Abstract
This article surveys resource-light monolingual approaches to morphological analysis and tagging. While supervised analyzers and taggers are very accurate, they are extremely expensive to create. Therefore, most of the world languages and dialects have no realistic prospect for morphological tools created in this way. The weakly-supervised approaches aim to minimize time, expertise and/or financial cost needed for their development. We discuss the algorithms and their performance considering issues such as accuracy, portability, development time and granularity of the output.
| Original language | English |
|---|---|
| Pages (from-to) | 622-634 |
| Number of pages | 13 |
| Journal | Linguistics and Language Compass |
| Volume | 6 |
| Issue number | 10 |
| DOIs | |
| State | Published - 1 Jan 2012 |
Fingerprint
Cite this
}
Resource-Light Approaches to Computational Morphology Part 1 : Monolingual Approaches. / Hana, Jirka; Feldman, Anna.
In: Linguistics and Language Compass, Vol. 6, No. 10, 01.01.2012, p. 622-634.Research output: Contribution to journal › Article › Research › peer-review
TY - JOUR
T1 - Resource-Light Approaches to Computational Morphology Part 1
T2 - Monolingual Approaches
AU - Hana, Jirka
AU - Feldman, Anna
PY - 2012/1/1
Y1 - 2012/1/1
N2 - This article surveys resource-light monolingual approaches to morphological analysis and tagging. While supervised analyzers and taggers are very accurate, they are extremely expensive to create. Therefore, most of the world languages and dialects have no realistic prospect for morphological tools created in this way. The weakly-supervised approaches aim to minimize time, expertise and/or financial cost needed for their development. We discuss the algorithms and their performance considering issues such as accuracy, portability, development time and granularity of the output.
AB - This article surveys resource-light monolingual approaches to morphological analysis and tagging. While supervised analyzers and taggers are very accurate, they are extremely expensive to create. Therefore, most of the world languages and dialects have no realistic prospect for morphological tools created in this way. The weakly-supervised approaches aim to minimize time, expertise and/or financial cost needed for their development. We discuss the algorithms and their performance considering issues such as accuracy, portability, development time and granularity of the output.
UR - http://www.scopus.com/inward/record.url?scp=84867299275&partnerID=8YFLogxK
U2 - 10.1002/lnc3.358
DO - 10.1002/lnc3.358
M3 - Article
VL - 6
SP - 622
EP - 634
JO - Linguistics and Language Compass
JF - Linguistics and Language Compass
SN - 1749-818X
IS - 10
ER -