Concept Extraction Using Pointer-Generator Networks
Concept extraction is crucial for a number of downstream applications. However, surprisingly enough, straightforward single token/nominal chunk-concept alignment or dictionary lookup techniques such as DBpedia Spotlight still prevail. We propose a generic open-domain OOV-oriented extractive model th...
Main Authors: | , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2008.11295 https://arxiv.org/abs/2008.11295 |
id |
ftdatacite:10.48550/arxiv.2008.11295 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2008.11295 2023-05-15T18:32:42+02:00 Concept Extraction Using Pointer-Generator Networks Shvets, Alexander Wanner, Leo 2020 https://dx.doi.org/10.48550/arxiv.2008.11295 https://arxiv.org/abs/2008.11295 unknown arXiv Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 CC-BY Computation and Language cs.CL FOS Computer and information sciences Article CreativeWork article Preprint 2020 ftdatacite https://doi.org/10.48550/arxiv.2008.11295 2022-03-10T15:47:48Z Concept extraction is crucial for a number of downstream applications. However, surprisingly enough, straightforward single token/nominal chunk-concept alignment or dictionary lookup techniques such as DBpedia Spotlight still prevail. We propose a generic open-domain OOV-oriented extractive model that is based on distant supervision of a pointer-generator network leveraging bidirectional LSTMs and a copy mechanism. The model has been trained on a large annotated corpus compiled specifically for this task from 250K Wikipedia pages, and tested on regular pages, where the pointers to other pages are considered as ground truth concepts. The outcome of the experiments shows that our model significantly outperforms standard techniques and, when used on top of DBpedia Spotlight, further improves its performance. The experiments furthermore show that the model can be readily ported to other datasets on which it equally achieves a state-of-the-art performance. : Contribution to the Proceedings of the 22nd International Conference on Knowledge Engineering and Knowledge Management (EKAW 2020). A link to the final authenticated publication will be added once it is available online. Keywords: Open-domain discourse texts, Concept extraction, Pointer-generator neural network, Distant supervision Article in Journal/Newspaper The Pointers DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computation and Language cs.CL FOS Computer and information sciences |
spellingShingle |
Computation and Language cs.CL FOS Computer and information sciences Shvets, Alexander Wanner, Leo Concept Extraction Using Pointer-Generator Networks |
topic_facet |
Computation and Language cs.CL FOS Computer and information sciences |
description |
Concept extraction is crucial for a number of downstream applications. However, surprisingly enough, straightforward single token/nominal chunk-concept alignment or dictionary lookup techniques such as DBpedia Spotlight still prevail. We propose a generic open-domain OOV-oriented extractive model that is based on distant supervision of a pointer-generator network leveraging bidirectional LSTMs and a copy mechanism. The model has been trained on a large annotated corpus compiled specifically for this task from 250K Wikipedia pages, and tested on regular pages, where the pointers to other pages are considered as ground truth concepts. The outcome of the experiments shows that our model significantly outperforms standard techniques and, when used on top of DBpedia Spotlight, further improves its performance. The experiments furthermore show that the model can be readily ported to other datasets on which it equally achieves a state-of-the-art performance. : Contribution to the Proceedings of the 22nd International Conference on Knowledge Engineering and Knowledge Management (EKAW 2020). A link to the final authenticated publication will be added once it is available online. Keywords: Open-domain discourse texts, Concept extraction, Pointer-generator neural network, Distant supervision |
format |
Article in Journal/Newspaper |
author |
Shvets, Alexander Wanner, Leo |
author_facet |
Shvets, Alexander Wanner, Leo |
author_sort |
Shvets, Alexander |
title |
Concept Extraction Using Pointer-Generator Networks |
title_short |
Concept Extraction Using Pointer-Generator Networks |
title_full |
Concept Extraction Using Pointer-Generator Networks |
title_fullStr |
Concept Extraction Using Pointer-Generator Networks |
title_full_unstemmed |
Concept Extraction Using Pointer-Generator Networks |
title_sort |
concept extraction using pointer-generator networks |
publisher |
arXiv |
publishDate |
2020 |
url |
https://dx.doi.org/10.48550/arxiv.2008.11295 https://arxiv.org/abs/2008.11295 |
genre |
The Pointers |
genre_facet |
The Pointers |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.48550/arxiv.2008.11295 |
_version_ |
1766216893869326336 |