activity
20172022
most citedPlato Dialogue System: A Flexible Conversational AI Research Platform

15 citations · 43 across the 13 of their papers we have counts for

collaborators

15 papers

cs.CL20227 cited

Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding

Maximillian Chen, Alexandros Papangelis, Chenyang Tao +5

Dialogue understanding tasks often necessitate abundant annotated data to achieve good performance and that presents challenges in low-resource settings. To alleviate this barrier,…

cs.CL20223 cited

What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation

Sarik Ghazarian, Behnam Hedayatnia, Alexandros Papangelis +2

Accurate automatic evaluation metrics for open-domain dialogs are in high demand. Existing model-based metrics for system response evaluation are trained on human annotated data, w…

cs.CL2021

Training Conversational Agents with Generative Conversational Networks

Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim +1

Rich, open-domain textual data available on the web resulted in great advancements for language processing. However, while that data may be suitable for language processing tasks,…

cs.CL20212 cited

"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations

Seokhwan Kim, Yang Liu, Di Jin +4

Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the natu…

cs.CL20211 cited

Generative Conversational Networks

Alexandros Papangelis, Karthik Gopalakrishnan, Aishwarya Padmakumar +3

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to…

cs.CL2021

Open-domain Topic Identification of Out-of-domain Utterances using Wikipedia

A. Augustin, A. Papangelis, M. Kotti +3

Users of spoken dialogue systems (SDS) expect high quality interactions across a wide range of diverse topics. However, the implementation of SDS capable of responding to every con…