1.6k citations · 3.7k across the 27 of their papers we have counts for
32 papers
Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation
Kartik Kartik, Sanjana Soni, Anoop Kunchukuttan +2
The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This…
DANSK and DaCy 2.6.0: Domain Generalization of Danish Named Entity Recognition
Kenneth Enevoldsen, Emil Trenckner Jessen, Rebekah Baglini
Named entity recognition is one of the cornerstones of Danish NLP, essential for language technology applications within both industry and research. However, Danish NER is inhibite…
Toward Joint Language Modeling for Speech Units and Text
Ju-Chieh Chou, Chung-Ming Chien, Wei-Ning Hsu +5
Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of lan…
Scaling Speech Technology to 1,000+ Languages
Vineel Pratap, Andros Tjandra, Bowen Shi +13
Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to ab…
Textually Pretrained Speech Language Models
Michael Hassid, Tal Remez, Tu Anh Nguyen +9
Speech language models (SpeechLMs) process and generate acoustic data only, without textual supervision. In this work, we propose TWIST, a method for training SpeechLMs using a war…
Scaling Laws for Generative Mixed-Modal Language Models
Armen Aghajanyan, Lili Yu, Alexis Conneau +7
Generative language models define distributions over sequences of tokens that can represent essentially any combination of data modalities (e.g., any permutation of image tokens fr…
FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
Alexis Conneau, Min Ma, Simran Khanuja +6
We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of…
XTREME-S: Evaluating Cross-lingual Speech Representations
Alexis Conneau, Ankur Bapna, Yu Zhang +16
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classif…
Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
Ye Jia, Yifan Ding, Ankur Bapna +4
End-to-end speech-to-speech translation (S2ST) without relying on intermediate text representations is a rapidly emerging frontier of research. Recent works have demonstrated that…
mSLAM: Massively multilingual joint pre-training for speech and text
Ankur Bapna, Colin Cherry, Yu Zhang +6
We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unla…
XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Arun Babu, Changhan Wang, Andros Tjandra +10
This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a mill…
SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
Ankur Bapna, Yu-an Chung, Nan Wu +7
Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been h…
Larger-Scale Transformers for Multilingual Masked Language Modeling
Naman Goyal, Jingfei Du, Myle Ott +2
Recent work has demonstrated the effectiveness of cross-lingual language model pretraining for cross-lingual understanding. In this study, we present the results of two larger mult…
Unsupervised Speech Recognition
Alexei Baevski, Wei-Ning Hsu, Alexis Conneau +1
Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages…
Large-Scale Self- and Semi-Supervised Learning for Speech Translation
Changhan Wang, Anne Wu, Juan Pino +3
In this paper, we improve speech translation (ST) through effectively leveraging large quantities of unlabeled speech and text data in different and complementary ways. We explore…
Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning
Beliz Gunel, Jingfei Du, Alexis Conneau +1
State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on…
Self-training and Pre-training are Complementary for Speech Recognition
Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko +5
Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data. However, it is not clear whether they l…
Self-training Improves Pre-training for Natural Language Understanding
Jingfei Du, Edouard Grave, Beliz Gunel +5
Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through…
Unsupervised Cross-lingual Representation Learning for Speech Recognition
Alexis Conneau, Alexei Baevski, Ronan Collobert +2
This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec…
CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data
Guillaume Wenzek, Marie-Anne Lachaux, Alexis Conneau +4
Pre-training text representations have led to significant improvements in many areas of natural language processing. The quality of these models benefits greatly from the size of t…
Unsupervised Cross-lingual Representation Learning at Scale
Alexis Conneau, Kartikay Khandelwal, Naman Goyal +7
This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transfor…
Emerging Cross-lingual Structure in Pretrained Language Models
Shijie Wu, Alexis Conneau, Haoran Li +2
We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of sev…
Cross-lingual Language Model Pretraining
Guillaume Lample, Alexis Conneau
Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages an…
XNLI: Evaluating Cross-lingual Sentence Representations
Alexis Conneau, Guillaume Lample, Ruty Rinott +4
State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a si…