Affective Neural Response Generation
This addresses the limitation of existing models in generating emotionally engaging dialogue, which is incremental as it builds on standard encoder-decoder architectures.
The paper tackled the problem of neural conversational models ignoring affective content by proposing three novel methods to incorporate emotional aspects into LSTM encoder-decoder models, resulting in improved conversational prowess with more emotionally rich, interesting, and natural responses.
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.