Year: 2021
Type: conference-paper
Abstract: To be good conversational partners, natural language processing (NLP) systems should be trained to produce contextually useful utterances.Prior work has investigated training NLP systems with communication-based objectives, where a neural listener stands in as a communication partner.However, these systems commonly suffer from semantic drift where the learned language diverges radically from natural language.We propose a method that uses a population of neural listeners to regularize speaker training.We first show that language drift originates from the poor uncertainty calibration of a neural listener, which makes high-certainty predictions on novel sentences.We explore ensemble-and dropoutbased populations of listeners and find that the former results in better uncertainty quantification.We evaluate both population-based objectives on reference games, and show that the ensemble method with better calibration enables the speaker to generate pragmatic utterances while scaling to a large vocabulary and generalizing to new games and listeners.1
Authors: Rose Wang, Julia White, Jesse Mu, Noah Goodman
Institution: Stanford University
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: National Science Foundation
OpenAlex ID: W3206128609