Abstract
Automatic Keyphrase Extraction is the fundamental step underpinning many Natural Language Processing tasks. However,
the performance of the current solutions heavily relies on the selection of features, rendering the algorithms to be dataset
dependent and failing to capture the semantic meanings of phrases and documents. This research investigated extensively on
the current solutions and built on the most recent success of deep neural networks in natural language processing to mimic the
human cognitive process of keyphrase identification. A number of novel models to learn the meaning of phrases and documents
have been developed and evaluated, achieving the state-of-the-art performance.
the performance of the current solutions heavily relies on the selection of features, rendering the algorithms to be dataset
dependent and failing to capture the semantic meanings of phrases and documents. This research investigated extensively on
the current solutions and built on the most recent success of deep neural networks in natural language processing to mimic the
human cognitive process of keyphrase identification. A number of novel models to learn the meaning of phrases and documents
have been developed and evaluated, achieving the state-of-the-art performance.
Original language | English |
---|---|
Qualification | Doctor of Philosophy |
Awarding Institution |
|
Supervisors/Advisors |
|
Thesis sponsors | |
Award date | 9 Jan 2018 |
DOIs | |
Publication status | Unpublished - 2017 |