Explicitly conditioning response generation on predicted socio-emotional label sequences yields only small, mixed quality gains over direct generation, and the claimed benefit is confounded by a 10-candidate reranking setup.
CAiRE: An Empathetic Neural Chatbot
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we present an end-to-end empathetic conversation agent CAiRE. Our system adapts TransferTransfo (Wolf et al., 2019) learning approach that fine-tunes a large-scale pre-trained language model with multi-task objectives: response language modeling, response prediction and dialogue emotion detection. We evaluate our model on the recently proposed empathetic-dialogues dataset (Rashkin et al., 2019), the experiment results show that CAiRE achieves state-of-the-art performance on dialogue emotion detection and empathetic response generation.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems
Explicitly conditioning response generation on predicted socio-emotional label sequences yields only small, mixed quality gains over direct generation, and the claimed benefit is confounded by a 10-candidate reranking setup.