This paper studies the Semantic Network Language Generation (SNLG), which is used to generate natural language from the information represented as Semantic Networks (SN). After a brief analysis of the challenges faced by SNLG, a Semantic Network Serialization Grammar (SNSG) is proposed to generate natural language from semantic networks. The SNSG is constituted by four components: (a) a semantic pattern approach to serializing a trivial semantic star into a language stream. (b) a transformative generation to serialize a trivial semantic tree by serializing semantic star recursively. (c) a procedure of trivialization to convert any complicated semantic star or semantic tree into composition of trivial semantic tree. (d) a mechanism of semantic pattern priority and semantic pattern network to guarantee a sentence generated from a semantic tree to be well formed. Based on the SNSG, a new approach of the content planning for SNLG is proposed to improve the content integrity. For discourse planning, a trivialization time splitting method is presented to make well-formed sentence, and a splitting time aggregation method is proposed to improve the readability of sentence. Finally a fully semantized Semantic Wiki system, the Natural Wiki, is developed to verify and demonstrate the theory and techniques addressed in this paper.
%0 Journal Article
%1 DaiZhangEtAl10www
%A Dai, Yintang
%A Zhang, Shiyong
%A Chen, Jidong
%A Chen, Tianyuan
%A Zhang, Wei
%D 2010
%J World Wide Web
%K v1205 springer paper ai language processing semantic knowledge text generation zzz.th.c4
%N 3
%P 307-341
%R 10.1007/s11280-010-0087-z
%T Semantic Network Language Generation based on a Semantic Networks Serialization Grammar
%V 13
%X This paper studies the Semantic Network Language Generation (SNLG), which is used to generate natural language from the information represented as Semantic Networks (SN). After a brief analysis of the challenges faced by SNLG, a Semantic Network Serialization Grammar (SNSG) is proposed to generate natural language from semantic networks. The SNSG is constituted by four components: (a) a semantic pattern approach to serializing a trivial semantic star into a language stream. (b) a transformative generation to serialize a trivial semantic tree by serializing semantic star recursively. (c) a procedure of trivialization to convert any complicated semantic star or semantic tree into composition of trivial semantic tree. (d) a mechanism of semantic pattern priority and semantic pattern network to guarantee a sentence generated from a semantic tree to be well formed. Based on the SNSG, a new approach of the content planning for SNLG is proposed to improve the content integrity. For discourse planning, a trivialization time splitting method is presented to make well-formed sentence, and a splitting time aggregation method is proposed to improve the readability of sentence. Finally a fully semantized Semantic Wiki system, the Natural Wiki, is developed to verify and demonstrate the theory and techniques addressed in this paper.
@article{DaiZhangEtAl10www,
abstract = {This paper studies the Semantic Network Language Generation (SNLG), which is used to generate natural language from the information represented as Semantic Networks (SN). After a brief analysis of the challenges faced by SNLG, a Semantic Network Serialization Grammar (SNSG) is proposed to generate natural language from semantic networks. The SNSG is constituted by four components: (a) a semantic pattern approach to serializing a trivial semantic star into a language stream. (b) a transformative generation to serialize a trivial semantic tree by serializing semantic star recursively. (c) a procedure of trivialization to convert any complicated semantic star or semantic tree into composition of trivial semantic tree. (d) a mechanism of semantic pattern priority and semantic pattern network to guarantee a sentence generated from a semantic tree to be well formed. Based on the SNSG, a new approach of the content planning for SNLG is proposed to improve the content integrity. For discourse planning, a trivialization time splitting method is presented to make well-formed sentence, and a splitting time aggregation method is proposed to improve the readability of sentence. Finally a fully semantized Semantic Wiki system, the Natural Wiki, is developed to verify and demonstrate the theory and techniques addressed in this paper.},
added-at = {2012-05-30T10:44:46.000+0200},
author = {Dai, Yintang and Zhang, Shiyong and Chen, Jidong and Chen, Tianyuan and Zhang, Wei},
biburl = {https://www.bibsonomy.org/bibtex/2b7915b557e6cdeee393152e0fddcae3d/flint63},
doi = {10.1007/s11280-010-0087-z},
file = {SpringerLink:2010/DaiZhangEtAl10www.pdf:PDF},
groups = {public},
interhash = {18e0065850f60db6a5c022bb40152ed8},
intrahash = {b7915b557e6cdeee393152e0fddcae3d},
issn = {1386-145X},
journal = {World Wide Web},
keywords = {v1205 springer paper ai language processing semantic knowledge text generation zzz.th.c4},
number = 3,
pages = {307-341},
timestamp = {2018-04-16T12:00:59.000+0200},
title = {Semantic Network Language Generation based on a Semantic Networks Serialization Grammar},
username = {flint63},
volume = 13,
year = 2010
}