Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Welivita, Anuradha"'
Autor:
Welivita, Anuradha, Pu, Pearl
With the emergence of large language models (LLMs), investigating if they can surpass humans in areas such as emotion recognition and empathetic responding has become a focal point of research. This paper presents a comprehensive study exploring the
Externí odkaz:
http://arxiv.org/abs/2406.05063
Autor:
Welivita, Anuradha, Pu, Pearl
This paper investigates the empathetic responding capabilities of ChatGPT, particularly its latest iteration, GPT-4, in comparison to human-generated responses to a wide range of emotional scenarios, both positive and negative. We employ a rigorous e
Externí odkaz:
http://arxiv.org/abs/2403.05572
Autor:
Welivita, Anuradha, Pu, Pearl
AI-driven chatbots have become an emerging solution to address psychological distress. Due to the lack of psychotherapeutic data, researchers use dialogues scraped from online peer support forums to train them. But since the responses in such platfor
Externí odkaz:
http://arxiv.org/abs/2305.10195
Use of a Taxonomy of Empathetic Response Intents to Control and Interpret Empathy in Neural Chatbots
Autor:
Welivita, Anuradha, Pu, Pearl
A recent trend in the domain of open-domain conversational agents is enabling them to converse empathetically to emotional prompts. Current approaches either follow an end-to-end approach or condition the responses on similar emotion labels to genera
Externí odkaz:
http://arxiv.org/abs/2305.10096
We propose a novel large-scale emotional dialogue dataset, consisting of 1M dialogues retrieved from the OpenSubtitles corpus and annotated with 32 emotions and 9 empathetic response intents using a BERT-based fine-grained dialogue emotion classifier
Externí odkaz:
http://arxiv.org/abs/2012.13624
Autor:
Welivita, Anuradha, Pu, Pearl
Open-domain conversational agents or chatbots are becoming increasingly popular in the natural language processing community. One of the challenges is enabling them to converse in an empathetic manner. Current neural response generation methods rely
Externí odkaz:
http://arxiv.org/abs/2012.04080
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Welivita, Anuradha, Pu, Pearl
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:11459-11467
The demands of the modern world are increasingly responsible for causing psychological burdens and bringing adverse impacts on our mental health. As a result, neural conversational agents with empathetic responding and distress management capabilitie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1e0222240ec2f302f7a910e168e9b5c
https://doi.org/10.1609/aaai.v36i10.21398
https://doi.org/10.1609/aaai.v36i10.21398
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Recent development in NLP shows a strong trend towards refining pre-trained models with a domain-specific dataset. This is especially the case for response generation where emotion plays an important role. However, existing empathetic datasets remain
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6a4af39f19452f94154013884ad114a
https://doi.org/10.18653/v1/2021.emnlp-main.96
https://doi.org/10.18653/v1/2021.emnlp-main.96
Publikováno v:
International Journal of Online & Biomedical Engineering; 2020, Vol. 16 Issue 8, p68-84, 17p