Difference between revisions of "User:Francis Tyers/Sandbox2"
Jump to navigation
Jump to search
| (18 intermediate revisions by 3 users not shown) | |||
| Line 1: | Line 1: | ||
Constraint-based lexical selection for rule-based machine translation |
|||
==Agenda== |
|||
<pre> |
|||
Corpus: cawiki-20110616-pages-articles.xml.bz2 |
|||
cleaned with `aq-wikicrp' |
|||
1758582 lines |
|||
For http://xixona.dlsi.ua.es/freerbmt09/ |
|||
531983 unique analyses |
|||
531436 lines with >1 translation (30%) |
|||
2740 analyses with >1 translation |
|||
287 words (lemma+pos) with >1 translation in corpus |
|||
712 words in dictionary with >1 translation |
|||
1.03 fertility of dictionary over corpus (e.g. total number of word:word translations / total number of words) |
|||
</pre> |
|||
* Logging on xixona, knowing what people are translating (which language pair etc.) |
|||
Test corpus: |
|||
* Possible applications: |
|||
* quality control |
|||
* 150 test words |
|||
* encourage language pair maintainers |
|||
* 1,500 sentences |
|||
* give an idea of missing terms (on a temporal basis? What's in the news?) - getting the information so we can adapt the translators to what people are translating: if certain topics are coming up in the news ('swine flu' etc.), try to catch them |
|||
* 10 per test word |
|||
* Making a 3.2 release -- x-stage transfer, some changes in lttoolbox |
|||
* Randomly selected from the subset of sentences which were found in the corpus. |
|||
* Planning for new releases, apertium 3.4, apertium 4.0? |
|||
* Only words with >100 example sentences included |
|||
* Webservices -- what, when, where ? |
|||
* Rationale: Dictionary doesn't provide good enough coverage to produce statistically significant results over a whole corpus. |
|||
* Should we have a concentrated effort on Revo Vortaro import? |
|||
* Reta Vortaro is fairly consistent; it has clear delineation between simple, unambiguous terms; terms with more than one possible translation (where the first one listed is the preferred default); and polysemous words. Theres evenan XML version |
|||
* Discarding because of bad tagging/MWE recognition: 'to', 'sol', 'portada', 'cap', 'cop', 'marxa' (less than 60% correct) |
|||
* Dix profiling - finding out (on a corpus or on testvoc) how often each entry is used, i.a. for removing unused .dix entries - demo by Jacob |
|||
Training corpus: |
|||
Baselines: |
|||
* TL Frequency-best |
|||
* TLM-best |
|||
* Linguist set |
|||
* Full analysis:Full analysis dic from Giza++ |
|||
* Rules from phrase table |
|||
Process for using GIZA++: |
|||
* Tag both sides of the corpus (europarl, en-ca, first 1,700,000 sentences) with the Apertium language pair. |
|||
* Extract the model/lex.f2e file. |
|||
* Take the top scoring analysis:analysis results where the POS matches |
|||
* Where the word is already ambiguous in the Apertium dictionaries, add the possibilities from GIZA to the dictionary so that they may be chosen -- only added with POS tag. |
|||
==Annotation process== |
|||
# Translate corpus (native speaker of English, competent Catalan), adding missing translations to bilingual dictionary options. |
|||
#* Words with too many tagging errors, or MWE errors are left out. |
|||
# Proofread corpus |
|||
# Run corpus up to lexical transfer stage |
|||
# Annotate output of lexical transfer |
|||
Latest revision as of 08:11, 30 September 2011
Constraint-based lexical selection for rule-based machine translation
Corpus: cawiki-20110616-pages-articles.xml.bz2
cleaned with `aq-wikicrp'
1758582 lines
531983 unique analyses
531436 lines with >1 translation (30%)
2740 analyses with >1 translation
287 words (lemma+pos) with >1 translation in corpus
712 words in dictionary with >1 translation
1.03 fertility of dictionary over corpus (e.g. total number of word:word translations / total number of words)
Test corpus:
- 150 test words
- 1,500 sentences
- 10 per test word
- Randomly selected from the subset of sentences which were found in the corpus.
- Only words with >100 example sentences included
- Rationale: Dictionary doesn't provide good enough coverage to produce statistically significant results over a whole corpus.
- Discarding because of bad tagging/MWE recognition: 'to', 'sol', 'portada', 'cap', 'cop', 'marxa' (less than 60% correct)
Training corpus:
Baselines:
- TL Frequency-best
- TLM-best
- Linguist set
- Full analysis:Full analysis dic from Giza++
- Rules from phrase table
Process for using GIZA++:
- Tag both sides of the corpus (europarl, en-ca, first 1,700,000 sentences) with the Apertium language pair.
- Extract the model/lex.f2e file.
- Take the top scoring analysis:analysis results where the POS matches
- Where the word is already ambiguous in the Apertium dictionaries, add the possibilities from GIZA to the dictionary so that they may be chosen -- only added with POS tag.
Annotation process[edit]
- Translate corpus (native speaker of English, competent Catalan), adding missing translations to bilingual dictionary options.
- Words with too many tagging errors, or MWE errors are left out.
- Proofread corpus
- Run corpus up to lexical transfer stage
- Annotate output of lexical transfer
