Towards Simple but Efficient Next Utterance Ranking
| Autor: | Nicolas Hernandez, Basma El Amel Boussaha, Emmanuel Morin, Christine Jacquin |
|---|---|
| Přispěvatelé: | Traitement Automatique du Langage Naturel (TALN ), Laboratoire des Sciences du Numérique de Nantes (LS2N), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS), PASTEL, Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Sequence
General Computer Science Computer science business.industry 020206 networking & telecommunications Context (language use) 02 engineering and technology computer.software_genre 01 natural sciences Ranking (information retrieval) [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] Semantic similarity Best response 0103 physical sciences Converse 0202 electrical engineering electronic engineering information engineering Relevance (information retrieval) Artificial intelligence business 010301 acoustics computer Word (computer architecture) Natural language processing ComputingMilieux_MISCELLANEOUS |
| Zdroj: | 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing) 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), Apr 2019, La Rochelle, France |
| Popis: | Retrieval-based dialogue systems converse with humans by ranking candidate responses according to their relevance to the history of the conversation (context). Recent studies either match the context with the response on only sequence level or use complex architectures to match them on the word and sequence levels. We show that both information levels are important and that a simple architecture can capture them effectively. We propose an end to endmulti level response retrieval dialogue system. Our model learns to match the context with the best response by computing their semantic similarity on the word and sequence levels. Empirical evaluation on two dialogue datasets shows that our model outperforms several state of the art systems and performs as good as the best system while being conceptually simpler. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|