Difference between revisions of "User:Dmin1/Final project"
(→Evaluation) |
|||
| Line 12: | Line 12: | ||
=Evaluation= | =Evaluation= | ||
| + | In this implementation of Korean POS analyzer, I was able to analyze most of noun morphology correctly. However, as there were multiple level of suffixes that attaches to verbs in Korean, the analysis and construction of Verb alteration was not easy. | ||
| + | |||
| + | I observed that most of the errors come from either 1)lemmas not yet added or 2)failure to analyze different verb forms. | ||
| + | |||
==Coverage of corpora== | ==Coverage of corpora== | ||
| + | ==="Trained Corpus"=== | ||
| + | *kor.phrases.COURT.txt: | ||
| + | *kor.phrases.GENESIS.txt: | ||
| + | *kor.phrases.HIROHITO.txt: | ||
| + | *kor.phrases.ROH.txt: | ||
| + | *kor.phrases.STALIN.txt: | ||
| + | *kor.phrases.WIKI.txt: | ||
| + | |||
| + | ==="Test Corpus"==== | ||
| + | *Random 1200 (1): | ||
| + | *Random 1200 (2): | ||
| + | |||
==Precision and Recall== | ==Precision and Recall== | ||
| + | ===Using Random 1200 words from Wikipedia Dump=== | ||
| + | *Precision | ||
| + | *Recall | ||
=Repository= | =Repository= | ||
Revision as of 03:58, 9 May 2017
This page provides an overview and an evaluation of Korean Finite State Transducer I developed.
Contents
Motivation
For the final project, I decided to work on Finite State Transducer for Korean. Although there are several open-sourced POS tagger(Kkoma, HanNanum, and Komoran), none of them are purely rule-based; HanNanum and Komoran uses Hidden Markov Models(statistical method for making inferences about sequential data), and Kkoma requires the usage of a custom relational database.
Although the techniques employed in the aforementioned systems are crucial in achieving state-of-the-art performance, they have certain drawbacks. First, even after achieving extremely high performance, the probabilistic nature of such techniques make it very hard to identify what aspect of the system actually encodes the linguistic pattern. Thus, when an error occurs, it is usually impossible to correct the system manually. On the other hand, this is the development scheme for rule-based systems.
Also, apertium module for Korean has not been developed yet. Therefore, I decided to implement a transducer for Korean.
Overview
In this implementation of Korean POS analyzer, I was able to analyze most of noun morphology correctly. However, as there were multiple level of suffixes that attaches to verbs in Korean, the analysis and construction of Verb alteration was not easy.
Evaluation
In this implementation of Korean POS analyzer, I was able to analyze most of noun morphology correctly. However, as there were multiple level of suffixes that attaches to verbs in Korean, the analysis and construction of Verb alteration was not easy.
I observed that most of the errors come from either 1)lemmas not yet added or 2)failure to analyze different verb forms.
Coverage of corpora
"Trained Corpus"
- kor.phrases.COURT.txt:
- kor.phrases.GENESIS.txt:
- kor.phrases.HIROHITO.txt:
- kor.phrases.ROH.txt:
- kor.phrases.STALIN.txt:
- kor.phrases.WIKI.txt:
"Test Corpus"=
- Random 1200 (1):
- Random 1200 (2):
Precision and Recall
Using Random 1200 words from Wikipedia Dump
- Precision
- Recall
