Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast

07/22/2019
by   Vrindavan Harrison, et al.
0

Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused solely on the semantic fidelity of outputs, recent work has started to explore methods for controlling the style of the generated text while simultaneously achieving semantic accuracy. Here we experiment with two stylistic benchmark tasks, generating language that exhibits variation in personality, and generating discourse contrast. We report a huge performance improvement in both stylistic control and semantic accuracy over the state of the art on both of these benchmarks. We test several different models and show that putting stylistic conditioning in the decoder and eliminating the semantic re-ranker used in earlier models results in more than 15 points higher BLEU for Personality, with a reduction of semantic error to near zero. We also report an improvement from .75 to .81 in controlling contrast and a reduction in semantic error from 16

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/08/2023

Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning

Prompt-based or in-context learning has achieved high zero-shot performa...
research
05/22/2018

Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

Natural language generators for task-oriented dialogue must effectively ...
research
08/20/2020

Controlling Dialogue Generation with Semantic Exemplars

Dialogue systems pretrained with large language models generate locally ...
research
07/09/2017

Controlling Linguistic Style Aspects in Neural Language Generation

Most work on neural natural language generation (NNLG) focus on controll...
research
06/17/2019

Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue

Generating fluent natural language responses from structured semantic re...
research
03/12/2016

Neural Discourse Relation Recognition with Semantic Memory

Humans comprehend the meanings and relations of discourses heavily relyi...
research
02/04/2022

Tracking Discourse Influence in Darknet Forums

This technical report documents our efforts in addressing the tasks set ...

Please sign up or login with your details

Forgot password? Click here to reset