RESEARCH

CONVERSATIONAL AI

OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs

July 29, 2019

Abstract

We study a conversational reasoning model that strategically traverses through a large-scale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes. For this study, we collect a new Open-ended Dialog ↔ KG parallel corpus called OpenDialKG, where each utterance from 15K human-to-human role-playing dialogs is manually annotated with ground-truth reference to corresponding entities and paths from a large-scale KG with 1M+ facts. We then propose the DialKG Walker model that learns the symbolic transitions of dialog contexts as structured traversals over KG, and predicts natural entities to introduce given previous dialog contexts via a novel domain-agnostic, attention-based graph path decoder. Automatic and human evaluations show that our model can retrieve more natural and human-like responses than the state-of-the-art baselines or rule-based models, in both in-domain and cross-domain tasks. The proposed model also generates a KG walk path for each entity retrieved, providing a natural way to explain conversational reasoning.

Download the Paper

Related Publications

July 29, 2019

NLP

SPEECH & AUDIO

OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs | Facebook AI Research

We study a conversational reasoning model that strategically traverses through a large-scale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes. For this study, we collect a new Open-ended…

Shane Moon, Pararth Shah, Anuj Kumar, Rajen Subba

July 29, 2019

December 04, 2018

NLP

CONVERSATIONAL AI

Improving Semantic Parsing for Task Oriented Dialog | Facebook AI Research

Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results. In this paper, we present three different improvements to the model: contextualized embeddings, ensembling, and…

Arash Einolghozati, Panupong Pasupat, Sonal Gupta, Rushin Shah, Mrinal Mohit, Mike Lewis, Luke Zettlemoyer

December 04, 2018

December 04, 2018

CONVERSATIONAL AI

NLP

Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog | Facebook AI Research

One of the first steps in the utterance interpretation pipeline of many task-oriented conversational AI systems is to identify user intents and the corresponding slots. Neural sequence labeling models have achieved very high accuracy on these…

Sebastian Schuster, Sonal Gupta, Rushin Shah, Mike Lewis

December 04, 2018

December 03, 2018

CONVERSATIONAL AI

Explore-Exploit: A Framework for Interactive and Online Learning | Facebook AI Research

Interactive user interfaces need to continuously evolve based on the interactions that a user has (or does not have) with the system. This may require constant exploration of various options that the system may have for the user and obtaining…

Honglei Liu, Anuj Kumar, Wenhai Yang, Benoit Dumoulin

December 03, 2018

Related Work

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.