I need to write a text parser for the education domain which can extract out the information like institute, location, course etc from the free text.
Currently i am doing it through lucene, steps are as follows:
Index all the data related to institute, courses and location.
Making shingles of the free text and searching each shingle in location, course and institute index dir and then trying to find out which part of text represents location, course etc.
In this approach I am missing lot of cases like B.tech can be written as btech, b-tech or b.tech.
I want to know is there any thing available which can do all these kind of things, I have heard about Ling-pipe and Gate but don't know how efficient they are.
You definitely need GATE. GATE has 2 main most frequently used features (among thousands others): rules and dictionaries. Dictionaries (gazetteers in GATE's terms) allow you to put all possible cases like "B.tech", "btech" and so on in a single text file and let GATE find and mark them all. Rules (more precisely, JAPE-rules) allow you to define patterns in text. For example, here's pattern to catch MIT's postal address ("77 Massachusetts Ave., Building XX, Cambridge MA 02139"):
{Token.kind == number}(SP){Token.orth == uppercase}(SP){Lookup.majorType == avenue}(COMMA)(SP)
{Token.string == "Building"}(SP){Token.kind == number}(COMMA)(SP)
{Lookup.majorType == city}(SP){Lookup.majorType == USState}(SP){Token.kind == number}
where (SP) and (COMMA) - macros (just to make text shorter), {Somthing} - is annotation, , {Token.kind == number} - annotation "Token" with feature "kind" equal to "number" (i.e. just number in the text), {Lookup} - annotation that captures values from dictionary (BTW, GATE already has dictionaries for such things as US cities). This is quite simple example, but you should see how easily you can cover even very complicated cases.
I didn't use Lucene but in your case I would leave different forms of the same keyword as they are and just hold a link table or such. In this table I'd keep the relation of these different forms.
You may need to write a regular expression to cover each possible form of your vocabulary.
Be careful about your choice of analyzer / tokenizer, because words like B.tech can be easily split into 2 different words (i.e. B and tech).
You may want to check UIMA. As Lingpipe and Gate, this framework features text annotation, which is what you are trying to do. Here is a tutorial which will help you write an annotator for UIMA:
http://uima.apache.org/d/uimaj-2.3.1/tutorials_and_users_guides.html#ugr.tug.aae.developing_annotator_code
UIMA has addons, in particular one for Lucene integration.
You can try http://code.google.com/p/graph-expression/
example of Adress parsing rules
GraphRegExp.Matcher Token = match("Token");
GraphRegExp.Matcher Country = GraphUtils.regexp("^USA$", Token);
GraphRegExp.Matcher Number = GraphUtils.regexp("^\\d+$", Token);
GraphRegExp.Matcher StateLike = GraphUtils.regexp("^([A-Z]{2})$", Token);
GraphRegExp.Matcher Postoffice = seq(match("BoxPrefix"), Number);
GraphRegExp.Matcher Postcode =
mark("Postcode", seq(GraphUtils.regexp("^\\d{5}$", Token), opt(GraphUtils.regexp("^\\d{4}$", Token))))
;
//mark(String, Matcher) -- means creating chunk over sub matcher
GraphRegExp.Matcher streetAddress = mark("StreetAddress", seq(Number, times(Token, 2, 5).reluctant()));
//without new lines
streetAddress = regexpNot("\n", streetAddress);
GraphRegExp.Matcher City = mark("City", GraphUtils.regexp("^[A-Z]\\w+$", Token));
Chunker chunker = Chunkers.pipeline(
Chunkers.regexp("Token", "\\w+"),
Chunkers.regexp("BoxPrefix", "\\b(POB|PO BOX)\\b"),
new GraphExpChunker("Address",
seq(
opt(streetAddress),
opt(Postoffice),
City,
StateLike,
Postcode,
Country
)
).setDebugString(true)
);
B.tech can be written as btech, b-tech or b.tech
Lucene will let you do fuzzy searches based on the Levenshtein Distance. A query for roam~ (note the ~) will find terms like foam and roams.
That might allow you to match the different cases.
Related
I am using cloud google vision API to extract text from Aadhaar and PAN. How can I get exact user details like name, father's name, and address?
Raw Data
ଭାରତ ସରକାର
Government of India
ଜିତ୍ୟାନନ୍ଦ ଖେମୁକୁ
NITYANANDA KHEMUDU
ପିତା : ସୀତାରାମ ଖେମୁକୁ
Father: Sitaram Khemudu
ଜନ୍ମ ତାରିଖ / DOB : 01.07.1999
ପୁରୁଷ / Male
ମୋ ଆଧାର, ମୋ ପରିଚୟ
I have built 5-6 OCR till date like aadhar, pan, ITR, Driving Linces etc., using google cloud vision API, I think you are looking for response like
{"pan_card_no":"ECXXXXXX123",
"name":"fshksj"
}
to get such response you need to built your own logic, here are some logic's i can share with you
Perform OCR on your document using Google_cloud_vision API and store that response into one array (Goggle gives logic line by line)
Like in above case if you want to grab DOB first you can build logic like i) if "DOB" in (list of item) then grab the numeric values
To get the name what you can do is dropping the unnecessary items from list by if using if condition like (if "India" in i) or (if i.isdigit()) then drop it likewise you can drop the unnesseary items from main list to get the Name
to grab the Address what you can do is, 95% of the time address come with pincode at last, so what you can do is treat pincode as a last index of address and look of "Address" kind of keyword then add all the elements from "Add keyword index" to "pincode index" ( this can be easily done in list) to validate whether the pincode is valid or not you can use library like Pyzipin
There are multiple conditions that you can use, above are the very basic one i mentioned, if you need any specific logic then then you can ask me
Imagine I have a report, a letter actually, which I need to translate to several languages. I have created a greeting field in the form which is filled programatically by an onchange event method.
if self.partner_id.gender == 'female':
self.letter_greeting = _('Dear %s %s,') % ( # the translation should be "Estimada"
self.repr_recipient_id.title.shorcut, surname
)
elif self.partner_id.gender == 'male':
self.letter_greeting = _('Dear %s %s,') % ( # translation "Estimado"
self.repr_recipient_id.title.shorcut, surname
)
else:
self.letter_greeting = _('Dear %s %s,') % ( # translation: "Estimado/a"
self.partner_id.title.shorcut, surname
)
In that case the word Dear should be translated to different Spanish translations depending on which option is used, this is because we use different termination depending on the gender. Exporting the po file I found that all the options are altogether, that make sense because almost all the cases the translations will be the same, but not in this case:
#. module: custom_module
#: code:addons/custom_module/models/sale_order.py:334
#: code:addons/custom_module/models/sale_order.py:338
#: code:addons/custom_module/models/sale_order.py:342
#, python-format
msgid "Dear %s %s,"
msgstr "Dear %s %s,"
Solutions I can apply directly
Put all the terms in different entries to avoid the same translation manually every time I need to update the po file. This can be cumbersome if you have many different words with that problem. If I do it and I open the file with poedit, this error appears: duplicate message definition
Put all the possible combinations with slashes, this is done y some other parts of Odoo. For both gender would be:
#. module: stock
#: model:res.company,msg:stock.res_company
msgid "Dear"
msgstr "Estimado/a"
This is just an example. I can think of many words that look the same in English, but they use different spelling or meanings in other languages depending on the context.
Possible best solutions
I don't know if Odoo know anything aboutu the context of a word to know if it was already translated or not. Adding a context manually could solve the problem, at least for words with different meanings.
The nicest solution would be to have a parameter to the translation module to make sure that the word is exported as an isolated entry for that especific translation.
Do you think that I am giving to it too much importance haha? Do you know if there is any better solution? Why is poedit not taking into account that problem at all?
I propose an extension of models res.partner.title and res.partner.
res.partner.title should get a translateable field for saving salutation prefixes like 'Dear' or 'Sehr geehrter' (German). Maybe it's worth to get something about genders, too, but i won't get into detail here about that.
You probably want to show the configuring user an example like "Dear Mr. Name" or something like that. A computed field should work.
On res.partner you should just implement either a computed field or just a method to get a full salutation for a partner record.
To some degree this is a linguistics problem. I believe the best solution would be to use a different "Source Language", one made up of keys, and then have English as another Translation. The word "Dear" in English does not have a gender context (and typically, much of English doesn't), while the word "Estimado" in Spanish does. The translation from that Spanish word to English is more appropriately "Masculine Dear." Therefore, using keys as your source language, you would have this:
SourceText (EnglishDescription) -> Translation (English) -> Translation (Spanish)
DearMasculine -> Dear -> Estimado
DearFeminine -> Dear -> Estimada
DearNuetral -> Dear -> Estimado/a
I am using premium account (not sandbox) for data collection.
I want to collect:
All tweets in English that contain ‘china’ or ‘chinese’ that are user geolocated to US and not geolocated at tweet level, excluding all retweets
All tweets in English that contain ‘china’ or ‘chinese’ that are user geolocated to ‘Minnesota’ and not geolocated at tweet level, excluding all retweets
The code is as follows:
premium_search_args = load_credentials('twitter_API.yaml',
yaml_key ='search_tweets_premium_api', env_overwrite=False)
# keywords for the search
# key word 1
keywords = '(China OR Chinese) lang:en profile_country:US -place_country:US -is:retweet'
# key word 2
keywords = '(China OR Chinese) lang:en -place_country:US profile_region:"Minnesota" -is:retweet'
# define search rule
rule = gen_rule_payload(keywords,from_date='2019-12-01',
to_date='2019-12-10',results_per_call=500)
# create result stream and print before start
rs = ResultStream(rule_payload=rule, max_results=1250000,
**premium_search_args)
My problems are that:
For the first one, a large portion of the results I get didn’t satisfy the query. First, some don’t have Profile Geo enrichment, i.e. user.derived.locations attribute is not in the user object. Second, if it is, a lot don’t have country code US, i.e. they are identified to other countries.
For the second one, the result I get from this method is a smaller subset of the results I can get from 1). That is, when I filter all tweets user geolocated to Minnesota (by user.derived.locations.region) from profile_country:US, it gives a larger sample than using profile_region:“Minnesota”. A considerable amount of data is missing using this method.
I have tried several times but it seems that user geolocation operators don’t work exactly what I want. Does anyone has any idea why this is the case? I would very much appreciate any answers/suggestions/comments.
Thank you!
When dealing with exact matches I'm given a real world query like this:
"not in education, employment, or training"
Converted to a Lucene query with stopwords removed gives:
+Content:"? ? education employment ? training"
Here's a more contrived example:
"there is no such thing"
Converted to a Lucene query with stopwords removed gives:
+Content:"? ? ? ? thing"
My goal is to have searches like these match only the exact match as the user entered it.
Could one solution be to clear the stopwords list? would this have adverse affects? if so what? (my google-fu failed)
This all depends on the analyzer you are using. The StandardAnalyzer uses Stop words and strips them out, in fact the StopAnalyzer is where the StandardAnalyzer gets its stop words from.
Use the WhitespaceAnalyzer or create your own by inheriting from one that most closely suits your needs and modify it to be what you want.
Alternatively, if you like the StandardAnalyzer you can new one up with a custom stop word list:
//This is what the default stop word list is in case you want to use or filter this
var defaultStopWords = StopAnalyzer.ENGLISH_STOP_WORDS_SET;
//create a new StandardAnalyzer with custom stop words
var sa = new StandardAnalyzer(
Version.LUCENE_29, //depends on your version
new HashSet<string> //pass in your own stop word list
{
"hello",
"world"
});
I’m pretty new to python (using python 3) and spacy (and programming too). Please bear with me.
I have three questions where two are more or less the same I just can’t get it to work.
I took the “syntax specific search with spacy” (example) and tried to make different things work.
My program currently reads txt and the normal extraction
if w.lower_ != 'music':
return False
works.
My first question is: How can I get spacy to extract two words?
For example: “classical music”
With the previous mentioned snippet I can make it extract either classical or music. But if I only search for one of the words I also get results I don’t want like.
Classical – period / era
Or when I look for only music
Music – baroque, modern
The second question is: How can I get the dependencies to work?
The example dependency with:
elif w.dep_ != 'nsubj': # Is it the subject of a verb?
return False
works fine. But everything else I tried does not really work.
For example, I want to extract sentences with the word “birthday” and the dependency ‘DATE’. (so the dependency is an entity)
I got
if d.ent_type_ != ‘DATE’:
return False
To work.
So now it would look like:
def extract_information(w,d):
if w.lower_ != ‘birthday’:
return False
elif d.ent_type_ != ‘DATE’:
return False
else:
return True
Does something like this even work?
If it works the third question would be how I can filter sentences for example with a DATE. So If the sentence contains a certain word and a DATE exclude it.
Last thing maybe, I read somewhere that the dependencies are based on the “Stanford typed dependencies manual”. Is there a list which of those dependencies work with spacy?
Thank you for your patience and help :)
Before I get into offering some simple suggestions to your questions, have you tried using displaCy's visualiser on some of your sentences?
Using an example sentence 'John's birthday was yesterday', you'll find that within the parsed sentence, birthday and yesterday are not necessarily direct dependencies of one another. So searching based on the birthday word having a dependency of a DATE type entity, might not be yield the best of results.
Onto the first question:
A brute force method would be to look for matching subsequent words after you have parsed the sentence.
doc = nlp(u'Mary enjoys classical music.')
for (i,token) in enumerate(doc):
if (token.lower_ == 'classical') and (i != len(doc)-1):
if doc[i+1].lower_ == 'music':
print 'Target Acquired!'
If you're unsure of what enumerate does, look it up. It's the pythonic way of using python.
To questions 2 and 3, one simple (but not elegant) way of solving this is to just identify in a parsed sentence if the word 'birthday' exists and if it contains an entity of type 'DATE'.
doc = nlp(u'John\'s birthday was yesterday.')
for token in doc:
if token.lower_ == 'birthday':
for entities in doc.ents:
if entities.label_ == 'DATE':
print 'Found ya!'
As for the list of dependencies, I presume you're referring to the Part-Of-Speech tags. Check out the documentation on this page.
Good luck! Hope that helped.