2017 · 133 citations · 19 references
EngineeringPsycholinguisticsSpoken Dialog SystemCommunicationText MiningNatural Language ProcessingContext InformationComputational LinguisticsConversation AnalysisLanguage StudiesUser ContextMachine TranslationCognitive ScienceEmpirical StudyDialogue ManagementNatural Language InterfaceNlp TaskDialog SystemsConversational Recommender SystemContext More UsefulSpeech CommunicationGenerative Conversational SystemsContext ModelLinguistics
Generative conversational systems are gaining traction in NLP, yet no systematic comparison exists to determine how best to leverage context in dialog processing. The study empirically compares various dialog models to investigate how context information affects performance. We evaluate multiple context‑aware neural conversational models on dialog tasks, comparing their effectiveness. A variant that weights context vectors by relevance outperforms all other baselines.
Generative conversational systems are attracting increasing attention in natural language processing (NLP). Recently, researchers have noticed the importance of context information in dialog processing, and built various models to utilize context. However, there is no systematic comparison to analyze how to use context effectively. In this paper, we conduct an empirical study to compare various models and investigate the effect of context information in dialog systems. We also propose a variant that explicitly weights context vectors by context-query relevance, outperforming the other baselines.
19
Neural Responding Machine for Short-Text Conversation
Lifeng Shang, Zhengdong Lu, Hang Li · 2015 · 1K citations · Full text