Models, code, and papers for "Richard Csaky":

Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System

Sep 11, 2019
Richard Csaky

This is the application document for the 2019 Amazon Alexa competition. We give an overall vision of our conversational experience, as well as a sample conversation that we would like our dialog system to achieve by the end of the competition. We believe personalization, knowledge, and self-play are important components towards better chatbots. These are further highlighted by our detailed system architecture proposal and novelty section. Finally, we describe how we would ensure an engaging experience, how this research would impact the field, and related work.

* 14 pages. Originally written for the 2019 Amazon Alexa application 

  Click for Model/Code and Paper
Deep Learning Based Chatbot Models

Aug 23, 2019
Richard Csaky

A conversational agent (chatbot) is a piece of software that is able to communicate with humans using natural language. Modeling conversation is an important task in natural language processing and artificial intelligence. While chatbots can be used for various tasks, in general they have to understand users' utterances and provide responses that are relevant to the problem at hand. In my work, I conduct an in-depth survey of recent literature, examining over 70 publications related to chatbots published in the last 3 years. Then, I proceed to make the argument that the very nature of the general conversation domain demands approaches that are different from current state-of-of-the-art architectures. Based on several examples from the literature I show why current chatbot models fail to take into account enough priors when generating responses and how this affects the quality of the conversation. In the case of chatbots, these priors can be outside sources of information that the conversation is conditioned on like the persona or mood of the conversers. In addition to presenting the reasons behind this problem, I propose several ideas on how it could be remedied. The next section focuses on adapting the very recent Transformer model to the chatbot domain, which is currently state-of-the-art in neural machine translation. I first present experiments with the vanilla model, using conversations extracted from the Cornell Movie-Dialog Corpus. Secondly, I augment the model with some of my ideas regarding the issues of encoder-decoder architectures. More specifically, I feed additional features into the model like mood or persona together with the raw conversation data. Finally, I conduct a detailed analysis of how the vanilla model performs on conversational data by comparing it to previous chatbot models and how the additional features affect the quality of the generated responses.

* 67 pages. Written in October of 2017 for a university conference. In April of 2019, it won first place at the Hungarian Scientific Students' Associations Report, which is a national competition-like conference for students 

  Click for Model/Code and Paper
Improving Neural Conversational Models with Entropy-Based Data Filtering

Jun 04, 2019
Richard Csaky, Patrik Purgai, Gabor Recski

Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. Priors such as persona, emotion, or topic provide additional information to dialog models to aid response generation, but annotating a dataset with priors is expensive and such annotations are rarely available. While previous methods for improving the quality of open-domain response generation focused on either the underlying model or the training objective, we present a method of filtering dialog datasets by removing generic utterances from training data using a simple entropy-based approach that does not require human supervision. We conduct extensive experiments with different variations of our method, and compare dialog models across 17 evaluation metrics to show that training on datasets filtered this way results in better conversational quality as chatbots learn to output more diverse responses.

* 20 pages. To be presented at ACL 2019. Camera-ready 

  Click for Model/Code and Paper