@inproceedings{chitez-etal-2024-towards-romanian,
title = "Towards a {R}omanian Phrasal Academic Lexicon",
author = "Chitez, Madalina and
Bucur, Ana-Maria and
Dinca, Andreea and
Rogobete, Roxana",
booktitle = "Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)",
month = sep,
year = "2024",
address = "Sofia, Bulgaria",
publisher = "Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences",
url = "https://aclanthology.org/2024.clib-1.10/",
pages = "106--112",
abstract = "The lack of NLP based research studies on academic writing in Romania results in an unbalanced development of automatic support tools in Romanian compared to other languages, such as English. For this study, we use Romanian subsets of two bilingual academic writing corpora: the ROGER corpus, consisting of university student papers, and the EXPRES corpus, composed of expert research articles. Working with the Romanian Academic Word List / RoAWL, we present two phrase extraction phases: (i) use Ro-AWL words as node words to extract collocations according to the thresholds of statistical measures and (ii) classify extracted phrases into general versus domain-specific multi-word units. We show how manual rhetorical function annotation of resulting phrases can be combined with automatic function detection. The comparison between academic phrases in ROGER and EXPRES validates the final phrase list. The Romanian phrasal academic lexicon (ROPAL), similar to the Oxford Phrasal Academic Lexicon (OPAL), is a written academic phrase lexicon for Romanian language made available for academic use and further research or applications."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chitez-etal-2024-towards-romanian">
<titleInfo>
<title>Towards a Romanian Phrasal Academic Lexicon</title>
</titleInfo>
<name type="personal">
<namePart type="given">Madalina</namePart>
<namePart type="family">Chitez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana-Maria</namePart>
<namePart type="family">Bucur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreea</namePart>
<namePart type="family">Dinca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roxana</namePart>
<namePart type="family">Rogobete</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)</title>
</titleInfo>
<originInfo>
<publisher>Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences</publisher>
<place>
<placeTerm type="text">Sofia, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The lack of NLP based research studies on academic writing in Romania results in an unbalanced development of automatic support tools in Romanian compared to other languages, such as English. For this study, we use Romanian subsets of two bilingual academic writing corpora: the ROGER corpus, consisting of university student papers, and the EXPRES corpus, composed of expert research articles. Working with the Romanian Academic Word List / RoAWL, we present two phrase extraction phases: (i) use Ro-AWL words as node words to extract collocations according to the thresholds of statistical measures and (ii) classify extracted phrases into general versus domain-specific multi-word units. We show how manual rhetorical function annotation of resulting phrases can be combined with automatic function detection. The comparison between academic phrases in ROGER and EXPRES validates the final phrase list. The Romanian phrasal academic lexicon (ROPAL), similar to the Oxford Phrasal Academic Lexicon (OPAL), is a written academic phrase lexicon for Romanian language made available for academic use and further research or applications.</abstract>
<identifier type="citekey">chitez-etal-2024-towards-romanian</identifier>
<location>
<url>https://aclanthology.org/2024.clib-1.10/</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>106</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Romanian Phrasal Academic Lexicon
%A Chitez, Madalina
%A Bucur, Ana-Maria
%A Dinca, Andreea
%A Rogobete, Roxana
%S Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)
%D 2024
%8 September
%I Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences
%C Sofia, Bulgaria
%F chitez-etal-2024-towards-romanian
%X The lack of NLP based research studies on academic writing in Romania results in an unbalanced development of automatic support tools in Romanian compared to other languages, such as English. For this study, we use Romanian subsets of two bilingual academic writing corpora: the ROGER corpus, consisting of university student papers, and the EXPRES corpus, composed of expert research articles. Working with the Romanian Academic Word List / RoAWL, we present two phrase extraction phases: (i) use Ro-AWL words as node words to extract collocations according to the thresholds of statistical measures and (ii) classify extracted phrases into general versus domain-specific multi-word units. We show how manual rhetorical function annotation of resulting phrases can be combined with automatic function detection. The comparison between academic phrases in ROGER and EXPRES validates the final phrase list. The Romanian phrasal academic lexicon (ROPAL), similar to the Oxford Phrasal Academic Lexicon (OPAL), is a written academic phrase lexicon for Romanian language made available for academic use and further research or applications.
%U https://aclanthology.org/2024.clib-1.10/
%P 106-112
Markdown (Informal)
[Towards a Romanian Phrasal Academic Lexicon](https://aclanthology.org/2024.clib-1.10/) (Chitez et al., CLIB 2024)
ACL
- Madalina Chitez, Ana-Maria Bucur, Andreea Dinca, and Roxana Rogobete. 2024. Towards a Romanian Phrasal Academic Lexicon. In Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024), pages 106–112, Sofia, Bulgaria. Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences.