3.7k citations
- Meta (United States)US158 papers
- New York UniversityUS11 papers
- Carnegie Mellon UniversityUS10 papers
- University of California, BerkeleyUS8 papers
- Stanford UniversityUS7 papers
- University of WashingtonUS7 papers
- Cornell UniversityUS6 papers
- University of OxfordGB6 papers
- Massachusetts Institute of TechnologyUS5 papers
- Meta (Israel)IL5 papers
- ETH ZurichCH4 papers
- Google (United States)US4 papers
9 papers · 2 filters
CoVoST 2 and Massively Multilingual Speech-to-Text Translation
Changhan Wang, Anne Wu, Juan Pino
Speech translation has recently become an increasingly popular topic of research, partly due to the development of benchmark datasets. Nevertheless, current datasets cover a limite…
What they do when in doubt: a study of inductive biases in seq2seq learners
Eugene Kharitonov, Rahma Chaabouni
Sequence-to-sequence (seq2seq) learners are widely used, but we still have only limited knowledge about what inductive biases shape the way they generalize. We address that by inve…
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation
Jungo Kasai, Nikolaos Pappas, Hao Peng +2
Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine trans…
Cross-lingual Retrieval for Iterative Self-Supervised Training
Chau Tran, Yuqing Tang, Xian Li +1
Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be furt…
Self-Training for End-to-End Speech Translation
Juan Pino, Qiantong Xu, Xutai Ma +2
One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech transl…
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Patrick Lewis, Ethan Perez, Aleksandra Piktus +9
Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. Howe…