Affect-LM: A Neural Language Model for Customizable Affective Text Generation
This work addresses the challenge of generating emotionally customizable text for applications in conversational AI, though it is incremental as it extends existing LSTM models.
The authors tackled the problem of integrating affective information into neural language models for text generation, resulting in Affect-LM, which customizes emotional content in sentences and improves language model prediction, as shown by perception studies and perplexity experiments.
Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research in this direction but the problem of integrating state-of-the-art neural language models with affective information remains an area ripe for exploration. In this paper, we propose an extension to an LSTM (Long Short-Term Memory) language model for generating conversational text, conditioned on affect categories. Our proposed model, Affect-LM enables us to customize the degree of emotional content in generated sentences through an additional design parameter. Perception studies conducted using Amazon Mechanical Turk show that Affect-LM generates naturally looking emotional sentences without sacrificing grammatical correctness. Affect-LM also learns affect-discriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.