Joëlle Pineau

The RLLChatbot: a solution to the ConvAI challenge

2018 · arXiv (Cornell University)

Current conversational systems can follow simple commands and answer basic questions, but they have difficulty maintaining coherent and open-ended conversations about specific topics. Competitions like the Conversational Intelligence (ConvAI) challenge are being organized to push …

Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic

2020 · arXiv (Cornell University)

Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a recent approach that applies single-agent AIRL to multi-agent problems where we seek to recover both policies for our agents and reward functions that promote expert-like behavior. While …

An Introduction to Deep Reinforcement Learning

2018 · Foundations and Trends® in Machine Learning

Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision making tasks that were previously out of …

UnNatural Language Inference

2021

Koustuv Sinha, Prasanna Parthasarathi, Joelle Pineau, Adina Williams. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Masked Language Modeling and the Distributional Hypothesis: Order Word\n Matters Pre-training for Little

2021 · arXiv (Cornell University)

A possible explanation for the impressive performance of masked language\nmodel (MLM) pre-training is that such models have learned to represent the\nsyntactic structures prevalent in classical NLP pipelines. In this paper, we\npropose a different explanation: MLMs …

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

2022 · arXiv (Cornell University)

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new …

A Survey of Available Corpora for Building Data-Driven Dialogue Systems

2015 · arXiv (Cornell University)

During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models. In the area of dialogue systems, the trend is less obvious, and most practical …

How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

2016 · arXiv (Cornell University)

We investigate evaluation metrics for dialogue response generation systems where supervised labels, such as task completion, are not available. Recent works in response generation have adopted metrics from machine translation to compare a model's generated …

An Actor-Critic Algorithm for Sequence Prediction

2016 · arXiv (Cornell University)

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models …

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up the possibility for realistic, …

Language GANs Falling Short

2020 · International Conference on Learning Representations

Traditional natural language generation (NLG) models are trained using maximum likelihood estimation (MLE) which differs from the sample generation inference procedure. During training the ground truth tokens are passed to the model, however, during inference, …

Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines. In this paper, we propose a …