Search Results for author: Marco Baroni

Found 86 papers, 27 papers with code

Cross-Domain Image Captioning with Discriminative Finetuning

1 code implementation CVPR 2023 Roberto Dessì, Michele Bevilacqua, Eleonora Gualdoni, Nathanael Carraz Rakotonirina, Francesca Franzon, Marco Baroni

However, when the model is used without further tuning to generate captions for out-of-domain datasets, our discriminatively-finetuned captioner generates descriptions that resemble human references more than those produced by the same captioner without finetuning.

Descriptive Image Captioning

Can discrete information extraction prompts generalize across language models?

1 code implementation20 Feb 2023 Nathanaël Carraz Rakotonirina, Roberto Dessì, Fabio Petroni, Sebastian Riedel, Marco Baroni

We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information.

Language Modelling slot-filling +1

Referential communication in heterogeneous communities of pre-trained visual deep networks

1 code implementation4 Feb 2023 Matéo Mahaut, Francesca Franzon, Roberto Dessì, Marco Baroni

As a first step in this direction, we systematically explore the task of \textit{referential communication} in a community of heterogeneous state-of-the-art pre-trained visual networks, showing that they can develop, in a self-supervised way, a shared protocol to refer to a target object among a set of candidates.

Self-Driving Cars

Communication breakdown: On the low mutual intelligibility between human and neural captioning

1 code implementation20 Oct 2022 Roberto Dessì, Eleonora Gualdoni, Francesca Franzon, Gemma Boleda, Marco Baroni

We compare the 0-shot performance of a neural caption-based image retriever when given as input either human-produced captions or captions generated by a neural captioner.


How BPE Affects Memorization in Transformers

no code implementations6 Oct 2021 Eugene Kharitonov, Marco Baroni, Dieuwke Hupkes

In this work, we demonstrate that the size of the subword vocabulary learned by Byte-Pair Encoding (BPE) greatly affects both ability and tendency of standard Transformer models to memorize training data, even when we control for the number of learned parameters.


On the proper role of linguistically-oriented deep net analysis in linguistic theorizing

no code implementations16 Jun 2021 Marco Baroni

A lively research field has recently emerged that uses experimental methods to probe the linguistic behavior of modern deep networks.

Interpretable agent communication from scratch (with a generic visual processor emerging on the side)

1 code implementation NeurIPS 2021 Roberto Dessì, Eugene Kharitonov, Marco Baroni

As deep networks begin to be deployed as autonomous agents, the issue of how they can communicate with each other becomes important.

Self-Supervised Learning

Mechanisms for Handling Nested Dependencies in Neural-Network Language Models and Humans

no code implementations19 Jun 2020 Yair Lakretz, Dieuwke Hupkes, Alessandra Vergallito, Marco Marelli, Marco Baroni, Stanislas Dehaene

We studied whether a modern artificial neural network trained with "deep learning" methods mimics a central aspect of human sentence processing, namely the storing of grammatical number and gender information in working memory and its use in long-distance agreement (e. g., capturing the correct number agreement between subject and verb when they are separated by other phrases).

Emergent Multi-Agent Communication in the Deep Learning Era

no code implementations3 Jun 2020 Angeliki Lazaridou, Marco Baroni

The ability to cooperate through language is a defining feature of humans.

Syntactic Structure from Deep Learning

no code implementations22 Apr 2020 Tal Linzen, Marco Baroni

Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such as machine translation.

Language Acquisition Machine Translation +1

Compositionality and Generalization in Emergent Languages

1 code implementation ACL 2020 Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux, Marco Baroni

Third, while compositionality is not necessary for generalization, it provides an advantage in terms of language transmission: The more compositional a language is, the more easily it will be picked up by new learners, even when the latter differ in architecture from the original agents.


Emergent Language Generalization and Acquisition Speed are not tied to Compositionality

1 code implementation EMNLP (BlackboxNLP) 2020 Eugene Kharitonov, Marco Baroni

Studies of discrete languages emerging when neural agents communicate to solve a joint task often look for evidence of compositional structure.

Rat big, cat eaten! Ideas for a useful deep-agent protolanguage

no code implementations17 Mar 2020 Marco Baroni

Deep-agent communities developing their own language-like communication protocol are a hot (or at least warm) topic in AI.

A Benchmark for Systematic Generalization in Grounded Language Understanding

4 code implementations NeurIPS 2020 Laura Ruis, Jacob Andreas, Marco Baroni, Diane Bouchacourt, Brenden M. Lake

In this paper, we introduce a new benchmark, gSCAN, for evaluating compositional generalization in situated language understanding.

Systematic Generalization

Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game

no code implementations5 Nov 2019 Roberto Dessì, Diane Bouchacourt, Davide Crepaldi, Marco Baroni

Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon.

On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study

no code implementations ACL 2019 Damian Blasi, Ryan Cotterell, Lawrence Wolf-Sonkin, Sabine Stoll, Balthasar Bickel, Marco Baroni

Embedding a clause inside another ({``}the girl [who likes cars [that run fast]] has arrived{''}) is a fundamental resource that has been argued to be a key driver of linguistic expressiveness.

EGG: a toolkit for research on Emergence of lanGuage in Games

no code implementations IJCNLP 2019 Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni

There is renewed interest in simulating language emergence among deep neural agents that communicate to jointly solve a task, spurred by the practical aim to develop language-enabled interactive AIs, as well as by theoretical questions about the evolution of human language.

Entropy Minimization In Emergent Languages

1 code implementation ICML 2020 Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni

There is growing interest in studying the languages that emerge when neural agents are jointly trained to solve tasks requiring communication through a discrete channel.

Representation Learning

Word-order biases in deep-agent emergent communication

1 code implementation ACL 2019 Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni

We train models to communicate about paths in a simple gridworld, using miniature languages that reflect or violate various natural language trends, such as the tendency to avoid redundancy or to minimize long-distance dependencies.

Anti-efficient encoding in emergent communication

1 code implementation NeurIPS 2019 Rahma Chaabouni, Eugene Kharitonov, Emmanuel Dupoux, Marco Baroni

Despite renewed interest in emergent language simulations with neural networks, little is known about the basic properties of the induced code, and how they compare to human language.

Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances

1 code implementation ACL 2019 Diane Bouchacourt, Marco Baroni

Recent research studies communication emergence in communities of deep network agents assigned a joint task, hoping to gain insights on human language evolution.

CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks

no code implementations ACL 2019 Roberto Dessì, Marco Baroni

Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of "jump around" 0-shot from the component words.

Linguistic generalization and compositionality in modern artificial neural networks

no code implementations30 Mar 2019 Marco Baroni

In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks.

Systematic Generalization

The emergence of number and syntax units in LSTM language models

1 code implementation NAACL 2019 Yair Lakretz, German Kruszewski, Theo Desbordes, Dieuwke Hupkes, Stanislas Dehaene, Marco Baroni

Importantly, the behaviour of these units is partially controlled by other units independently shown to track syntactic structure.

Language Modelling

Human few-shot learning of compositional instructions

2 code implementations14 Jan 2019 Brenden M. Lake, Tal Linzen, Marco Baroni

There have been striking recent improvements in machine learning for natural language processing, yet the best algorithms require vast amounts of experience and struggle to generalize new concepts in compositional ways.

Few-Shot Learning

Jump to better conclusions: SCAN both left and right

1 code implementation WS 2018 Jasmijn Bastings, Marco Baroni, Jason Weston, Kyunghyun Cho, Douwe Kiela

Lake and Baroni (2018) recently introduced the SCAN data set, which consists of simple commands paired with action sequences and is intended to test the strong generalization abilities of recurrent sequence-to-sequence models.

How agents see things: On visual representations in an emergent language game

no code implementations EMNLP 2018 Diane Bouchacourt, Marco Baroni

There is growing interest in the language developed by agents interacting in emergent-communication settings.

Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks

no code implementations WS 2018 João Loula, Marco Baroni, Brenden M. Lake

Systematic compositionality is the ability to recombine meaningful units with regular and predictable outcomes, and it's seen as key to humans' capacity for generalization in language.

What you can cram into a single vector: Probing sentence embeddings for linguistic properties

6 code implementations3 May 2018 Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, Marco Baroni

Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing.

General Classification Sentence Classification +1

Colorless green recurrent networks dream hierarchically

2 code implementations NAACL 2018 Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, Marco Baroni

Recurrent neural networks (RNNs) have achieved impressive results in a variety of linguistic processing tasks, suggesting that they can induce non-trivial properties of language.

Language Modelling

Memorize or generalize? Searching for a compositional RNN in a haystack

1 code implementation18 Feb 2018 Adam Liška, Germán Kruszewski, Marco Baroni

Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other.

Causal Discovery Using Proxy Variables

no code implementations23 Feb 2017 Mateo Rojas-Carulla, Marco Baroni, David Lopez-Paz

In this paper, we develop a framework to estimate the cause-effect relation between two static entities $x$ and $y$: for instance, an art masterpiece $x$ and its fraudulent copy $y$.

Causal Discovery

Living a discrete life in a continuous world: Reference with distributed representations

no code implementations6 Feb 2017 Gemma Boleda, Sebastian Padó, Nghia The Pham, Marco Baroni

Reference is a crucial property of language that allows us to connect linguistic expressions to the world.

CommAI: Evaluating the first steps towards a useful general AI

no code implementations31 Jan 2017 Marco Baroni, Armand Joulin, Allan Jabri, Germàn Kruszewski, Angeliki Lazaridou, Klemen Simonic, Tomas Mikolov

With machine learning successfully applied to new daunting problems almost every day, general AI starts looking like an attainable goal.

BIG-bench Machine Learning Continual Learning +2

Multi-Agent Cooperation and the Emergence of (Natural) Language

1 code implementation21 Dec 2016 Angeliki Lazaridou, Alexander Peysakhovich, Marco Baroni

The sender is told one of them is the target and is allowed to send a message from a fixed, arbitrary vocabulary to the receiver.

"Show me the cup": Reference with Continuous Representations

no code implementations28 Jun 2016 Gemma Boleda, Sebastian Padó, Marco Baroni

One of the most basic functions of language is to refer to objects in a shared scene.

Towards Multi-Agent Communication-Based Language Learning

no code implementations23 May 2016 Angeliki Lazaridou, Nghia The Pham, Marco Baroni

We propose an interactive multimodal framework for language learning.

The red one!: On learning to refer to things based on their discriminative properties

no code implementations8 Mar 2016 Angeliki Lazaridou, Nghia The Pham, Marco Baroni

As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (cat) and a context (sofa), identifies their discriminative attributes, i. e., properties that distinguish them (has_tail).

A Roadmap towards Machine Intelligence

1 code implementation25 Nov 2015 Tomas Mikolov, Armand Joulin, Marco Baroni

The development of intelligent machines is one of the biggest unsolved challenges in computer science.

Unveiling the Dreams of Word Embeddings: Towards Language-Driven Image Generation

no code implementations10 Jun 2015 Angeliki Lazaridou, Dat Tien Nguyen, Raffaella Bernardi, Marco Baroni

We introduce language-driven image generation, the task of generating an image visualizing the semantic contents of a word embedding, e. g., given the word embedding of grasshopper, we generate a natural image of a grasshopper.

Image Generation Word Embeddings

Combining Language and Vision with a Multimodal Skip-gram Model

no code implementations HLT 2015 Angeliki Lazaridou, Nghia The Pham, Marco Baroni

We extend the SKIP-GRAM model of Mikolov et al. (2013a) by taking visual information into account.


From Visual Attributes to Adjectives through Decompositional Distributional Semantics

no code implementations TACL 2015 Angeliki Lazaridou, Georgiana Dinu, Adam Liska, Marco Baroni

By building on the recent "zero-shot learning" approach, and paying attention to the linguistic nature of attributes as noun modifiers, and specifically adjectives, we show that it is possible to tag images with attribute-denoting adjectives even when no training data containing the relevant annotation are available.

Object Recognition Retrieval +2

Deriving Boolean structures from distributional vectors

no code implementations TACL 2015 German Kruszewski, Denis Paperno, Marco Baroni

Corpus-based distributional semantic models capture degrees of semantic relatedness among the words of very large vocabularies, but have problems with logical phenomena such as entailment, that are instead elegantly handled by model-theoretic approaches, which, in turn, do not scale up.

Improving zero-shot learning by mitigating the hubness problem

4 code implementations20 Dec 2014 Georgiana Dinu, Angeliki Lazaridou, Marco Baroni

The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels.

Image Retrieval Retrieval +1

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