About: Chinese Sentence Semantic Matching Based on Multi-Granularity Fusion Model

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

About: Chinese Sentence Semantic Matching Based on Multi-Granularity Fusion Model 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	Chinese Sentence Semantic Matching Based on Multi-Granularity Fusion Model
Creator	Li, Fangfang Zhang, Xu Lu, Wenpeng Wang, Shoujin Zhang, Guoqiang
Source	PMC
abstract	Sentence semantic matching is the cornerstone of many natural language processing tasks, including Chinese language processing. It is well known that Chinese sentences with different polysemous words or word order may have totally different semantic meanings. Thus, to represent and match the sentence semantic meaning accurately, one challenge that must be solved is how to capture the semantic features from the multi-granularity perspective, e.g., characters and words. To address the above challenge, we propose a novel sentence semantic matching model which is based on the fusion of semantic features from character-granularity and word-granularity, respectively. Particularly, the multi-granularity fusion intends to extract more semantic features to better optimize the downstream sentence semantic matching. In addition, we propose the equilibrium cross-entropy, a novel loss function, by setting mean square error (MSE) as an equilibrium factor of cross-entropy. The experimental results conducted on Chinese open data set demonstrate that our proposed model combined with binary equilibrium cross-entropy loss function is superior to the existing state-of-the-art sentence semantic matching models.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1007/978-3-030-47436-2_19
has license	no-cc
sha1sum (hex)	670f7dc7cc303a53c1027c285f4c839c4a7a3f03
schema:url	https://doi.org/10.1007/978-3-030-47436-2_19
resource representing a document's title	Chinese Sentence Semantic Matching Based on Multi-Granularity Fusion Model
has PubMed Central identifier	PMC7206256
schema:publication	Advances in Knowledge Discovery and Data Mining
resource representing a document's body	covid:670f7dc7cc303a53c1027c285f4c839c4a7a3f03#body_text
is schema:about of	named entity 'model' named entity 'accurately' named entity 'semantic matching' named entity 'MSE' named entity 'optimize' named entity 'TO EXTRACT' named entity 'INCLUDING' named entity 'SETTING' named entity 'KNOWN' named entity 'semantic' named entity 'polysemous' named entity 'match' named entity 'cross-entropy' named entity 'sentence' named entity 'sentence' named entity 'loss function' named entity 'semantic' named entity 'semantic meaning' named entity 'open data' named entity 'polysemous words' named entity 'superior' named entity 'MSE' named entity 'inference' named entity 'machine translation' named entity 'n-grams' named entity 'loss function' named entity 'MSE' named entity 'loss function' named entity 'feature extraction' named entity 'deep feature' named entity 'MSE' named entity 'MGF' named entity 'matrices' named entity 'semantic information' named entity 'fuzzy classification' named entity 'loss function' named entity 'convolutional neural network' named entity 'test set' named entity 'cross-entropy' named entity 'MGF' named entity 'deep feature' named entity 'loss function' named entity 'data set' named entity 'natural language understanding' named entity 'MGF' named entity 'neural network' named entity 'semantic feature' named entity 'semantic feature' named entity 'deep learning' named entity 'deep feature' named entity 'vectors' named entity 'MGF' named entity 'loss function' named entity 'sigmoid' named entity 'semantic feature' named entity 'early stopping' named entity 'LSTM' named entity 'semantic information' named entity 'vector representations' named entity 'Sigmoid function' named entity 'Chinese characters' named entity 'vectors' named entity 'NLP' named entity 'loss function' named entity 'MSE' named entity 'LSTMs' named entity 'cross-entropy' named entity 'long short term memory' named entity 'cross-entropy' named entity 'vectors' named entity 'question answering' named entity 'relu' named entity 'vectors' named entity 'loss function' named entity 'cross-entropy' named entity 'data set' named entity 'MGF' named entity 'natural language understanding' named entity 'concatenate'

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