Neural machine translation: A review

F Stahlberg - Journal of Artificial Intelligence Research, 2020‏ - jair.org
The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

Generative Artificial Intelligence for Software Engineering--A Research Agenda

A Nguyen-Duc, B Cabrero-Daniel, A Przybylek… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Generative Artificial Intelligence (GenAI) tools have become increasingly prevalent in
software development, offering assistance to various managerial and technical project …

Starcoder: may the source be with you!

R Li, LB Allal, Y Zi, N Muennighoff, D Kocetkov… - arxiv preprint arxiv …, 2023‏ - arxiv.org
The BigCode community, an open-scientific collaboration working on the responsible
development of Large Language Models for Code (Code LLMs), introduces StarCoder and …

Unsupervised cross-lingual representation learning for speech recognition

A Conneau, A Baevski, R Collobert… - arxiv preprint arxiv …, 2020‏ - arxiv.org
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 …

vq-wav2vec: Self-supervised learning of discrete speech representations

A Baevski, S Schneider, M Auli - arxiv preprint arxiv:1910.05453, 2019‏ - arxiv.org
We propose vq-wav2vec to learn discrete representations of audio segments through a
wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel …

wav2vec: Unsupervised pre-training for speech recognition

S Schneider, A Baevski, R Collobert, M Auli - arxiv preprint arxiv …, 2019‏ - arxiv.org
We explore unsupervised pre-training for speech recognition by learning representations of
raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting …

Large-scale evidence for logarithmic effects of word predictability on reading time

C Shain, C Meister, T Pimentel… - Proceedings of the …, 2024‏ - National Acad Sciences
During real-time language comprehension, our minds rapidly decode complex meanings
from sequences of words. The difficulty of doing so is known to be related to words' …

BLiMP: The benchmark of linguistic minimal pairs for English

A Warstadt, A Parrish, H Liu, A Mohananey… - Transactions of the …, 2020‏ - direct.mit.edu
Abstract We introduce The Benchmark of Linguistic Minimal Pairs (BLiMP), a challenge set
for evaluating the linguistic knowledge of language models (LMs) on major grammatical …

Learning to ask: Neural question generation for reading comprehension

X Du, J Shao, C Cardie - arxiv preprint arxiv:1705.00106, 2017‏ - arxiv.org
We study automatic question generation for sentences from text passages in reading
comprehension. We introduce an attention-based sequence learning model for the task and …

[HTML][HTML] Deep speech 2: End-to-end speech recognition in english and mandarin

D Amodei, S Ananthanarayanan… - International …, 2016‏ - proceedings.mlr.press
We show that an end-to-end deep learning approach can be used to recognize either
English or Mandarin Chinese speech–two vastly different languages. Because it replaces …