About: Keyphrase Extraction as Sequence Labeling Using Contextualized Embeddings

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Keyphrase Extraction as Sequence Labeling Using Contextualized Embeddings Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Keyphrase Extraction as Sequence Labeling Using Contextualized Embeddings
Creator	Zhang, Haimin Gosangi, Rakesh Kulkarni, Mayank Kumar, Yaman Mahata, Debanjan Ratn Shah, Rajiv Sahrawat, Dhruva Sharma, Agniv Stent, Amanda Zimmermann, Roger
Source	PMC
abstract	In this paper, we formulate keyphrase extraction from scholarly articles as a sequence labeling task solved using a BiLSTM-CRF, where the words in the input text are represented using deep contextualized embeddings. We evaluate the proposed architecture using both contextualized and fixed word embedding models on three different benchmark datasets, and compare with existing popular unsupervised and supervised techniques. Our results quantify the benefits of: (a) using contextualized embeddings over fixed word embeddings; (b) using a BiLSTM-CRF architecture with contextualized word embeddings over fine-tuning the contextualized embedding model directly; and (c) using domain-specific contextualized embeddings (SciBERT). Through error analysis, we also provide some insights into why particular models work better than the others. Lastly, we present a case study where we analyze different self-attention layers of the two best models (BERT and SciBERT) to better understand their predictions.
has issue date	2020-03-24(xsd:dateTime)
bibo:doi	10.1007/978-3-030-45442-5_41
has license	no-cc
sha1sum (hex)	a214c88feb818ad2a630e317c0c148cc3ed6259c
schema:url	https://doi.org/10.1007/978-3-030-45442-5_41
resource representing a document's title	Keyphrase Extraction as Sequence Labeling Using Contextualized Embeddings
has PubMed Central identifier	PMC7148038
schema:publication	Advances in Information Retrieval
resource representing a document's body	covid:a214c88feb818ad2a630e317c0c148cc3ed6259c#body_text
is schema:about of	named entity 'layers' named entity 'solved' named entity 'text' named entity 'word embeddings' named entity 'Labeling' named entity 'DEEP' named entity 'USING' named entity 'PARTICULAR' named entity 'SCIBERT' named entity 'PREDICTIONS' named entity 'LAYERS' named entity 'TASK' named entity 'INPUT' named entity 'WORD' named entity 'OUR' named entity 'PAPER' named entity 'ERROR ANALYSIS' named entity 'embeddings' named entity 'insights' named entity 'word embeddings' named entity 'scholarly' named entity 'existing' named entity 'predictions' named entity 'contextualized' named entity 'contextualized' named entity 'Sequence' named entity 'word embeddings' named entity 'case study' named entity 'stop word' named entity 'procedural language' named entity 'binary classification' named entity 'contextual embedding' named entity 'general purpose' named entity 'discrete-event simulation' named entity 'Wikipedia' named entity 'conjunctions' named entity 'metadata' named entity 'GPT-2' named entity 'n-grams' named entity 'object-oriented' named entity 'object-oriented' named entity 'scholarly articles' named entity 'object-oriented' named entity 'software projects' named entity 'object-oriented' named entity 'Sequence labeling' named entity 'object-oriented' named entity 'false negatives' named entity 'LRB' named entity 'vector' named entity 'Hydrozincite' named entity 'named entity' named entity 'k I' named entity 'noun phrases' named entity 'sequence labeling' named entity 'generation stage' named entity 'word embeddings' named entity 'knowledge base' named entity 'object-oriented' named entity 'SemEval' named entity 'contextual embedding' named entity 'affine transformation' named entity 'sequence labeling' named entity 'word embeddings' named entity 'domain-specific language' named entity 'binary classification' named entity 'Keyphrase extraction' named entity 'Experimental Settings' named entity 'Inspec' named entity 'procedural language' named entity 'SemEval' named entity 'corpora' named entity 'NLP' named entity 'object-oriented'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software