I Know the Feeling: Learning to Converse with Empathy

By Hannah Rashkin, Eric Michael Smith, Margaret Li, Y-Lan Boureau. 2018

51 citations recorded by the source corpus.

Beyond understanding what is being discussed, human communication requires an awareness of what someone is feeling. One challenge for dialogue agents is being able to recognize feelings in the conversation partner and reply accordingly, a key communicative skill that is trivial for humans. Research in this area is made difficult by the paucity of large-scale publicly available datasets both for emotion and relevant dialogues. This work proposes a new task for empathetic dialogue generation and EmpatheticDialogues, a dataset of 25k conversations grounded in emotional contexts to facilitate training and evaluating dialogue systems. Our experiments indicate that models explicitly leveraging emotion predictions from previous utterances are perceived to be more empathetic by human evaluators, while improving on other metrics as well (e.g. perceived relevance of responses, BLEU scores).

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Towards a Human-like Open-Domain Chatbot (2020, background): “A limitation of our work is that it does not cover aspects such as empathy (Zhou et al., 2018; Rashkin et al., 2018).”
Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, background): “, 2018), including multiple persona-based chat applications (Shuster et al., 2018a,b; Rashkin et al., 2018).”
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems (2019, background): “Towards social and emotional coherence, previous works have investigated various features and loss functions based on emotion [32, 33, 13, 23].”
Emotionally-Aware Chatbots: A Survey (2019, methodology): “After getting all of the human judgement with diﬀerent criteria, some of these studies used a t-test to get the statistical signiﬁcance [23, 26], while some other used inter-annotator agreement measurement such as Fleiss Kappa [45, 65].”
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations (2018, background): “A conversational emotion recognition system can be used to generate appropriate responses by analyzing user emotions (Zhou et al., 2017; Rashkin et al., 2018).”
HappyBot: Generating Empathetic Dialogue Responses by Improving User Experience Look-ahead (2019, methodology): “MultiSeq The MultiSeq model is the multi-task model trained as in (Rashkin et al., 2018) by using the Bi-GRU encoder to jointly predict the emotion of context x.”
A survey on empathetic dialogue systems (2020, methodology): “, emotion classifier) could be employed to recognize the emotion labels [46, 54, 75, 9, 76].”