I'm using this api to translate text: https://learn.microsoft.com/azure/cognitive-services/translator/reference/v3-0-translate
When user key in the keyword "tidak", it gets English as detected language, which is wrong, because there is no such word in English. It is a Malay word which means "No".
Is there a channel I report this to Microsoft so that they can fix the translation for this word? It is an important word in Malay for our chatbot.
Thanks.
You can get support or post your feedback here .
Related
While using google translate api for english to hindi translation, we are trying to fetch translated roman hindi for an english search query, searching for suitable method.
Currently, the transliteration from English en to Hindi hi, which means that the result will the translated text with only Latin characters, is not supported. As per the comments, from English shoes the expected output would be joote. However, the output is जूते.
There is an already open Feature request within Google's Issue tracker, here, addressing the Transliteration for the Cloud Translation API. Thus, you can click on the +1 button and leave a comment so the Googlers know this issue is also relevant to you. Lastly, I should point out that this platform is used to track bugs and feature requests made by the costumers.
The project that I'm working on mandates (by law) the name of the business to be displayed to the users in the regional language.
The best option that I could find was Google Transliterate. I'm aware Google Transliterate API has been officially deprecated as of May 26, 2011 but is still available to be used - which solves by need.
So my question is - How can I use Transliterate API without the need to open a web browser? When a user keys in a Edit Text say for e.g. "Baskin Robbins" I would like to get it transliterated behind the scene. I'm on minSdk 10.
Any pointers to working samples would be very much appreciated. Is LiquidCore as possibility? https://github.com/LiquidPlayer/LiquidCore . Any known implementation of Liquidcore & Transliterate? Please advise.
www.google.com/transliterate/indic?tlqt=1&langpair=en|ta&text=baskin%20robbins
Also see here
Implementing Google transliterate API using REST and C#, facing unicode and parsing issues
Is it possible and if so how to respond within a skill with different languages? For example I'm developing a skill for the German skill store which reads various texts from the internet. Those can be any in language and I can determine the language when I'm about to emit the response.
From what I can see the SSML subset Alexa implements does not specify the language in which the response is given. But Alexa's own Kindle skill is able to read me eBooks in either German or English (perhaps Amazon's own skills are special).
As said in other answers the right way is to use the <lang> tag in SSML. However since the english voice do not speak German it is quite weird. The right solution is to change the voice using <voice> tag.
Here is an example in German
<speak>
<voice name="Hans"><lang xml:lang="de-DE">Ich bin ein Berliner</lang></voice>.
I am a Berliner.
</speak>
It is described in this doc https://developer.amazon.com/fr/docs/custom-skills/speech-synthesis-markup-language-ssml-reference.html#examplefrench-content-in-an-english-skill
It looks like this is not possible at the moment: https://forums.developer.amazon.com/questions/55086/specify-output-language-per-intent.html
You can use the <lang> tag in SSML for this.
Here is an example in German.
<speak>
<lang xml:lang="de-DE">Mein Luftkissenfahrzeug ist voller Aale</lang>.
Hello in the default language.
</speak>
Here is a list of supported Amazon Polly languages for Alexa.
I am currently working on something where I am trying to translate a paragraph which includes more than one language.
Now I have realised with the google translate API if we have lets say:
hello bye hola
it will detect the language as English and if its:
hello hola adios then it will detect Spanish.
So basically whichever language has the highest word count in the sentence/paragraph, it will detect that language. Now the funny thing is that on google translate they actually have this feature.
Is there any way that to fix this issue so that it will only detect the foreign language and not English?
No, there's not a way to do that with the Google Translate API because there's just no mechanism for that exposed in their public API.
If you use an alternate language detection library, you can define a threshold under which to remove the content of the less-represented language. This would allow you to remove the English content if it makes up less than, say, 30% of the text in your overall sample.
For example, see the RemoveMinorityScriptsTextFilterTest class in the optimaize/language-detector project.
I'm looking for a way to include a full blown English dictionary in an iPhone app (a word game), the database must be able to include all conjugation possibilities for verbs, must include singular and plural spellings. So my app can query the database to check if the spelling is correct.
Is there a free or commercial database that would include those data?
You can use UITextChecker for spell-checking.
Regarding a dictionary, when I built an iOS dictionary library sometime ago (www.lexicontext.com) I used WordNet. WordNet contains a lot of interesting semantic info ...
NSSpellChecker is your easiest option, but it might be more complete to use the online Scrabble official dictionary as well and check it against both (only one match required.)
You could do a web-service request using http://www.hasbro.com/scrabble/en_US/search.cfm
http://www.a2zwordfinder.com/cgi-bin/scrabble.cgi?Letters=&Pattern=______&MatchType=Exactly&MinLetters=3&SortBy=Alpha&SearchType=Scrabble
Change min letters to get different results
The best place to find a database for a spell-checker is probably a free text processing application. So, I'd try with Open Office version of Word. Download it, install it and simply find the dictionary file.
Open Office is licensed under LGPL, so it should be fine, just check if the licence covers the data as well (i.e. the dictionary file).
Maybe this English corpus helps: http://www.wordfrequency.info/free.asp