assuming that I know nothing about everything and that I'm starting in programming TODAY what do you say would be necessary for me to learn in order to start working with Natural Language Processing?
I've been struggling with some string parsing methods but so far it is just annoying me and making me create ugly code. I'm looking for some fresh new ideas on how to create a Remember The Milk API like to parse user's input in order to provide an input form for fast data entry that are not based on fields but in simple one line phrases instead.
EDIT: RTM is todo list system. So in order to enter a task you don't need to type in each field to fill values (task name, due date, location, etc). You can simply type in a phrase like "Dentist appointment monday at 2PM in WhateverPlace" and it will parse it and fill all fields for you.
I don't have any kind of technical constraints since it's going to be a personal project but I'm more familiar with .NET world. Actually, I'm not sure this is a matter of language but if it's necessary I'm more than willing to learn a new language to do it.
My project is related to personal finances so the phrases are more like "Spent 10USD on Coffee last night with my girlfriend" and it would fill location, amount of $$$, tags and other stuff.
Thanks a lot for any kind of directions that you might give me!
This does not appear to require full NLP. Simple pattern-based information extraction will probably suffice. The basic idea is to tokenize the text, then recognize/classify certain keywords, and finally recognize patterns/phrases.
In your example, tokenizing gives you "Dentist", "appointment", "monday", "at", "2PM", "in", "WhateverPlace". Your tool will recognize that "monday" is a day of the week, "2PM" is a time, etc. Finally, you can find patterns like [at] [TIME] and [in] [Place] and use those to fill in the fields.
A framework like GATE may help, but even that may be a larger hammer than you really need.
Have a look at NLTK, its a good resource for beginner programmers interested in NLP.
http://www.nltk.org/
It is written in python which is one of the easier programming languages.
Now that I understand your problem, here is my solution:
You can develop a kind of restricted vocabulary, in which all amounts must end witha $ sign or any time must be in form of 00:00 and/or end with AM/PM, regarding detecting items, you can use list of objects from ontology such as Open Cyc. Open Cyc can provide you with list of all objects such beer, coffee, bread and milk etc. this will help you to detect objects in the short phrase. Still it would be a very fuzzy approach.
Related
I'm currently working on an internationalisation project for a large web application - initially we're just implementing French but more languages will follow in time. One of the issues we've come across is how to display adjectives.
Let's take "Active" as an example. When we received translations back from the company we're using, they returned "Actif(ve)", as English "Active" translates to masculine "Actif" or feminine "Active". We're unsure of how to display this, and wondered if there are any well established conventions in the web development world.
As far as I see it there are three possible scenarios:
We know at development time which noun a given adjective is referring to. In this case we can determine and use the correct gender.
We're referring to a user, either directly ("you") or in the third person. Short of making every user have a gender, I don't see a better approach than displaying both, i.e. "Actif(ve)"
We are displaying the adjective in isolation, not knowing which noun it's referring to. For example in a table of data, some rows might be dealing with a masculine entity, some feminine.
Scenarios 2 and 3 seem to be the toughest ones. Does anyone have any experience handling these issues? Any tips would be appreciated!
This is complex, because we cannot imagine all the cases, and there is risk to go in "opinion based" answer, so I keep it short and generic.
Usually I prefer to give context in translation (for translator), e.g. providing template: _("active {user_name}" (so also the ordering will be correct if languages want different ordering).
Then you may need to change code and template into _("active {first_name_feminine}") and _("active {first_name_masculine}") (and possibly more for duals, trials, plurals, collectives, honorific, etc.). Note: check that the translator will not mangle the {} and the string inside. Usually you need specific export/import scripts. Or I add a note inside the string, and I quickly translate into English removing the note to the translator). Also this can be automated (be creative on using special Unicode characters which should not be used in normal text, to delimit such text).
But if you cannot know the gender, the Actif(ve) may be the polite version used in such language. You need a native speaker test, and changes back and forth.
I got a financial application and I wish to add to it the ability to get user command or input in textbox and then take the right action. for example, wish the user to write "show the revenue in the last 10 days" and it'll show the revenue to him/her - the point is that I wish it to really understand the meaning of the question, so the previus statement will bring the same results as "do I got any revenue in the last 10 days" or something like that - BI (something like the Wolfram|Alpha engine).
I wonder if there's any opensource library or algorithm books or whatever that I can use to learn the subject. Regards to opensource libraries - I don't mind which language it'll be written in.
I've read about this subject and saw many engines and services (OpenNLP, Apache UIMA, CoreNLP etc.) but did not figure out if they're right for my needs.
Any answer or suggestion is welcome.
Many thanks!
The field you're talking about is usually called "natural language processing". It's hard, and an active field of research. There are various libraries which you could consider based on your preferred programming language and use case:
http://en.wikipedia.org/wiki/List_of_natural_language_processing_toolkits
I've used NLTK a little bit. This field is seriously difficult to get right, so you might want to try to restrict your application to some small set of verbs and nouns such that people are using a controlled vocabulary in the first instance, and then try to extend it beyond that.
I have users that have authenticated with a social media site. Now based on their last X (let's say 200) posts, I want to map how much that content matches up with a finite list of keywords.
What would be the best way to do this to capture associated words/concepts (maybe that's too difficult) or just get a score of how much, say, my tweet history maps to 'Walrus' or 'banana'?
Would a naive Bayes work here to separate into 'matches' and 'no match'?
In Python I would say NLTK can easily do it. In Ruby maybe gem called lda-ruby will help you. Whole LDA concept is well explained here - look at Sarah Palin's email for example. There's even the example of an app (not entirely in Ruby, but still) which did that -> github.com/echen/sarah-palin-lda
Or maybe I just say stupid things and that can't help you at all. I'm not an expert ;)
A simple bayes would work in this case, it is highly used to detect if emails are spam or not so for a simple keyword matching it should work pretty well.
For this problem you could also apply a recommendation system where you look for the top recommended keyword for a user (or for a post).
There are a ton of ways for doing this. I would recommend you to read Programming Collective Intelligence. It is explained using python but since you know ruby there should be not problem to understand the code.
I have tags on my website, and I input them one by one when I create a blog post. I love gmail's new feature, that ask you if you want to include X in a mail, if you type Y's name and that you often include both of them in the same messages.
I'd like to do something similar on my website, but I don't know how to represent the tags "related-ness" in an object or database ... thoughts ?
It all boils down to create associations between certain characteristics of your posts and certain tags, and then - when you press the "publish" button - to analyse the new post and propose all tags matched with your post characteristics.
This can be done in several ways from a "totally hard-coded" association to some sort of "learning AI"... and everything in-between.
Hard-coded solutions
This are the simplest algorithms to implement. You should first decide what characteristics of your post are relevant for tagging (e.g.: it's length if you tag them "short" or "long", the presence of photos or videos if you tag them "multimedia-content", etc...). The most obvious is however to focus on which words are used in posts. For example you could build a mapping like this:
tag_hint_words = {'code-development' : ['programming',
'language', 'python', 'function',
'object', 'method'],
'family' : ['Theresa', 'kids',
'uncle Ben', 'holidays']}
Then you would check your post for the presence of the words in the list (the code between [ and ] ) and propose the tag (the word before :) as a possible candidate.
A common approach is to give "scores", or in other word to put a number that indicates the probability a given tag is the right one. For example: if your post would contain the sentence...
After months of programming, we finally left for the summer holidays at uncle Ben's cottage. Theresa and the kids were ecstatic!
...despite the presence of the word "programming" the program should indicate family as the most likely tag to use, as there are many more words hinting.
Learning AI's
One of the obvious limitations of the above method is that - say one day you pick up java beside python - you would probably need to change your code and include words like "java" or "oracle" too. The same applies if you create new tags.
To circumvent this limitation (and have some fun!!) you could try to implement a learning algorithm. Learning algorithms are those who refine their outcome the more you use them (so they indeed... learn!). Some algorithm requires initial training (many spam filters and voice recognition programs need this initial "primer"). Some don't.
I am absolutely no expert on the subject, but two common AI's are: the Naive Bayes Classifier and some flavour of Neural network.
Although the WP pages might look scary, they are surprisingly easy to implement (at least in Python). Here's the recording of a lecture at PyCon 2009 on the subject "Easy AI with Python". I found it very informative and even somehow inspiring! :)
HTH!
You should have a look at this post :
Any suggestions for a db schema for storing related keywords?
If you're looking for a schema for storing related tags it will help.
Relevancy searches where multiple agents play a part are usually done using Collaborative filtering. You might want to give that a look see.
Look up Clustering (Machine Learning algorithm). Don't be intimidated by math, it's a pretty straightforward algorithm. Check out Machine Learning for Hackers for simpler explanations of many Machine Learning algorithms and methods.
To make matter more specific:
How to detect people names (seems like simple case of named entity extraction?)
How to detect addresses: my best guess - find postcode (regexes); country and town names and take some text around them.
As for phones, emails - they could be probably caught by various regexes + preprocessing
Don't care about education/working experience at this point
Reasoning:
In order to build a fulltext index on resumes all vulnerable information should be stripped out from them.
P.S. any 3rd party APIs/services won't do as a solution.
The problem you're interested in is information extraction from semi structured sources. http://en.wikipedia.org/wiki/Information_extraction
I think you should download a couple of research papers in this area to get a sense of what can be done and what can't.
I feel it can't be done by a machine.
Every other resume will have a different format and layout.
The best you can do is to design an internal format and manually copy every resume content in there. Or ask candidates to fill out your form (not many will bother).
I think that the problem should be broken up into two search domains:
Finding information relating to proper names
Finding information that is formulaic
Firstly the information relating to proper names could probably be best found by searching for items that are either grammatically important or significant. I.e. English capitalizes only the first word of the sentence and proper nouns. For the gramatical rules you could look for all of the words that have the first letter of the word capitalized and check it against a database that contains the word and the type [i.e. Bob - Name, Elon - Place, England - Place].
Secondly: Information that is formulaic. This is more about the email addresses, phone numbers, and physical addresses. All of these have a specific formats that don't change. Use a regex and use an algorithm to detect the quality of the matches.
Watch out:
The grammatical rules change based on language. German capitalizes EVERY noun. It might be best to detect the language of the document prior to applying your rules. Also, another issue with this [and my resume sometimes] is how it is designed. If the resume was designed with something other than a text editor [designer tools] the text may not line up, or be in a bitmap format.
TL;DR Version: NLP techniques can help you a lot.