KSU at SemEval-2019 Task 3: Hybrid Features for Emotion Recognition in Textual Conversation
| Autor: | Mohamed El Bachir Menai, Nourah Alswaidan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry media_common.quotation_subject 05 social sciences 050301 education 050801 communication & media studies computer.software_genre Convolutional neural network SemEval Task (project management) 0508 media and communications Mood Conversation Emotion recognition Meaning (existential) Artificial intelligence business 0503 education computer Natural language processing media_common |
| Zdroj: | SemEval@NAACL-HLT |
| DOI: | 10.18653/v1/s19-2041 |
| Popis: | We proposed a model to address emotion recognition in textual conversation based on using automatically extracted features and human engineered features. The proposed model utilizes a fast gated-recurrent-unit backed by CuDNN, and a convolutional neural network to automatically extract features. The human engineered features take the frequency-inverse document frequency of semantic meaning and mood tags extracted from SinticNet. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|