University of Cambridge
Structured Learning with Inexact Search: Advances in Shift-Reduce CCG Parsing
Abstract
dc:description.abstractStatistical shift-reduce parsing involves the interplay of representation learning, structured learning, and inexact search. This dissertation considers approaches that tightly integrate these three elements and explores three novel models for shift-reduce CCG parsing. First, I develop a dependency model, in which the selection of shift-reduce action sequences producing a dependency structure is treated as a hidden variable; the key components of the model are a dependency oracle and a learning algorithm that integrates the dependency oracle, the structured perceptron, and beam search. Second, I present expected F-measure training and show how to derive a globally normalized RNN model, in which beam search is naturally incorporated and used in conjunction with the objective to learn shift-reduce action sequences optimized for the final evaluation metric. Finally, I describe an LSTM model that is able to construct parser state representations incrementally by following the shift-reduce syntactic derivation process; I show expected F-measure training, which is agnostic to the underlying neural network, can be applied in this setting to obtain globally normalized greedy and beam-search LSTM shift-reduce parsers.
Degree
thesis:*- Name dc:type.qualificationname
- Doctor of Philosophy (PhD)
- Level dc:type.qualificationlevel
- Doctoral
- Grantor dc:publisher.institution
- University of Cambridge
- Year dc:date.issued
- 2017
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Xu, Wenduan
- Advisor dc:contributor.advisor
-
- Clark, Stephen
Subjects
dc:subject × 7Rights
dc:rightsIdentifiers
dc:identifier.*- DOI dc:identifier.doi
- https://doi.org/10.17863/CAM.16866
- OAI identifier oai:identifier
- oai:www.repository.cam.ac.uk:1810/270026