Emotionally-Triggered Short Text Conversation using Attention-Based Sequence Generation Models

摘要

Emotional Intelligence is a eld from which awareness is heavily being raised. Coupled withlanguage generation, one expects to further humanize the machine and be a step closer to the user by generating responses that are consistent with a specfic emotion. The analysis of sentimentwithin documents or sentences have been widely studied and improved while the generation of emotional content remains under-researched. Meanwhile, generative models have recently known series of improvements thanks to Generative Adversarial Network (GAN). Promising results are frequently reported in both natural language processing and computer vision. However, when applied to text generation, adversarial learning may lead to poor quality sentences and mode collapse. In this paper, we leverage one-round data conversation from social media to propose a novel approach in order to generate grammatically-correct-and-emotional-consistent answers for Short-Text Conversation task (STC-3) for NTCIR-14 workshop. We make use of an Attention based Sequence-to-Sequence as our generator, inspired from StarGAN framework. We provide emotion embeddings and direct feedback from an emotion classi er to guide the generator. To avoid the aforementioned issues with adversarial networks, we alternatively train our generator using maximum likelihood and adversarial loss.