PGTask: Introducing the Task of Profile Generation from Dialogues

04/13/2023
by   Rui Ribeiro, et al.
0

Recent approaches have attempted to personalize dialogue systems by leveraging profile information into models. However, this knowledge is scarce and difficult to obtain, which makes the extraction/generation of profile information from dialogues a fundamental asset. To surpass this limitation, we introduce the Profile Generation Task (PGTask). We contribute with a new dataset for this problem, comprising profile sentences aligned with related utterances, extracted from a corpus of dialogues. Furthermore, using state-of-the-art methods, we provide a benchmark for profile generation on this novel dataset. Our experiments disclose the challenges of profile generation, and we hope that this introduces a new research direction.

READ FULL TEXT
research
01/22/2018

Personalizing Dialogue Agents: I have a dog, do you have pets too?

Chit-chat models are known to have several problems: they lack specifici...
research
12/22/2021

Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding

Current researches on spoken language understanding (SLU) heavily are li...
research
08/11/2020

Planimation

Planimation is a modular and extensible open source framework to visuali...
research
03/14/2019

Profile Closeness in Complex Networks

We introduce a new centrality measure, known as profile closeness, for c...
research
07/13/2020

COVID-19 infectivity profile correction

The infectivity profile of an individual with COVID-19 is attributed to ...
research
09/23/2012

Creation of Digital Test Form for Prepress Department

The main problem in colour management in prepress department is lack of ...
research
03/01/2019

Are profile likelihoods likelihoods? No, but sometimes they can be

We contribute our two cents to the ongoing discussion on whether profile...

Please sign up or login with your details

Forgot password? Click here to reset