19 citations · 62 across the 17 of their papers we have counts for
24 papers
Curriculum Learning with Adam: The Devil Is in the Wrong Details
Lucas Weber, Jaap Jumelet, Paul Michel +2
Curriculum learning (CL) posits that machine learning models -- similar to humans -- may learn more efficiently from data that match their current learning progress. However, CL me…
Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses
Xenia Ohmer, Elia Bruni, Dieuwke Hupkes
At the staggering pace with which the capabilities of large language models (LLMs) are increasing, creating future-proof evaluation sets to assess their understanding becomes more…
Emergence of hierarchical reference systems in multi-agent communication
Xenia Ohmer, Marko Duda, Elia Bruni
In natural language, referencing objects at different levels of specificity is a fundamental pragmatic mechanism for efficient communication in context. We develop a novel communic…
The paradox of the compositionality of natural language: a neural machine translation case study
Verna Dankers, Elia Bruni, Dieuwke Hupkes
Obtaining human-like performance in NLP is often argued to require compositional generalisation. Whether neural networks exhibit this ability is usually studied by training models…
Language Modelling as a Multi-Task Problem
Lucas Weber, Jaap Jumelet, Elia Bruni +1
In this paper, we propose to study language modelling as a multi-task problem, bringing together three strands of research: multi-task learning, linguistics, and interpretability.…
The Grammar of Emergent Languages
Oskar van der Wal, Silvan de Boer, Elia Bruni +1
In this paper, we consider the syntactic properties of languages emerged in referential games, using unsupervised grammar induction (UGI) techniques originally designed to analyse…
Internal and external pressures on language emergence: least effort, object constancy and frequency
Diana Rodríguez Luna, Edoardo Maria Ponti, Dieuwke Hupkes +1
In previous work, artificial agents were shown to achieve almost perfect accuracy in referential games where they have to communicate to identify images. Nevertheless, the resultin…
Compositional properties of emergent languages in deep learning
Bence Keresztury, Elia Bruni
Recent findings in multi-agent deep learning systems point towards the emergence of compositional languages. These claims are often made without exact analysis or testing of the la…
Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning
Michiel van der Meer, Matteo Pirotta, Elia Bruni
In this work, we present an alternative approach to making an agent compositional through the use of a diagnostic classifier. Because of the need for explainable agents in automate…
Co-evolution of language and agents in referential games
Gautier Dagan, Dieuwke Hupkes, Elia Bruni
Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take i…
Generalizing Emergent Communication
Thomas A. Unger, Elia Bruni
We converted the recently developed BabyAI grid world platform to a sender/receiver setup in order to test the hypothesis that established deep reinforcement learning techniques ar…
Learning to Request Guidance in Emergent Communication
Benjamin Kolb, Leon Lang, Henning Bartsch +6
Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing…
Location Attention for Extrapolation to Longer Sequences
Yann Dubois, Gautier Dagan, Dieuwke Hupkes +1
Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to…
Mastering emergent language: learning to guide in simulated navigation
Mathijs Mul, Diane Bouchacourt, Elia Bruni
To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher whi…
Compositionality decomposed: how do neural networks generalise?
Dieuwke Hupkes, Verna Dankers, Mathijs Mul +1
Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack…
The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue
Janosch Haber, Tim Baumgärtner, Ece Takmaz +3
This paper introduces the PhotoBook dataset, a large-scale collection of visually-grounded, task-oriented dialogues in English designed to investigate shared dialogue history accum…
Assessing incrementality in sequence-to-sequence models
Dennis Ulmer, Dieuwke Hupkes, Elia Bruni
Since their inception, encoder-decoder models have successfully been applied to a wide array of problems in computational linguistics. The most recent successes are predominantly d…
On the Realization of Compositionality in Neural Networks
Joris Baan, Jana Leible, Mitja Nikolaus +5
We present a detailed comparison of two types of sequence to sequence models trained to conduct a compositional task. The models are architecturally identical at inference time, bu…
Transcoding compositionally: using attention to find more generalizable solutions
Kris Korrel, Dieuwke Hupkes, Verna Dankers +1
While sequence-to-sequence models have shown remarkable generalization power across several natural language tasks, their construct of solutions are argued to be less compositional…
The Fast and the Flexible: training neural networks to learn to follow instructions from small data
Rezka Leonandya, Elia Bruni, Dieuwke Hupkes +1
Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is…
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
Ravi Shekhar, Aashish Venkatesh, Tim Baumgärtner +4
We propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on t…
Ask No More: Deciding when to guess in referential visual dialogue
Ravi Shekhar, Tim Baumgartner, Aashish Venkatesh +3
Our goal is to explore how the abilities brought in by a dialogue manager can be included in end-to-end visually grounded conversational agents. We make initial steps towards this…
Learning compositionally through attentive guidance
Dieuwke Hupkes, Anand Singh, Kris Korrel +2
While neural network models have been successfully applied to domains that require substantial generalisation skills, recent studies have implied that they struggle when solving th…
Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest
Korsuk Sirinukunwattana, Josien P. W. Pluim, Hao Chen +16
Colorectal adenocarcinoma originating in intestinal glandular structures is the most common form of colon cancer. In clinical practice, the morphology of intestinal glands, includi…