Query-Based Keyphrase Extraction from Long Documents

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU145669" target="_blank" >RIV/00216305:26230/22:PU145669 - isvavai.cz</a>
Result on the web
<a href="https://journals.flvc.org/FLAIRS/article/view/130737" target="_blank" >https://journals.flvc.org/FLAIRS/article/view/130737</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.32473/flairs.v35i.130737" target="_blank" >10.32473/flairs.v35i.130737</a>

Result language
angličtina
Original language name
Query-Based Keyphrase Extraction from Long Documents
Original language description
Transformer-based architectures in natural language processing force input size limits that can be problematic when long documents need to be processed. This paper overcomes this issue for keyphrase extraction by chunking the long documents while keeping a global context as a query defining the topic for which relevant keyphrases should be extracted. The developed system employs a pre-trained BERT model and adapts it to estimate the probability that a given text span forms a keyphrase. We experimented using various context sizes on two popular datasets, Inspec and SemEval, and a large novel dataset. The presented results show that a shorter context with a query overcomes a longer one without the query on long documents.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project
<a href="/en/project/FW03010656" target="_blank" >FW03010656: Multilingual assistant for searching, analysing and processing information and decision support</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)