About: Neural Query-Biased Abstractive Summarization Using Copying Mechanism

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

About: Neural Query-Biased Abstractive Summarization Using Copying Mechanism Goto Sponge NotDistinct Permalink

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

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Neural Query-Biased Abstractive Summarization Using Copying Mechanism
Creator	Chen, Hsin-Hsi Huang, Hen-Hsen Ishigaki, Tatsuya Okumura, Manabu Takamura, Hiroya
Source	PMC
abstract	This paper deals with the query-biased summarization task. Conventional non-neural network-based approaches have achieved better performance by primarily including the words overlapping between the source and the query in the summary. However, recurrent neural network (RNN)-based approaches do not explicitly model this phenomenon. Therefore, we model an RNN-based query-biased summarizer to primarily include the overlapping words in the summary, using a copying mechanism. Experimental results, in terms of both automatic evaluation with ROUGE and manual evaluation, show that the strategy to include the overlapping words also works well for neural query-biased summarizers.
has issue date	2020-03-24(xsd:dateTime)
bibo:doi	10.1007/978-3-030-45442-5_22
has license	no-cc
sha1sum (hex)	589f0114d0c048690d0260bd451d6bb710309670
schema:url	https://doi.org/10.1007/978-3-030-45442-5_22
resource representing a document's title	Neural Query-Biased Abstractive Summarization Using Copying Mechanism
has PubMed Central identifier	PMC7148071
schema:publication	Advances in Information Retrieval
resource representing a document's body	covid:589f0114d0c048690d0260bd451d6bb710309670#body_text
is schema:about of	named entity 'Neural' named entity 'BIASED' named entity 'MANUAL' named entity 'OVERLAPPING' named entity 'INCLUDE' named entity 'This' named entity 'probability' named entity 'vector' named entity 'word embeddings' named entity 'learning rate' named entity 'bootstrap resampling' named entity 'strategy' named entity 'copying mechanism' named entity 'Abstractive' named entity 'evaluation' named entity 'Objective Function' named entity 'RNN' named entity 'weighted average' named entity 'probability distribution' named entity 'training data' named entity 'neural network' named entity 'set of words' named entity 'probability' named entity 'vector' named entity 'probability distribution' named entity 'vector' named entity 'probability' named entity 'LSTM' named entity 'statistically significant' named entity 'bootstrap resampling' named entity 'search engines' named entity 'training data' named entity 'simple encoder' named entity 'LSTM' named entity 'recurrent neural network' named entity 'probability' named entity 'training data' named entity 'vector' named entity 'vector' named entity 'RNN' named entity 'probability distribution' named entity 'softmax function' named entity '0.9' named entity 'matrices' named entity 'one-hot' named entity 'LSTM' named entity 'probability distribution' named entity 'GloVe' named entity 'LSTM' named entity 'word embedding' named entity 'art model' named entity 'matrices' named entity 'LSTM' named entity 'vector' named entity 'RNN' named entity 'sigmoid function' named entity 'set of words' named entity 'vector' named entity 'document summarization' named entity 'matrices' named entity 'RNN' named entity 'probability' named entity 'probability distribution' named entity 'dot product' named entity 'probability distribution' named entity 'statistically significant' named entity 'dimensional weight' named entity 'Long Short-term Memory' named entity 'neural network' named entity 'recurrent neural network' named entity 'Copying Mechanism' named entity 'WORKS' named entity 'SUMMARY' named entity 'HAVE' named entity 'TASK' named entity 'Experimental results' named entity 'RNN' named entity 'WORDS' named entity 'PERFORMANCE'

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