The Open UniversitySkip to content
 

End-to-End Quantum-like Language Models with Application to Question Answering

Zhang, Peng; Niu, Jiabin; Su, Zhan; Wang, Benyou; Ma, Liqun and Song, Dawei (2018). End-to-End Quantum-like Language Models with Application to Question Answering. In: 32nd AAAI Conference on Artificial Intelligence (AAAI-18), 2-7 February 2018, New Orleans, Louisiana, USA, Association for the Advancement of Artificial Intelligence.

Full text available as:
[img]
Preview
PDF (Version of Record) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview
URL: https://aaai.org/Conferences/AAAI-18/
Google Scholar: Look up in Google Scholar

Abstract

Language Modeling (LM) is a fundamental research topic ina range of areas. Recently, inspired by quantum theory, a novel Quantum Language Model (QLM) has been proposed for Information Retrieval (IR). In this paper, we aim to broaden the theoretical and practical basis of QLM. We develop a Neural Network based Quantum-like Language Model (NNQLM) and apply it to Question Answering. Specifically, based on word embeddings, we design a new density matrix, which represents a sentence (e.g., a question or an answer) and encodes a mixture of semantic subspaces. Such a density matrix, together with a joint representation of the question and the answer, can be integrated into neural network architectures (e.g., 2-dimensional convolutional neural networks). Experiments on the TREC-QA and WIKIQA datasets have verified the effectiveness of our proposed models.

Item Type: Conference or Workshop Item
Copyright Holders: 2018 Association for the Advancement of Artificial Intelligence
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Research Group: Centre for Research in Computing (CRC)
Item ID: 52878
Depositing User: Dawei Song
Date Deposited: 15 Jan 2018 10:59
Last Modified: 15 Jan 2018 10:59
URI: http://oro.open.ac.uk/id/eprint/52878
Share this page:

Download history for this item

These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU