Affective Neural Response Generation

2017/09/12 by Asghar, Nabiha, Poupart, Pascal, Hoey, Jesse +2 · 1 citation
#68T50 #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #I.2.7 #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.1709.03968

Abstract

Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content. We take a step in this direction by proposing three novel ways to incorporate affective/emotional aspects into long short term memory (LSTM) encoder-decoder neural conversation models: (1) affective word embeddings, which are cognitively engineered, (2) affect-based objective functions that augment the standard cross-entropy loss, and (3) affectively diverse beam search for decoding. Experiments show that these techniques improve the open-domain conversational prowess of encoder-decoder networks by enabling them to produce emotionally rich responses that are more interesting and natural.

Cited by

• Generative Intelligence Systems in the Flow of Group Emotions

Related

• Affect-LM: A Neural Language Model for Customizable Affective Text Generation
• An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss
• A Multi-Turn Emotionally Engaging Dialog Model
• Emotional Neural Language Generation Grounded in Situational Contexts
• Emotional Conversation Generation with Heterogeneous Graph Neural Network