1. Unsupervised Natural Question Answering with a Small Model
- Author
-
Sam Witteveen and Martin Andrews
- Subjects
FOS: Computer and information sciences ,Computer Science - Computation and Language ,Computer Science - Artificial Intelligence ,business.industry ,Computer science ,Factoid ,Short paper ,computer.software_genre ,Computer Science - Information Retrieval ,Artificial Intelligence (cs.AI) ,Question answering ,Natural (music) ,Unsupervised learning ,Language model ,Artificial intelligence ,Architecture ,business ,Computation and Language (cs.CL) ,computer ,Information Retrieval (cs.IR) ,Natural language processing - Abstract
The recent (2019-02) demonstration of the power of huge language models such as GPT-2 to memorise the answers to factoid questions raises questions about the extent to which knowledge is being embedded directly within these large models. This short paper describes an architecture through which much smaller models can also answer such questions - by making use of 'raw' external knowledge. The contribution of this work is that the methods presented here rely on unsupervised learning techniques, complementing the unsupervised training of the Language Model. The goal of this line of research is to be able to add knowledge explicitly, without extensive training., Accepted paper for FEVER workshop at EMNLP-IJCNLP 2019. (4 pages + references)
- Published
- 2019