Commitment detection in emails and dialog generation with IL and IRL

Are you going?

59 spots left

Share:

Every last Friday of the month

Location image of event venue

Details

This Thursday (!) we'll have two talks followed by drinks.

17:00 Hosein Azarbonyad (KLM): Domain Adaptation for Commitment Detection in Email

17:30 Ziming Li (University of Amsterdam): Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

========================

17:00 Hosein Azarbonyad (KLM): Domain Adaptation for Commitment Detection in Email

People often make commitments to perform future actions. Detecting commitments made in email (e.g., "I'll send the report by end of day'') enables digital assistants to help their users recall promises they have made and assist them in meeting those promises in a timely manner. Commitments can be reliably extracted from emails when models are trained and evaluated on the same domain (corpus). However, their performance degrades when the evaluation domain differs. This illustrates the domain bias associated with email datasets and a need for more robust and generalizable models for commitment detection. To learn a domain-independent commitment model, we first characterize the differences between domains (email corpora) and then use this characterization to transfer knowledge between them. We investigate the performance of domain adaptation, namely transfer learning, at different granularities: feature-level adaptation and sample-level adaptation. We extend this further using a neural autoencoder trained to learn a domain-independent representation for training samples. We show that transfer learning can help remove domain bias to obtain models with less domain dependence.

========================

17:30 Ziming Li (University of Amsterdam): Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a recently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more accurate and precise reward signal for generator training. We evaluate the performance of the resulting model with automatic metrics and human evaluations in two annotation settings. Our experimental results demonstrate that our model can generate more high-quality responses and achieve higher overall performance than the state-of-the-art.