Related papers: Triangular Transfer: Freezing the Pivot for Triang…
Cross-lingual dependency parsing involves transferring syntactic knowledge from one language to another. It is a crucial component for inducing dependency parsers in low-resource scenarios where no training data for a language exists. Using…
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…
Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it…
Developing a unified multilingual model has long been a pursuit for machine translation. However, existing approaches suffer from performance degradation -- a single multilingual model is inferior to separately trained bilingual ones on…
A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers…
Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one step closer to reaching this goal, it is becoming evident…
Recent progress in neural machine translation is directed towards larger neural networks trained on an increasing amount of hardware resources. As a result, NMT models are costly to train, both financially, due to the electricity and…
This work focuses on comparing different solutions for machine translation on low resource language pairs, namely, with zero-shot transfer learning and unsupervised machine translation. We discuss how the data size affects the performance…
Transfer learning is a powerful tool enabling model training with limited amounts of data. This technique is particularly useful in real-world problems where data availability is often a serious limitation. The simplest transfer learning…
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…
Machine translation is the discipline concerned with developing automated tools for translating from one human language to another. Statistical machine translation (SMT) is the dominant paradigm in this field. In SMT, translations are…
Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…
An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or…
This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual information to…
We present the second ever evaluated Arabic dialect-to-dialect machine translation effort, and the first to leverage external resources beyond a small parallel corpus. The subject has not previously received serious attention due to lack of…
As an effective alternative to the direct fine-tuning on target tasks in specific languages, cross-lingual transfer addresses the challenges of limited training data by decoupling ''task ability'' and ''language ability'' by fine-tuning on…
Machine translation is one of the applications of natural language processing which has been explored in different languages. Recently researchers started paying attention towards machine translation for resource-poor languages and closely…
Improving neural machine translation (NMT) models using the back-translations of the monolingual target data (synthetic parallel data) is currently the state-of-the-art approach for training improved translation systems. The quality of the…
While prior work has established that the use of parallel data is conducive for cross-lingual learning, it is unclear if the improvements come from the data itself, or if it is the modeling of parallel interactions that matters. Exploring…
Although the parallel corpus has an irreplaceable role in machine translation, its scale and coverage is still beyond the actual needs. Non-parallel corpus resources on the web have an inestimable potential value in machine translation and…