Learning to Learn Semantic Parsers from Natural Language Supervision

02/22/2019
by   Igor Labutov, et al.
0

As humans, we often rely on language to learn language. For example, when corrected in a conversation, we may learn from that correction, over time improving our language fluency. Inspired by this observation, we propose a learning algorithm for training semantic parsers from supervision (feedback) expressed in natural language. Our algorithm learns a semantic parser from users' corrections such as "no, what I really meant was before his job, not after", by also simultaneously learning to parse this natural language feedback in order to leverage it as a form of supervision. Unlike supervision with gold-standard logical forms, our method does not require the user to be familiar with the underlying logical formalism, and unlike supervision from denotation, it does not require the user to know the correct answer to their query. This makes our learning algorithm naturally scalable in settings where existing conversational logs are available and can be leveraged as training data. We construct a novel dataset of natural language feedback in a conversational setting, and show that our method is effective at learning a semantic parser from such natural language supervision.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 8

page 9

page 10

page 13

research
10/30/2019

Building an Application Independent Natural Language Interface

Traditional approaches to building natural language (NL) interfaces typi...
research
09/18/2019

Natural Language Generation for Non-Expert Users

Motivated by the difficulty in presenting computational results, especia...
research
11/14/2017

Learning an Executable Neural Semantic Parser

This paper describes a neural semantic parser that maps natural language...
research
05/14/2023

Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing

Interactive semantic parsing based on natural language (NL) feedback, wh...
research
04/25/2017

From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood

Our goal is to learn a semantic parser that maps natural language uttera...
research
05/25/2020

Incidental Supervision: Moving beyond Supervised Learning

Machine Learning and Inference methods have become ubiquitous in our att...
research
11/29/2018

Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing

In semantic parsing for question-answering, it is often too expensive to...

Please sign up or login with your details

Forgot password? Click here to reset