Related papers: Automatic Construction of Discourse Corpora for Di…

Multilingual pre-training significantly improves many multilingual NLP tasks, including machine translation. Most existing methods are based on some variants of masked language modeling and text-denoising objectives on monolingual data.…

The availability of parallel texts is crucial to the performance of machine translation models. However, most of the world's languages face the predominant challenge of data scarcity. In this paper, we propose strategies to synthesize…

In an attempt to improve overall translation quality, there has been an increasing focus on integrating more linguistic elements into Machine Translation (MT). While significant progress has been achieved, especially recently with neural…

Document-level machine translation conditions on surrounding sentences to produce coherent translations. There has been much recent work in this area with the introduction of custom model architectures and decoding algorithms. This paper…

Speech-to-speech translation systems today do not adequately support use for dialog purposes. In particular, nuances of speaker intent and stance can be lost due to improper prosody transfer. We present an exploration of what needs to be…

This article presents a hybrid methodology for building a multilingual corpus designed to support the study of emerging concepts in the humanities and social sciences (HSS), illustrated here through the case of ``non-technological…

Parallel corpus is a critical resource in machine learning-based translation. The task of collecting, extracting, and aligning texts in order to build an acceptable corpus for doing the translation is very tedious most especially for…

This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which…

When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…

We introduce a new automatic evaluation method for speaker similarity assessment, that is consistent with human perceptual scores. Modern neural text-to-speech models require a vast amount of clean training data, which is why many solutions…

Recently, the utilization of extensive open-sourced text data has significantly advanced the performance of text-based large language models (LLMs). However, the use of in-the-wild large-scale speech data in the speech technology community…

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…

Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potential mismatch between required capabilities and training…

Existing dialog systems are all monolingual, where features shared among different languages are rarely explored. In this paper, we introduce a novel multilingual dialogue system. Specifically, we augment the sequence to sequence framework…

We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text from a target language. As opposed to…

Black-box machine translation systems have proven incredibly useful for a variety of applications yet by design are hard to adapt, tune to a specific domain, or build on top of. In this work, we introduce a method to improve such systems…

Text simplification is an intralingual translation task in which documents, or sentences of a complex source text are simplified for a target audience. The success of automatic text simplification systems is highly dependent on the quality…

Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate…

As large dialogue models become commonplace in practice, the problems surrounding high compute requirements for training, inference and larger memory footprint still persists. In this work, we present AUTODIAL, a multi-task dialogue model…

We propose a Bayesian model of unsupervised semantic role induction in multiple languages, and use it to explore the usefulness of parallel corpora for this task. Our joint Bayesian model consists of individual models for each language plus…