We take a novel approach to rapid, low-cost development of morpho-syntactically annotated resources without using parallel corpora or bilingual lexicons. The overall research question is how to exploit language resources and properties to facilitate and automate the creation of morphologically annotated corpora for new languages. This portability issue is especially relevant to minority languages, for which such resources are likely to remain unavailable in the foreseeable future. We compare the performance of our system on languages that belong to different language families (Romance vs. Slavic), as well as different language pairs within the same language family (Portuguese via Spanish vs. Catalan via Spanish). We show that across language families, the most difficult category is the category of nominals (the noun homonymy is challenging for morphological analysis and the order variation of adjectives within a sentence makes it challenging to create a realiable model), whereas different language families present different challenges with respect to their morpho-syntactic descriptions: for the Slavic languages, case is the most challenging category; for the Romance languages, gender is more challenging than case. In addition, we present an alternative evaluation metric for our system, where we measure how much human labor will be needed to convert the result of our tagging to a high precision annotated resource.
[1]
Terence Wade,et al.
A Comprehensive Russian Grammar
,
1992
.
[2]
Nicolau Dols,et al.
Catalan: A Comprehensive Grammar
,
1999
.
[3]
Jan Haji,et al.
Morphological and Syntactic Tagging of the Prague Dependency Treebank
,
1999
.
[4]
David Yarowsky,et al.
Minimally Supervised Morphological Analysis by Multimodal Alignment
,
2000,
ACL.
[5]
Jan Hajic,et al.
Morphological Tagging: Data vs. Dictionaries
,
2000,
ANLP.
[6]
Thorsten Brants,et al.
TnT – A Statistical Part-of-Speech Tagger
,
2000,
ANLP.
[7]
Mário A. Perini,et al.
Modern Portuguese: A Reference Grammar
,
2002
.
[8]
Chris Brew,et al.
A Resource-light Approach to Russian Morphology: Tagging Russian using Czech resources
,
2004,
EMNLP.
[9]
Chris Brew,et al.
Tagging Portuguese with a Spanish tagger using cognates
,
2006
.
[10]
Chris Brew,et al.
Experiments in Cross-Language Morphological Annotation Transfer
,
2006,
CICLing.
[11]
Jirka Hana.
KNOWLEDGE- AND LABOR-LIGHT MORPHOLOGICAL ANALYSIS 1
,
2008
.