Search Results for author: Laurent Sartran

Found 9 papers, 2 papers with code

SynJax: Structured Probability Distributions for JAX

3 code implementations7 Aug 2023 Miloš Stanojević, Laurent Sartran

The development of deep learning software libraries enabled significant progress in the field by allowing users to focus on modeling, while letting the library to take care of the tedious and time-consuming task of optimizing execution for modern hardware accelerators.

Measuring Progress in Fine-grained Vision-and-Language Understanding

2 code implementations12 May 2023 Emanuele Bugliarello, Laurent Sartran, Aishwarya Agrawal, Lisa Anne Hendricks, Aida Nematzadeh

While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding, such as the ability to recognise relationships, verbs, and numbers in images.

Visual Reasoning

Continuous diffusion for categorical data

no code implementations28 Nov 2022 Sander Dieleman, Laurent Sartran, Arman Roshannai, Nikolay Savinov, Yaroslav Ganin, Pierre H. Richemond, Arnaud Doucet, Robin Strudel, Chris Dyer, Conor Durkan, Curtis Hawthorne, Rémi Leblond, Will Grathwohl, Jonas Adler

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement.

Language Modelling

Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale

no code implementations1 Mar 2022 Laurent Sartran, Samuel Barrett, Adhiguna Kuncoro, Miloš Stanojević, Phil Blunsom, Chris Dyer

We find that TGs outperform various strong baselines on sentence-level language modeling perplexity, as well as on multiple syntax-sensitive language modeling evaluation metrics.

Inductive Bias Language Modelling +1

Enabling arbitrary translation objectives with Adaptive Tree Search

no code implementations ICLR 2022 Wang Ling, Wojciech Stokowiec, Domenic Donato, Laurent Sartran, Lei Yu, Austin Matthews, Chris Dyer

When applied to autoregressive models, our algorithm has different biases than beam search has, which enables a new analysis of the role of decoding bias in autoregressive models.

Translation

Rapid Task-Solving in Novel Environments

no code implementations ICLR 2021 Sam Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matt Botvinick, David Raposo

We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience.

Navigate

Better Document-Level Machine Translation with Bayes' Rule

no code implementations TACL 2020 Lei Yu, Laurent Sartran, Wojciech Stokowiec, Wang Ling, Lingpeng Kong, Phil Blunsom, Chris Dyer

We show that Bayes' rule provides an effective mechanism for creating document translation models that can be learned from only parallel sentences and monolingual documents---a compelling benefit as parallel documents are not always available.

Document Level Machine Translation Document Translation +4

Putting Machine Translation in Context with the Noisy Channel Model

no code implementations25 Sep 2019 Lei Yu, Laurent Sartran, Wojciech Stokowiec, Wang Ling, Lingpeng Kong, Phil Blunsom, Chris Dyer

We show that Bayes' rule provides a compelling mechanism for controlling unconditional document language models, using the long-standing challenge of effectively leveraging document context in machine translation.

Document Translation Language Modelling +3

Cannot find the paper you are looking for? You can Submit a new open access paper.