DeepAI AI Chat
Log In Sign Up

Refocusing on Relevance: Personalization in NLG

09/10/2021
by   Shiran Dudy, et al.
University of Colorado Boulder
Oregon Health & Science University
0

Many NLG tasks such as summarization, dialogue response, or open domain question answering focus primarily on a source text in order to generate a target response. This standard approach falls short, however, when a user's intent or context of work is not easily recoverable based solely on that source text – a scenario that we argue is more of the rule than the exception. In this work, we argue that NLG systems in general should place a much higher level of emphasis on making use of additional context, and suggest that relevance (as used in Information Retrieval) be thought of as a crucial tool for designing user-oriented text-generating tasks. We further discuss possible harms and hazards around such personalization, and argue that value-sensitive design represents a crucial path forward through these challenges.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/28/2021

Multi-stage Clarification in Conversational AI: The case of Question-Answering Dialogue Systems

Clarification resolution plays an important role in various information ...
10/18/2022

Towards Proactive Information Retrieval in Noisy Text with Wikipedia Concepts

Extracting useful information from the user history to clearly understan...
02/24/2021

Multichannel LSTM-CNN for Telugu Technical Domain Identification

With the instantaneous growth of text information, retrieving domain-ori...
11/11/2019

Interactive Attention for Semantic Text Matching

Semantic text matching, which matches a target text to a source text, is...
12/03/2020

Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries

Despite end-to-end neural systems making significant progress in the las...
11/16/2018

Investigating Bell Inequalities for Multidimensional Relevance Judgments in Information Retrieval

Relevance judgment in Information Retrieval is influenced by multiple fa...
03/17/2022

Time Dependency, Data Flow, and Competitive Advantage

Data is fundamental to machine learning-based products and services and ...