Looking for a free bilingual terminology extraction tool
இழை இடுபவர்: Sara Poggian (X)
Sara Poggian (X)
Sara Poggian (X)
Dec 14, 2009

Hallo everybody!

For a univeristy task I've to create a glossary, so i'm considering to use a bilingual terminology exctraction tool, able to extract terminology from one of the TM i'm creating for the same task. Do you known if there's somentihg free? I searched on the web, but I just found free tools working on single texts.

Thank you in advance

Regards

Sara Poggiani


 
Samuel Murray
Samuel Murray  Identity Verified
நெதர்லாந்து
Local time: 14:25
உறுப்பினர் (2006)
ஆங்கிலம் - ஆஃப்ரிகான்ஸ்
+ ...
If you find one (even if paid) Dec 14, 2009

Sara Poggiani wrote:
I'm considering to use a bilingual terminology extraction tool, able to extract terminology from one of the TMs I'm creating. Do you know if there's something free?


I know of no tools that can do this -- no free tools and no paid tools either. If you find anything, let us know.


 
FarkasAndras
FarkasAndras  Identity Verified
Local time: 14:25
ஆங்கிலம் - ஹங்கேரியன்
+ ...
Several out there Dec 14, 2009

Samuel Murray wrote:

Sara Poggiani wrote:
I'm considering to use a bilingual terminology extraction tool, able to extract terminology from one of the TMs I'm creating. Do you know if there's something free?


I know of no tools that can do this -- no free tools and no paid tools either. If you find anything, let us know.


Multiterm Extract comes to mind as the most famous example in translator circles.
I have never seen it in operation, but the little I heard suggests you shouldn't expect too much.
Honestly, I wouldn't expect any automatic tool to be much use when it comes to a task like this. The data is just too noisy for the process to be reliable.


Here's the wiki page with several free options: http://en.wikipedia.org/wiki/Terminology_extraction

Please come back and post your experiences if you try any of them.


 
SusanneM
SusanneM
Local time: 14:25
ஆங்கிலம் - ஜெர்மன்
+ ...
Only for German and English texts Dec 15, 2009

Terminology extraction for free is available here: http://www.beo-sphere.de/beo_term.php

 
Samuel Murray
Samuel Murray  Identity Verified
நெதர்லாந்து
Local time: 14:25
உறுப்பினர் (2006)
ஆங்கிலம் - ஆஃப்ரிகான்ஸ்
+ ...
@ SusanneM Dec 15, 2009

SusanneM wrote:
Terminology extraction for free is available here: http://www.beo-sphere.de/beo_term.php


Really? What does the line "Mehrsprachige Dokumente werden nicht korrekt verarbeitet" on that web site mean?


 
Sara Poggian (X)
Sara Poggian (X)
தலைப்பை ஆரம்பித்தல்
The final decision Dec 15, 2009

First of all many thanks to everybody for the help!

I just gave up searching for such a tool with this "bilingual function", and i will use for my purpose just the free tools working on single texts. I noticed in this first experience with terminology that human intervent is necessary in any case.....:-S
....but tecnology can help when you have to elaborate a big amount of words!!!

PS for SusanneM: i'm working on german texts so your suggestion is perfect, and th
... See more
First of all many thanks to everybody for the help!

I just gave up searching for such a tool with this "bilingual function", and i will use for my purpose just the free tools working on single texts. I noticed in this first experience with terminology that human intervent is necessary in any case.....:-S
....but tecnology can help when you have to elaborate a big amount of words!!!

PS for SusanneM: i'm working on german texts so your suggestion is perfect, and the tool seems to be quite accurate! thx

Ps To Farkas: among the links on the wikipedia page i tried this one http://labs.translated.net/terminology-extraction/. You have to insert the texts and this "software" based on a probabilistic tagger gives you back a list of words that are supposed to be classified as terminology...but i was not so satisfied with the final result!! and it works only with italian french and english texts!

Best regards

Sara
Collapse


 
Pablo Bouvier
Pablo Bouvier  Identity Verified
Local time: 14:25
ஜெர்மன் - ஸ்பேனிஷ்
+ ...
Looking for a free bilingual terminology extraction tool Dec 15, 2009

Samuel Murray wrote:

Sara Poggiani wrote:
I'm considering to use a bilingual terminology extraction tool, able to extract terminology from one of the TMs I'm creating. Do you know if there's something free?


I know of no tools that can do this -- no free tools and no paid tools either. If you find anything, let us know.




Please, try Synchroterm. You can ask a key for a time limited demo version. My experience with the EC memory (TMX, 658888 TU's) was rather negative, since the extraction process broked down. But, I am not going to say the product was deficient, since perhaps it needed a more powerful computer. Please, if you decide to try it, les us know your opininon.

[Editado a las 2009-12-15 17:31 GMT]


 
Sara Poggian (X)
Sara Poggian (X)
தலைப்பை ஆரம்பித்தல்
Samuel Dec 15, 2009

To Samuel: It means that multilingual documents won't be correctly elaborate!

i suppose...

bye


 
Kevin Lossner
Kevin Lossner  Identity Verified
போர்த்துகள்
Local time: 13:25
ஜெர்மன் - ஆங்கிலம்
+ ...
MT Extract Dec 15, 2009

I've used an older version of MultiTerm Extract for mining TMs; it's far from a perfect solution and requires a lot of manual intervention and correction, but I do find that it enables me to sort data faster, check contexts and include examples without too much fuss. The best term extraction I've ever seen was demonstrated in Berlin by Lou Cremers a few years ago, but that's more a budget item for agencies and corporate clients. Way out of my league I think.

Most of the time I do mo
... See more
I've used an older version of MultiTerm Extract for mining TMs; it's far from a perfect solution and requires a lot of manual intervention and correction, but I do find that it enables me to sort data faster, check contexts and include examples without too much fuss. The best term extraction I've ever seen was demonstrated in Berlin by Lou Cremers a few years ago, but that's more a budget item for agencies and corporate clients. Way out of my league I think.

Most of the time I do monolingual term surveys of corpora, and free tools or the DVX Lexicon work fine for that, though the lack of stop word functions in the latter is a real nuisance.

Jost Z's latest Toolkit newletter (155th Premium Edition) also mentions that the latest edition of Across includes:
crossMining is a new module that allows you to extract terminology from translation memories for various purposes, including quality assurance checks of the TMs when those lists are compared to verified terminology databases (one of the strong points of Across term recognition is its morphological capabilities in various European languages) or the employment of these dictionaries as Auto-completion dictionaries for the translation process.

Not in the free Personal Edition "of course".
Collapse


 
Kevin Lossner
Kevin Lossner  Identity Verified
போர்த்துகள்
Local time: 13:25
ஜெர்மன் - ஆங்கிலம்
+ ...
Very primitive Dec 15, 2009

SusanneM wrote:
Terminology extraction for free is available here: http://www.beo-sphere.de/beo_term.php


I just tried that out on a file containing all the test questions for weapons technology on next year's hunting exam in Brandenburg. I thought it might be useful for screening and making sure I have a grip on all the relevant vocabulary (after hearing that "Kunden" has something to do with teeth, that's been a source of concern). Curiously, there were 7 entries for "Würgebohrung" (I nearly choked on that), each with a frequency of one. And there is no recognition that "Gesetz" and the genitive for "Gesetzes" are the same word, etc. On the bright side, though, it does use stop word lists, but it's disappointing that I can't apply my own.

On the whole I find freeware tools like AntConc (http://www.antlab.sci.waseda.ac.jp/software.html) more useful and flexible.


 
Sara Poggian (X)
Sara Poggian (X)
தலைப்பை ஆரம்பித்தல்
Multiterm extract/ Across Dec 15, 2009

Dear Kevin

I know about MT extract, if i don't go wrong, it's an application of trados, i've never used it cause as a student i just use opensource tools, but i'm very curios to try it...so when i get a licence for trados i'll let you konw about my experience ...or if a i find someone who has it i'll ask to try!

about across, i've already downloaded the free personal edition...and discovered that the TM
... See more
Dear Kevin

I know about MT extract, if i don't go wrong, it's an application of trados, i've never used it cause as a student i just use opensource tools, but i'm very curios to try it...so when i get a licence for trados i'll let you konw about my experience ...or if a i find someone who has it i'll ask to try!

about across, i've already downloaded the free personal edition...and discovered that the TMs terminology extraction is not included

I agree with you about Antconc, and i'm using it to analyse my translation and create this glossary!

thank you for your answer!

sara
Collapse


 
Pablo Bouvier
Pablo Bouvier  Identity Verified
Local time: 14:25
ஜெர்மன் - ஸ்பேனிஷ்
+ ...
Looking for a free bilingual terminology extraction tool Dec 15, 2009

Sara Poggiani wrote:

Hallo everybody!

For a univeristy task I've to create a glossary, so i'm considering to use a bilingual terminology exctraction tool, able to extract terminology from one of the TM i'm creating for the same task. Do you known if there's somentihg free? I searched on the web, but I just found free tools working on single texts.

Thank you in advance

Regards

Sara Poggiani


Try Synchroterm. It is not free, but you can get a limited time demo key her:
http://www.bridgeterm.com/synchro_en.asp. It works with a source and target text with text format or with text translation memories (txt or tmx).


 


To report site rules violations or get help, contact a site moderator:

இந்த மன்றத்துக்கான மட்டுறுத்துனர்கள்
Maria Castro[Call to this topic]
Nawal Kramer[Call to this topic]

You can also contact site staff by submitting a support request »

Looking for a free bilingual terminology extraction tool







TM-Town
Manage your TMs and Terms ... and boost your translation business

Are you ready for something fresh in the industry? TM-Town is a unique new site for you -- the freelance translator -- to store, manage and share translation memories (TMs) and glossaries...and potentially meet new clients on the basis of your prior work.

More info »
Wordfast Pro
Translation Memory Software for Any Platform

Exclusive discount for ProZ.com users! Save over 13% when purchasing Wordfast Pro through ProZ.com. Wordfast is the world's #1 provider of platform-independent Translation Memory software. Consistently ranked the most user-friendly and highest value

Buy now! »