I am trying to extract numeric information from set of SMSs. The regexes fail in extracting balance and credit amounts as the patterns of the SMS is not consistent throughout the industry.
We are currently making assumptions to make it work like First Amount = Credit amount
Second Amount=Balance.
This has lot of limitations and error rate is gradually increasing.
Anyone has any alternatives to regexes?
There is no standard for this kind of message as every operator creates its own messages. this is marketing communication... Yet, for a given operator and a given plan all replies to balance inquiry messages should be the sames (as long as they are not changed by operators marketing teams...).
Regexes are a good tool but you need to know the message forehand and create the appropriate regex patterns
Related
We use the Azure Batch Transcription Service to get the Transcript of an Audio / Speech.
In here we noticed, that sometimes filler words like "uhm", "hm" or something similar are included, but very rarely - also as we used this service for a few months already and we have the feeling as if it "got less" (so less "uhm"s in the transcript)
Q1: Is there a way to get the fill words? We want to recieve them within the transcript.
Also, as we sometimes record conversations it can happen that someone says a name or is talking about other personal information.
Q2: Is there a way to "filter" those personal information / words within the transcript?
Sorry, I don't think there is a way to filter personal data/ word when translate. We only can do profanity Filter for batch transcription.
But I agree this feature will be very helpful. I will forward this feature request to product group to see if we can have this in the feature.
Thing I will suggest is to optimize the transcription as last to filter the sensitive information.
Regards,
Yutong
I'm working on a problem that at the very least seems to require named entity recognition, but I'm not sure how to go farther than the NER parse. What I'm trying to do is parse information (likely from tweets) regarding scheduling of events. So, for example, I'd like to be able to automatically resolve the yes/no answer to the question of "Are The Beatles playing tomorrow?" from short messages like:
"The Beatles cancelled their show tomorrow" or
"The Beatles' show is still on tomorrow"
I know NER will get me close as it will identify the band of interest and the time (if it's indicated), but there are many ways to express the concepts I'm interested in, for example:
"The Beatles are on for tomorrow" or
"The Beatles won't be playing tomorrow."
How can I go from an NER parsed representation to extracting the information of interest? Any suggestions would be much appreciated.
I guess you should search by event detection (optionally - in Twitter); maybe, also by question answering systems, if your example with yes/no questions wasn't just an illustration: if you know user needs in advance, this information may increase the quality of the system.
For start, there are some papers about event detection in Twitter: here and here.
As a baseline, you can create a list with positive verbs for your domain (to be, to schedule) and negative verbs (to cancel, to delay) - just start from manual list and expand it by synonyms from some dictionary, e.g. WordNet. Also check for negations - again, by presence of pre-specified words ('not' in different forms) in a tweet. Then, if there is a negation, you just invert the meaning.
Since you work with Twitter and most likely there would be just one event mentioned in a tweet, it can work pretty well.
My friend has a small business where customers order services using email. He receives several emails a day and sorting thru it is becoming cumbersome.
There are about 10 different kind of tasks the customer can request, and for each there are one or two words that specify it. The other info present in the emails is the place where the service is to be delivered, the time, and the involved people's names. The email also contains an ID, a long number with a fairly standard format.
The emails are very unstructured, but all contain the key info above. My question is: what is the best method to sweep thru these emails and extract the key info (such as type of service, place, people's names, the ID etc)?
I thought about some kind of pre-processing, then pass it thru AlchemyAPI and then test the Alchemy output using Neural Networks for each feature (key info). This can be supervised learning as I can do a feedback loop all the time, as once the info is inputted, I can have someone to validate.
Any ideas? Thanks
I guess some parts (ID, task, time) can be captured by a regular expression and dictionary matching. Have a look at GATE's JAPE tool.
It should be fairly easy to assemble a dictionary and then use the lookups for the "task", also you can reuse the available jape rules for date/time and write a new one for the ID (also, a simple regex could be fine).
For matching the location and people's names you should be careful, openCalais and alchemyAPI can give you good results if names and places are used in well defined sentences and will probably make more mistakes with some tabular or weird format. Also you can never be sure you captured the place and person correctly so don't rely on that for processing orders directly.
If you have more information about mails' structure or expected names and places (i.e. you have a "clients" table with all possible names), you would probably want to do your own tagging, otherwise I'd stick to openCalais or alchemyAPI + some regular expressions.
P.S. I assume all mails are in English.
I have a column which is made up of addresses as show below.
Address
1 Reid Street, Manchester, M1 2DF
12 Borough Road, London, E12,2FH
15 Jones Street, Newcastle, Tyne & Wear, NE1 3DN
etc .. etc....
I am wanting to split this into different columns to import into my SQL database. I have been trying to use Findstring to seperate by the comma but am having trouble when some addresses have more "sections" than others. ANy ideas whats the best way to go about this?
Many THanks
This is a requirements specification problem, not an implementation problem. The more you can afford to assume about the format of the addresses, the more detailed parsing you will be able to do; the other side of the same coin is that the less you will assume about the structure of the address, the fewer incorrect parses you will be blamed for.
It is crucial to determine whether you will only need to process UK postal emails, or whether worldwide addresses may occur.
Based on your examples, certain parts of the address seem to be always present, but please check this resource to determine whether they are really required in all UK email addresses.
If you find a match between the depth of parsing that you need, and the assumptions that you can safely make, you should be able to keep parsing by comma indexes (FINDSTRING); determine some components starting from the left, and some starting from the right of the string; and keep all that remains as an unparsed body.
It may also well happen that you will find that your current task is a mission impossible, especially in connection with international postal addresses. This is why most websites and other data collectors require the entry of postal address in an already parsed form by the user.
Excellent points raised by Hanika. Some of your parsing will depend on what your target destination looks like. As an ignorant yank, based on Hanika's link, I'd think your output would look something like
Addressee
Organisation
BuildingName
BuildingAddress
Locality
PostTown
Postcode
BasicsMet (boolean indicating whether minimum criteria for a good address has been met.)
In the US, just because an address could not be properly CASSed doesn't mean it couldn't be delivered - cip, my grandparent-in-laws live in enough small town that specifying their name and city is sufficient for delivery as local postal officials know who they are. For bulk mailings though, their address would not qualify for the bulk mailing rate and would default to first class mailing. I assume a similar scenario exists for UK mail
The general idea is for each row flowing through, you'll want to do your best to parse the data out into those buckets. The optimal solution for getting it "right" is to change the data entry method to validate and capture data into those discrete buckets. Since optimal never happens, it becomes your task to sort through the dross to find your gold.
Whilst you can write some fantastic expressions with FINDSTRING, I'd advise against it in this case as maintenance alone will drive you mad. Instead, add a Script Transformation and build your parsing logic in .NET (vb or c#). There will then be a cycle of running data through your transformation and having someone eyeball the results. If you find a new scenario, you go back and adjust your business rules. It's ugly, it's iterative and it's prone to producing results that a human wouldn't have.
Alternatives to rolling your address standardisation logic
buy it. Eventually your business needs outpace your ability to cope with constantly changing business rules. There are plenty of vendors out there but I'm only familiar with US based ones
upgrade to SQL Server 2012 to use DQS (Data Quality Services). You'll probably still need to buy a product to build out your knowledge base but you could offload the business rule making task to a domain expert ("Hey you, you make peanuts an hour. Make sure all the addresses coming out of this look like addresses" was how they covered this in the beginning of one of my jobs).
I have an app that extracts information from incoming messages. The messages all contain the same information, but they have different forms depending on the source that sent them.
Example:
Message from source A :
A: You spent $50.00 at Macy's on 2/20/12
Message from source B :
Purchase, $50.00, Macy's, 2Feb2012, Balance $5000.00
Every message from a single source has the same form though. So at the moment, I'm doing it by writing a set of regular expressions to first identify which message I'm trying to decode (i.e. what source it came from so I know what the form of the message is), and then extracting the necessary information from the message (in the above example, I want to know the transaction amount, the store where the transaction happened, and the date). If I discover a new source for a message, or a source changes the format of their message (doesn't happen very often, but could happen), I need to manually write the regular expressions for that message. I'm sure however that I could automate this using some kind of machine learning technique. I just don't know much about machine learning, and I don't know where to even start looking for a technique that would apply to my problem. I would like someone to just point me in the right direction on where to start reading.
In order to detect and label amounts, dates, person names and similar information you can use a technique called Named Entity Recognition. The Stanford Named Entity Recognizer comes with pretrained, ready to use models.
You also use whatever labeled data you have generated so far to learn a custom model for your application. The standard techniques used for this purpose are Conditional Random Fields or Sequence Perceptron. There are many toolkits implementing these models, including:
Wapiti - A simple and fast discriminative sequence labelling toolkit.
Sequor - sequence labeler based on Collins's (2002) perceptron.