Search Results for author: Hannes Schulz

Found 15 papers, 5 papers with code

Decomposed Mutual Information Estimation for Contrastive Representation Learning

no code implementations25 Jun 2021 Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Phil Bachman, Remi Tachet

We propose decomposing the full MI estimation problem into a sum of smaller estimation problems by splitting one of the views into progressively more informed subviews and by applying the chain rule on MI between the decomposed views.

Data Augmentation Dialogue Generation +2

Decomposing Mutual Information for Representation Learning

no code implementations1 Jan 2021 Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Remi Tachet des Combes, Philip Bachman

In this paper, we transform each view into a set of subviews and then decompose the original MI bound into a sum of bounds involving conditional MI between the subviews.

Dialogue Generation Representation Learning

Towards a Scalable and Distributed Infrastructure for Deep Learning Applications

1 code implementation6 Oct 2020 Bita Hasheminezhad, Shahrzad Shirzad, Nanmiao Wu, Patrick Diehl, Hannes Schulz, Hartmut Kaiser

Although recent scaling up approaches to training deep neural networks have proven to be effective, the computational intensity of large and complex models, as well as the availability of large-scale datasets, require deep learning frameworks to utilize scaling out techniques.

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.

Decoder Question Answering

The Knowref Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution

1 code implementation ACL 2019 Ali Emami, Paul Trichelair, Adam Trischler, Kaheer Suleman, Hannes Schulz, Jackie Chi Kit Cheung

To explain this performance gap, we show empirically that state-of-the art models often fail to capture context, instead relying on the gender or number of candidate antecedents to make a decision.

Common Sense Reasoning coreference-resolution +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 Diversity +4

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.

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.