Related papers: MT6: Multilingual Pretrained Text-to-Text Transfor…
Recent works in end-to-end speech-to-text translation (ST) have proposed multi-tasking methods with soft parameter sharing which leverage machine translation (MT) data via secondary encoders that map text inputs to an eventual cross-modal…
Machine translation (MT) post-editing and research data collection often rely on inefficient, disconnected workflows. We introduce TranslationCorrect, an integrated framework designed to streamline these tasks. TranslationCorrect combines…
This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual information when text inputs are complete. Instead, we attribute…
Targeted evaluations have found that machine translation systems often output incorrect gender, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social…
Graph-to-text generation aims to generate fluent texts from graph-based data. In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the impact of different task-adaptive pretraining strategies for…
Transformer has been successfully applied to many natural language processing tasks. However, for textual sequence matching, simple matching between the representation of a pair of sequences might bring in unnecessary noise. In this paper,…
Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory…
This work introduces a machine translation task where the output is aimed at audiences of different levels of target language proficiency. We collect a high quality dataset of news articles available in English and Spanish, written for…
Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly…
In this paper, we revisit math word problems~(MWPs) from the cross-lingual and multilingual perspective. We construct our MWP solvers over pretrained multilingual language models using sequence-to-sequence model with copy mechanism. We…
While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks. Multi-token prediction (MTP) has recently emerged as a promising alternative,…
Multilingual semantic parsing is a cost-effective method that allows a single model to understand different languages. However, researchers face a great imbalance of availability of training data, with English being resource rich, and other…
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation…
Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited…
Sequence to sequence learning has recently emerged as a new paradigm in supervised learning. To date, most of its applications focused on only one task and not much work explored this framework for multiple tasks. This paper examines three…
This paper explores the effectiveness of model-generated signals in improving zero-shot generalization of text-to-text Transformers such as T5. We study various designs to pretrain T5 using an auxiliary model to construct more challenging…
We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word…
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient approaches have ignored synthesizing emotional aspects of…
Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…
In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…