Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mapping
The Research Article Abstract (RAA) has been the focus of numerous investigations within both the Systemic Functional Linguistics (SFL) and the Natural Language Processing (NLP) communities, and from the text generation and the text analysis/parsing perspectives. Given the complexity of the object o...
Guardado en:
| Autor principal: | |
|---|---|
| Lenguaje: | English |
| Publicado: |
Pontificia Universidad Católica de Valparaíso. Instituto de Literatura y Ciencias del Lenguaje
2006
|
| Materias: | |
| Acceso en línea: | http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-09342006000300001 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:scielo:S0718-09342006000300001 |
|---|---|
| record_format |
dspace |
| spelling |
oai:scielo:S0718-093420060003000012006-12-28Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mappingCastel,Víctor Natural Language Generation Natural Language Processing Systemic Functional Linguistics Corpus linguistics computational linguistics The Research Article Abstract (RAA) has been the focus of numerous investigations within both the Systemic Functional Linguistics (SFL) and the Natural Language Processing (NLP) communities, and from the text generation and the text analysis/parsing perspectives. Given the complexity of the object of study, however, there still is a need for extensive studies of the RAA that provide detailed, descriptive, corpus-based, formally defined, and computationally implemented generalizations on the relationship between context and language. These three conditions appear to be central to any Natural Language Generation (NLG) project whose long-term goal is to simultaneously model the systemic-functional unity and diversity found in RAAs and use the resulting model for the development of tools for interactive, rhetorical, and linguistic assistance in RAA writing. This is the ultimate goal of the RedACTe Project, one theoretical-descriptive result of which is hereby presented. The basic formal mechanism used by the Cardiff Grammar for the generation of text-sentences is adapted and extended to capture systematic correlations between higher (genre and register) and lower (lexical-grammar) strata features of RAAs of the RedACTe Projects discipline samples. Generation procedures are defined and implemented, both within any one stratum and between strata, for mapping genre onto semantics and semantics onto form, and for text construction.info:eu-repo/semantics/openAccessPontificia Universidad Católica de Valparaíso. Instituto de Literatura y Ciencias del LenguajeRevista signos v.39 n.62 20062006-01-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-09342006000300001en10.4067/S0718-09342006000300001 |
| institution |
Scielo Chile |
| collection |
Scielo Chile |
| language |
English |
| topic |
Natural Language Generation Natural Language Processing Systemic Functional Linguistics Corpus linguistics computational linguistics |
| spellingShingle |
Natural Language Generation Natural Language Processing Systemic Functional Linguistics Corpus linguistics computational linguistics Castel,Víctor Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mapping |
| description |
The Research Article Abstract (RAA) has been the focus of numerous investigations within both the Systemic Functional Linguistics (SFL) and the Natural Language Processing (NLP) communities, and from the text generation and the text analysis/parsing perspectives. Given the complexity of the object of study, however, there still is a need for extensive studies of the RAA that provide detailed, descriptive, corpus-based, formally defined, and computationally implemented generalizations on the relationship between context and language. These three conditions appear to be central to any Natural Language Generation (NLG) project whose long-term goal is to simultaneously model the systemic-functional unity and diversity found in RAAs and use the resulting model for the development of tools for interactive, rhetorical, and linguistic assistance in RAA writing. This is the ultimate goal of the RedACTe Project, one theoretical-descriptive result of which is hereby presented. The basic formal mechanism used by the Cardiff Grammar for the generation of text-sentences is adapted and extended to capture systematic correlations between higher (genre and register) and lower (lexical-grammar) strata features of RAAs of the RedACTe Projects discipline samples. Generation procedures are defined and implemented, both within any one stratum and between strata, for mapping genre onto semantics and semantics onto form, and for text construction. |
| author |
Castel,Víctor |
| author_facet |
Castel,Víctor |
| author_sort |
Castel,Víctor |
| title |
Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mapping |
| title_short |
Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mapping |
| title_full |
Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mapping |
| title_fullStr |
Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mapping |
| title_full_unstemmed |
Generating abstracts from genre structure through lexicogrammar: Modelling of feature selection and mapping |
| title_sort |
generating abstracts from genre structure through lexicogrammar: modelling of feature selection and mapping |
| publisher |
Pontificia Universidad Católica de Valparaíso. Instituto de Literatura y Ciencias del Lenguaje |
| publishDate |
2006 |
| url |
http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-09342006000300001 |
| work_keys_str_mv |
AT castelvictor generatingabstractsfromgenrestructurethroughlexicogrammarmodellingoffeatureselectionandmapping |
| _version_ |
1714201812478722048 |