RESEARCH

CONVERSATIONAL AI

Improving Semantic Parsing for Task Oriented Dialog

December 4, 2018

Abstract

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 pairwise re-ranking based on a language model. We taxonomize the errors possible for the hierarchical representation, such as wrong top intent, missing spans or split spans, and show that the three approaches correct different kinds of errors. The best model combines the three techniques and gives 6.4% better exact match accuracy than the state-of-the-art, with an error reduction of 33%, resulting in a new state-of-the-art result on the Task Oriented Parsing (TOP) dataset.

Download the Paper

Related Publications

December 03, 2018

CONVERSATIONAL AI

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

Honglei Liu, Anuj Kumar, Wenhai Yang, Benoit Dumoulin

December 03, 2018

November 05, 2019

NLP

CONVERSATIONAL AI

Memory Grounded Conversational Reasoning | Facebook AI Research

Shane Moon, Pararth Shah, Anuj Kumar, Rajen Subba

November 05, 2019

December 04, 2018

CONVERSATIONAL AI

NLP

Improving Semantic Parsing for Task Oriented Dialog | Facebook AI Research

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

December 04, 2018

July 29, 2019

CONVERSATIONAL AI

NLP

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

Shane Moon, Pararth Shah, Anuj Kumar, Rajen Subba

July 29, 2019

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.