Abstract
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| Publication status | Unpublished - 2017 |
Fingerprint
Cite this
}
Keyphrase extraction: from distributional feature engineering to distributed semantic composition. / Wang, Rui.
2017.Research output: Thesis › Doctoral Thesis
TY - THES
T1 - Keyphrase extraction: from distributional feature engineering to distributed semantic composition
AU - Wang, Rui
PY - 2017
Y1 - 2017
N2 - 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 datasetdependent and failing to capture the semantic meanings of phrases and documents. This research investigated extensively onthe current solutions and built on the most recent success of deep neural networks in natural language processing to mimic thehuman cognitive process of keyphrase identification. A number of novel models to learn the meaning of phrases and documentshave been developed and evaluated, achieving the state-of-the-art performance.
AB - 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 datasetdependent and failing to capture the semantic meanings of phrases and documents. This research investigated extensively onthe current solutions and built on the most recent success of deep neural networks in natural language processing to mimic thehuman cognitive process of keyphrase identification. A number of novel models to learn the meaning of phrases and documentshave been developed and evaluated, achieving the state-of-the-art performance.
KW - automatic keyphrase extraction
KW - natural language processing
KW - deep neural networks
KW - semantic compositionality
U2 - 10.4225/23/5a6547885d4f6
DO - 10.4225/23/5a6547885d4f6
M3 - Doctoral Thesis
ER -