural machine translation (NMT) model towards the well-studied statistical word alignment models. We show that our novel guided…
It has been proved that large scale realistic Knowledge Based Machine Translation applications require acquisition of huge knowledge about language and about the world. This knowledge is encoded in computational grammars, lexicons and…
Voice conversion (VC) using sequence-to-sequence learning of context posterior probabilities is proposed. Conventional VC using shared context posterior probabilities predicts target speech parameters from the context posterior…
Neural topic models can augment or replace bag-of-words inputs with the learned representations of deep pre-trained transformer-based word prediction models. One added benefit when using representations from multilingual models is that they…
In end-to-end speech translation, acoustic representations learned by the encoder are usually fixed and static, from the perspective of the decoder, which is not desirable for dealing with the cross-modal and cross-lingual challenge in…