White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Leveraging structure for learning representations of words, sentences and knowledge bases

Komninos, Alexandros (2018) Leveraging structure for learning representations of words, sentences and knowledge bases. EngD thesis, University of York.

This is the latest version of this item.

[img]
Preview
Text
alexandros_komninos_engd_thesis.pdf - Examined Thesis (PDF)
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (2921Kb) | Preview

Abstract

This thesis presents work on learning representations of text and Knowledge Bases by taking into consideration their respective structures. The tasks for which the methods are developed and evaluated on are: Short-text classification, Word Sense Induction and Disambiguation, Knowledge Base Completion with linked text corpora, and large-scale Knowledge Base Question Answering. An introductory chapter states the aims and scope of the thesis, followed by a chapter on technical background and definitions. In chapter 3, the impact of dependency syntax on word representation learning in the context of short-text classification is investigated. A new definition of context in dependency graphs is proposed, which generalizes and extends previous definitions used in word representation learning. The resulting word and dependency feature embeddings are used together to represent dependency graph substructures in text classifiers. In chapter 4, a probabilistic latent variable model for Word Sense Induction and Disambiguation is presented. The model estimates sense clusters using pretrained continuous feature vectors of multiple context types: syntactic, local lexical and global lexical, while the number of sense clusters is determined by the Integrated Complete Likelihood criterion. A model for Knowledge Base Completion with linked text corpora is presented in chapter 5. The proposed model represents potential facts by merging subgraphs of the knowledge base with text through linked entities. The model learns to embed the merged graphs into a lower dimensional space and score the plausibility of the fact with a Multilayer Perceptron. Chapter 6 presents a system for Question Answering on Knowledge Bases. The system learns to decompose questions into entity and relation mentions and score their compatibility with queries on the knowledge base expressed as subgraphs. The model consists of several components trained jointly in order to match parts of the question with parts of a potential query by embedding their corresponding structures in lower dimensional spaces.

Item Type: Thesis (EngD)
Related URLs:
Academic Units: The University of York > Computer Science (York)
Identification Number/EthosID: uk.bl.ethos.759904
Depositing User: Mr Alexandros Komninos
Date Deposited: 23 Nov 2018 16:27
Last Modified: 19 Feb 2020 13:04
URI: http://etheses.whiterose.ac.uk/id/eprint/21616

Available Versions of this Item

  • Leveraging structure for learning representations of words, sentences and knowledge bases. (deposited 23 Nov 2018 16:27) [Currently Displayed]

You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.

Actions (repository staff only: login required)