Search Results for author: Layla El Asri

Found 16 papers, 7 papers with code

SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks

1 code implementation NeurIPS 2021 Bahare Fatemi, Layla El Asri, Seyed Mehran Kazemi

In this work, we propose the Simultaneous Learning of Adjacency and GNN Parameters with Self-supervision, or SLAPS, a method that provides more supervision for inferring a graph structure through self-supervision.

Graph structure learning

Diverse Keyphrase Generation with Neural Unlikelihood Training

1 code implementation COLING 2020 Hareesh Bahuleyan, Layla El Asri

Further, to encourage better model planning during the decoding process, we incorporate K-step ahead token prediction objective that computes both MLE and UL losses on future tokens as well.

Keyphrase Generation Text Generation

A Study of State Aliasing in Structured Prediction with RNNs

no code implementations ICLR Workshop drlStructPred 2019 Layla El Asri, Adam Trischler

We show through extensive experiments and analysis that, when trained with policy gradient, recurrent neural networks often fail to learn a state representation that leads to an optimal policy in settings where the same action should be taken at different states.

reinforcement-learning Reinforcement Learning (RL) +1

From FiLM to Video: Multi-turn Question Answering with Multi-modal Context

no code implementations17 Dec 2018 Dat Tien Nguyen, Shikhar Sharma, Hannes Schulz, Layla El Asri

Understanding audio-visual content and the ability to have an informative conversation about it have both been challenging areas for intelligent systems.

Question Answering

Towards Solving Text-based Games by Producing Adaptive Action Spaces

2 code implementations3 Dec 2018 Ruo Yu Tao, Marc-Alexandre Côté, Xingdi Yuan, Layla El Asri

To solve a text-based game, an agent needs to formulate valid text commands for a given context and find the ones that lead to success.

reinforcement-learning Reinforcement Learning (RL) +3

Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation

3 code implementations ICLR 2018 Shikhar Sharma, Layla El Asri, Hannes Schulz, Jeremie Zumer

However, previous work in dialogue response generation has shown that these metrics do not correlate strongly with human judgment in the non task-oriented dialogue setting.

Dialogue Generation Machine Translation +3

A Frame Tracking Model for Memory-Enhanced Dialogue Systems

no code implementations WS 2017 Hannes Schulz, Jeremie Zumer, Layla El Asri, Shikhar Sharma

Recently, resources and tasks were proposed to go beyond state tracking in dialogue systems.

A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems

no code implementations30 Jun 2016 Layla El Asri, Jing He, Kaheer Suleman

The model takes as input a sequence of dialogue contexts and outputs a sequence of dialogue acts corresponding to user intentions.

Dialogue State Tracking Spoken Dialogue Systems +1

Policy Networks with Two-Stage Training for Dialogue Systems

no code implementations WS 2016 Mehdi Fatemi, Layla El Asri, Hannes Schulz, Jing He, Kaheer Suleman

Indeed, with only a few hundred dialogues collected with a handcrafted policy, the actor-critic deep learner is considerably bootstrapped from a combination of supervised and batch RL.

Dialogue State Tracking Gaussian Processes +2

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