Affect-LM: A Neural Language Model for Customizable Affective Text Generation (bibtex)
by Sayan Ghosh, Mathieu Chollet, Eugene Laksana, Louis-Philippe Morency, Stefan Scherer
Abstract:
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 affectdiscriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.
Reference:
Affect-LM: A Neural Language Model for Customizable Affective Text Generation (Sayan Ghosh, Mathieu Chollet, Eugene Laksana, Louis-Philippe Morency, Stefan Scherer), In Proceedings of the Annual Meeting of the Association for Computational Linguistics 2017, arxiv.org, 2017.
Bibtex Entry:
@inproceedings{ghosh_affect-lm:_2017,
	address = {Vancouver, Canada},
	title = {Affect-{LM}: {A} {Neural} {Language} {Model} for {Customizable} {Affective} {Text} {Generation}},
	url = {https://arxiv.org/pdf/1704.06851.pdf},
	abstract = {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 affectdiscriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.},
	booktitle = {Proceedings of the {Annual} {Meeting} of the {Association} for {Computational} {Linguistics} 2017},
	publisher = {arxiv.org},
	author = {Ghosh, Sayan and Chollet, Mathieu and Laksana, Eugene and Morency, Louis-Philippe and Scherer, Stefan},
	month = jul,
	year = {2017},
	keywords = {Virtual Humans, UARC}
}
Powered by bibtexbrowser