Search Results for author:
Found 34 papers, 11 papers with code
Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest
Colorectal adenocarcinoma originating in intestinal glandular structures is the most common form of colon cancer.
Adversarial evaluation for open-domain dialogue generation
We investigate the potential of adversarial evaluation methods for open-domain dialogue generation systems, comparing the performance of a discriminative agent to that of humans on the same task.
Ask No More: Deciding when to guess in referential visual dialogue
We make initial steps towards this general goal by augmenting a task-oriented visual dialogue model with a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess.
Learning compositionally through attentive guidance
While neural network models have been successfully applied to domains that require substantial generalisation skills, recent studies have implied that they struggle when solving the task they are trained on requires inferring its underlying compositional structure.
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
We compare our approach to an alternative system which extends the baseline with reinforcement learning.
The Fast and the Flexible: training neural networks to learn to follow instructions from small data
Learning to follow human instructions is a long-pursued goal in artificial intelligence.
On the Realization of Compositionality in Neural Networks
We present a detailed comparison of two types of sequence to sequence models trained to conduct a compositional task.
The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue
This paper introduces the PhotoBook dataset, a large-scale collection of visually-grounded, task-oriented dialogues in English designed to investigate shared dialogue history accumulating during conversation.
Transcoding compositionally: using attention to find more generalizable solutions
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 than human-like generalization.
Assessing incrementality in sequence-to-sequence models
Since their inception, encoder-decoder models have successfully been applied to a wide array of problems in computational linguistics.
Mastering emergent language: learning to guide in simulated navigation
A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions.
Compositionality decomposed: how do neural networks generalise?
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 of agreement about what it means for a neural model to be compositional.
Learning to request guidance in emergent language
Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent.
Location Attention for Extrapolation to Longer Sequences
We hypothesize that models with a separate content- and location-based attention are more likely to extrapolate than those with common attention mechanisms.
Learning to Request Guidance in Emergent Communication
Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent.
Generalizing Emergent Communication
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 are sufficient to incentivize the emergence of a grounded discrete communication protocol between generalized agents.
Co-evolution of language and agents in referential games
However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners.
Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning
In this work, we present an alternative approach to making an agent compositional through the use of a diagnostic classifier.
Compositional properties of emergent languages in deep learning
Recent findings in multi-agent deep learning systems point towards the emergence of compositional languages.
Internal and external pressures on language emergence: least effort, object constancy and frequency
In previous work, artificial agents were shown to achieve almost perfect accuracy in referential games where they have to communicate to identify images.
The Grammar of Emergent Languages
In this paper, we consider the syntactic properties of languages emerged in referential games, using unsupervised grammar induction (UGI) techniques originally designed to analyse natural language.
Language Modelling as a Multi-Task Problem
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 paradox of the compositionality of natural language: a neural machine translation case study
Obtaining human-like performance in NLP is often argued to require compositional generalisation.
Emergence of hierarchical reference systems in multi-agent communication
We develop a novel communication game, the hierarchical reference game, to study the emergence of such reference systems in artificial agents.
Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses
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 and more challenging.
Curriculum Learning with Adam: The Devil Is in the Wrong Details
We present a number of different case studies with different common hand-crafted and automated CL approaches to illustrate this phenomenon, and we find that none of them outperforms optimisation with only Adam with well-chosen hyperparameters.
Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning
Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP.
GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models
Our evaluation reveals significant shortcomings in the language grounding and intuitive physics capabilities of these models.
The ICL Consistency Test
Just like the previous generation of task-tuned models, large language models (LLMs) that are adapted to tasks via prompt-based methods like in-context-learning (ICL) perform well in some setups but not in others.
