1 code implementation • ACL 2022 • Ekaterina Svikhnushina, Iuliana Voinea, Anuradha Welivita, Pearl Pu
To address this gap, we have developed an empathetic question taxonomy (EQT), with special attention paid to questions’ ability to capture communicative acts and their emotion-regulation intents.
1 code implementation • COLING 2022 • Anuradha Welivita, Pearl Pu
We use this data to conclude the extent to which conversational data from peer support platforms align with real therapeutic conversations and discuss in what ways they can be exploited to train therapeutic chatbots.
1 code implementation • EMNLP 2021 • Anuradha Welivita, Yubo Xie, Pearl Pu
Recent development in NLP shows a strong trend towards refining pre-trained models with a domain-specific dataset.
1 code implementation • SIGDIAL (ACL) 2022 • Ekaterina Svikhnushina, Anastasiia Filippova, Pearl Pu
Building an empathetic chatbot is an important objective in dialog generation research, with evaluation being one of the most challenging parts.
1 code implementation • 22 Feb 2024 • Anuradha Welivita, Pearl Pu
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.
no code implementations • 17 May 2023 • Anuradha Welivita, Pearl Pu
In this work, we make use of a taxonomy of eight empathetic response intents in addition to generic emotion categories in building a dialogue response generation model capable of generating empathetic responses in a controllable and interpretable manner.
1 code implementation • 17 May 2023 • Anuradha Welivita, Pearl Pu
AI-driven chatbots have become an emerging solution to address psychological distress.
no code implementations • 11 Apr 2023 • Ekaterina Svikhnushina, Pearl Pu
Existing evaluation metrics aim to automate offline user evaluation and approximate human judgment of pre-curated dialogs.
no code implementations • 25 Oct 2022 • Junze Li, Mengjie Zhao, Yubo Xie, Antonis Maronikolakis, Pearl Pu, Hinrich Schütze
Humor is a magnetic component in everyday human interactions and communications.
no code implementations • 22 May 2022 • Yubo Xie, Junze Li, Pearl Pu
The knowledge captured in this graph bears potential for conversational systems to understand how people offer acknowledgement, consoling, and a wide range of empathetic responses in social conversations.
no code implementations • 10 Aug 2021 • Yubo Xie, Pearl Pu
In this paper, we give an overview of commonsense reasoning in natural language processing, which requires a deeper understanding of the contexts and usually involves inference over implicit external knowledge.
no code implementations • SEMEVAL 2021 • Yubo Xie, Junze Li, Pearl Pu
The task aims at predicting whether the given text is humorous, the average humor rating given by the annotators, and whether the humor rating is controversial.
1 code implementation • CoNLL (EMNLP) 2021 • Yubo Xie, Pearl Pu
Empathetic dialog generation aims at generating coherent responses following previous dialog turns and, more importantly, showing a sense of caring and a desire to help.
no code implementations • 25 Dec 2020 • Anuradha Welivita, Yubo Xie, Pearl Pu
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.
no code implementations • ACL 2021 • Yubo Xie, Junze Li, Pearl Pu
Humor recognition has been widely studied as a text classification problem using data-driven approaches.
1 code implementation • COLING 2020 • Anuradha Welivita, Pearl Pu
Our goal is to produce a large-scale taxonomy for empathetic response intents.
1 code implementation • 15 Aug 2019 • Yubo Xie, Ekaterina Svikhnushina, Pearl Pu
Open-domain dialog systems (also known as chatbots) have increasingly drawn attention in natural language processing.