國立虎尾科技大學 |

From Complex Sentences to a Formal Semantic Representation using Syntactic Text Simplification and Open Information Extraction

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	From Complex Sentences to a Formal Semantic Representation using Syntactic Text Simplification and Open Information Extraction/ by Christina Niklaus.
作者:	Niklaus, Christina.
面頁冊數:	XLI, 318 p. 106 illus., 58 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Programming Language. -
電子資源:	https://doi.org/10.1007/978-3-658-38697-9
ISBN:	9783658386979

From Complex Sentences to a Formal Semantic Representation using Syntactic Text Simplification and Open Information Extraction
Niklaus, Christina.

From Complex Sentences to a Formal Semantic Representation using Syntactic Text Simplification and Open Information Extraction[electronic resource] /by Christina Niklaus. - 1st ed. 2022. - XLI, 318 p. 106 illus., 58 illus. in color.online resource.

Background -- Discourse-Aware Sentence Splitting -- Open Information Extraction -- Evaluation -- Conclusion.

This work presents a discourse-aware Text Simplification approach that splits and rephrases complex English sentences within the semantic context in which they occur. Based on a linguistically grounded transformation stage, complex sentences are transformed into shorter utterances with a simple canonical structure that can be easily analyzed by downstream applications. To avoid breaking down the input into a disjointed sequence of statements that is difficult to interpret, the author incorporates the semantic context between the split propositions in the form of hierarchical structures and semantic relationships, thus generating a novel representation of complex assertions that puts a semantic layer on top of the simplified sentences. In a second step, she leverages the semantic hierarchy of minimal propositions to improve the performance of Open IE frameworks. She shows that such systems benefit in two dimensions. First, the canonical structure of the simplified sentences facilitates the extraction of relational tuples, leading to an improved precision and recall of the extracted relations. Second, the semantic hierarchy can be leveraged to enrich the output of existing Open IE approaches with additional meta-information, resulting in a novel lightweight semantic representation for complex text data in the form of normalized and context-preserving relational tuples. About the author Christina Niklaus is an Assistant Professor in Computer Science at the University of St.Gallen with a focus on Data Science and NLP. .

ISBN: 9783658386979

Standard No.: 10.1007/978-3-658-38697-9doiSubjects--Topical Terms:

1365750
Programming Language.

LC Class. No.: P98-98.5

Dewey Class. No.: 410.285

From Complex Sentences to a Formal Semantic Representation using Syntactic Text Simplification and Open Information Extraction
LDR:03014nam a22003855i 4500 001 1082553
003 DE-He213
005 20220829134616.0
007 cr nn 008mamaa
008 221228s2022 gw | s |||| 0|eng d
020 $a 9783658386979 $9 978-3-658-38697-9
024 7 $a 10.1007/978-3-658-38697-9 $2 doi
035 $a 978-3-658-38697-9
050 4 $a P98-98.5
072 7 $a CFX $2 bicssc
072 7 $a LAN009000 $2 bisacsh
072 7 $a CFX $2 thema
082 0 4 $a 410.285 $2 23
100 1 $a Niklaus, Christina. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1388268
245 1 0 $a From Complex Sentences to a Formal Semantic Representation using Syntactic Text Simplification and Open Information Extraction $h [electronic resource] / $c by Christina Niklaus.
250 $a 1st ed. 2022.
264 1 $a Wiesbaden : $b Springer Fachmedien Wiesbaden : $b Imprint: Springer Vieweg, $c 2022.
300 $a XLI, 318 p. 106 illus., 58 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
505 0 $a Background -- Discourse-Aware Sentence Splitting -- Open Information Extraction -- Evaluation -- Conclusion.
520 $a This work presents a discourse-aware Text Simplification approach that splits and rephrases complex English sentences within the semantic context in which they occur. Based on a linguistically grounded transformation stage, complex sentences are transformed into shorter utterances with a simple canonical structure that can be easily analyzed by downstream applications. To avoid breaking down the input into a disjointed sequence of statements that is difficult to interpret, the author incorporates the semantic context between the split propositions in the form of hierarchical structures and semantic relationships, thus generating a novel representation of complex assertions that puts a semantic layer on top of the simplified sentences. In a second step, she leverages the semantic hierarchy of minimal propositions to improve the performance of Open IE frameworks. She shows that such systems benefit in two dimensions. First, the canonical structure of the simplified sentences facilitates the extraction of relational tuples, leading to an improved precision and recall of the extracted relations. Second, the semantic hierarchy can be leveraged to enrich the output of existing Open IE approaches with additional meta-information, resulting in a novel lightweight semantic representation for complex text data in the form of normalized and context-preserving relational tuples. About the author Christina Niklaus is an Assistant Professor in Computer Science at the University of St.Gallen with a focus on Data Science and NLP. .
650 2 4 $a Programming Language. $3 1365750
650 2 4 $a Natural Language Processing (NLP). $3 1254293
650 1 4 $a Computational Linguistics. $3 670080
650 0 $a Programming languages (Electronic computers). $3 1127615
650 0 $a Natural language processing (Computer science). $3 802180
650 0 $a Computational linguistics. $3 555811
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783658386962
776 0 8 $i Printed edition: $z 9783658386986
856 4 0 $u https://doi.org/10.1007/978-3-658-38697-9
912 $a ZDB-2-EDA
912 $a ZDB-2-SXED
950 $a Education (SpringerNature-41171)
950 $a Education (R0) (SpringerNature-43721)