LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues
| Autor: | Marc Dymetman, Jean-Michel Renders, Phong Le |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer science business.industry 05 social sciences 050301 education 010501 environmental sciences computer.software_genre 01 natural sciences Mixture of experts Artificial Intelligence (cs.AI) Artificial intelligence Language model business 0503 education computer Computation and Language (cs.CL) Natural language processing 0105 earth and related environmental sciences |
| Zdroj: | Rep4NLP@ACL |
| DOI: | 10.48550/arxiv.1605.01652 |
| Popis: | We introduce an LSTM-based method for dynamically integrating several wordprediction experts to obtain a conditional language model which can be good simultaneously at several subtasks. We illustrate this general approach with an application to dialogue where we integrate a neural chat model, good at conversational aspects, with a neural question-answering model, good at retrieving precise information from a knowledge-base, and show how the integration combines the strengths of the independent components. We hope that this focused contribution will attract attention on the benefits of using such mixtures of experts in NLP and dialogue systems specifically. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|