User profiles for Layla El Asri
Layla El AsriResearch Lead at Borealis AI Verified email at borealisai.com Cited by 1650 |
Frames: a corpus for adding memory to goal-oriented dialogue systems
This paper presents the Frames dataset (Frames is available at http://datasets.maluuba.com/Frames),
a corpus of 1369 human-human dialogues with an average of 15 turns per …
a corpus of 1369 human-human dialogues with an average of 15 turns per …
A sequence-to-sequence model for user simulation in spoken dialogue systems
User simulation is essential for generating enough data to train a statistical spoken dialogue
system. Previous models for user simulation suffer from several drawbacks, such as the …
system. Previous models for user simulation suffer from several drawbacks, such as the …
Textworld: A learning environment for text-based games
…, E Fine, J Moore, M Hausknecht, L El Asri…�- Computer Games: 7th�…, 2019 - Springer
We introduce TextWorld, a sandbox learning environment for the training and evaluation of
RL agents on text-based games. TextWorld is a Python library that handles interactive play-…
RL agents on text-based games. TextWorld is a Python library that handles interactive play-…
Slaps: Self-supervision improves structure learning for graph neural networks
Graph neural networks (GNNs) work well when the graph structure is provided. However,
this structure may not always be available in real-world applications. One solution to this …
this structure may not always be available in real-world applications. One solution to this …
Relevance of unsupervised metrics in task-oriented dialogue for evaluating natural language generation
Automated metrics such as BLEU are widely used in the machine translation literature. They
have also been used recently in the dialogue community for evaluating dialogue response …
have also been used recently in the dialogue community for evaluating dialogue response …
Policy networks with two-stage training for dialogue systems
In this paper, we propose to use deep policy networks which are trained with an advantage
actor-critic method for statistically optimised dialogue systems. First, we show that, on …
actor-critic method for statistically optimised dialogue systems. First, we show that, on …
Score-based inverse reinforcement learning
This paper reports theoretical and empirical results obtained for the score-based Inverse
Reinforcement Learning (IRL) algorithm. It relies on a non-standard setting for IRL consisting of …
Reinforcement Learning (IRL) algorithm. It relies on a non-standard setting for IRL consisting of …
Tell, draw, and repeat: Generating and modifying images based on continual linguistic instruction
Conditional text-to-image generation is an active area of research, with many possible
applications. Existing research has primarily focused on generating a single image from available …
applications. Existing research has primarily focused on generating a single image from available …
From film to video: Multi-turn question answering with multi-modal context
Understanding audio-visual content and the ability to have an informative conversation
about it have both been challenging areas for intelligent systems. The Audio Visual Scene-aware …
about it have both been challenging areas for intelligent systems. The Audio Visual Scene-aware …
Why exposure bias matters: An imitation learning perspective of error accumulation in language generation
Current language generation models suffer from issues such as repetition, incoherence, and
hallucinations. An often-repeated hypothesis is that this brittleness of generation models is …
hallucinations. An often-repeated hypothesis is that this brittleness of generation models is …