Which Model Should We Use for a Real-World Conversational Dialogue System? a Cross-Language Relevance Model or a Deep Neural Net?

Which Model Should We Use for a Real-World Conversational Dialogue System? a Cross-Language Relevance Model or a Deep Neural Net? Seyed Hossein Alavi author Anton Leuski author David Traum author 2020-may text English eng Proceedings of The 12th Language Resources and Evaluation Conference European Language Resources Association Marseille, France conference publication 979-10-95546-34-4 We compare two models for corpus-based selection of dialogue responses: one based on cross-language relevance with a cross-language LSTM model. Each model is tested on multiple corpora, collected from two different types of dialogue source material. Results show that while the LSTM model performs adequately on a very large corpus (millions of utterances), its performance is dominated by the cross-language relevance model for a more moderate-sized corpus (ten thousands of utterances). alavi-etal-2020-model https://www.aclweb.org/anthology/2020.lrec-1.92 2020-may 735 742