Respected Sir, Mem
I Wants to summarizing of text document (any unstructured i.e news Data). My first target is to find important events in this given text data and next(2nd step) based on these events i will select some important events (by some methods).
Please tell me some paper to find EVENTS from Text.(If LATEST then will be better)
Please tell me some paper which finding EVENTS using MACHINE LEARNING or SOFT COMPUTING.
THANK YOU
chandrtech15#gmail.com
http://www.google.com/cse?cx=011664571474657673452%3A4w9swzkcxiy&cof=FORID%3A0&q=event+extraction#gsc.tab=0&gsc.q=event%20extraction&gsc.page=1 This is a list of a google search over the ACL (Association for Computational Linguistics) anthology. There should be many relevant papers on the list.
Related
I am trying to scrape a website for financials of Indian companies as a side project & put it in Google Sheets using XPATH
Link: https://ticker.finology.in/company/AFFLE
I am able to extract data from elements that have a specific id like cash, net debt, etc. however I am stuck with extracting data for labels like Sales Growth.
tried
Copying the full xpath from console, //*[#id="mainContent_updAddRatios"]/div[13]/p/span - this works, however, i am reliable on the index of the div (13) and that may change for different companies, hence i am unable to automate it.
Please assist with a scalable solution
PS: I am a Product Manager with basic coding expertise as I was a developer few years ago.
At some point you need to "hardcode" something unless you have some other means of mapping the content of the page to your spreadsheet. In your example you appear to be targeting "Sales Growth" percentage. If you are not comfortable hardcoding the index of the div (13), you could identify it by the id of the "Sales Growth" label which is mainContent_lblSalesGrowthorCasa.
For example, change your
//*[#id="mainContent_updAddRatios"]/div[13]/p/span
to:
//*[#id = "mainContent_updAddRatios"]/div[.//span/#id = "mainContent_lblSalesGrowthorCasa"]/p/span
which is selecting the div based on the div containing a span with id="mainContent_lblSalesGrowthorCasa". Ultimately, whether you "hardcode" the exact index of the div or "hardcode" the ids of the nodes, you are still embedding assumptions regarding the structure of page.
Thanks #david, that helped.
Two questions
What if the structure of the page would change? Example: If the website decided to remove the p tag then would my sheet fail? How do we avoid failure in such cases?
Also, since every id is unique, the probability of that getting changed is lesser than the index being changed. Correct me, if I am wrong?
What do we do when the elements don't have an id like Profit Growth, RoE, RoCE etc
I've been working on building a data analysis sheet, which is quite verbose at the moment and a bit more complicated than it should be as I've been trying to figure this out. Please note, I work doing student data in a school.
Basically, I have two sets of input data:
Data imported from a CSV file that includes test data and codes for Common Core Standards and the questions tied to those standards as a whole class summary
Data imported from a CSV file that includes individual scores by question
I am looking to construct 2 views:
A view that collates and displays data of individual standards per student that includes a dropdown to change the standard allowing a teacher to see class performance by standard in a broad view. The drop-down is populated dynamically from the input data (so staff could eventually dump data and go directly to reports)
A view that collates and displays data of individual students broken down by performance on each standard allowing a teachers to see the broader spectrum for each student. The student drop-down is populated from Source list 2.
I have been able to build the first view, but am struggling with the second. I've been able to separate the question codes and develop strings of cell references to the scoring data, including a dynamic reference to the row the selected student's score data appears on in the second source set from above.
I tried to pass through an indirect() formula into a sum() so as to process for a mean evaluation, and have encountered errors. I think SUM() doesn't process comma-separated cell reference lists from Indirect() [or in general] or there is something that I am missing to help parse it. Here is the formula I have tried:
=Sum(vlookup(D7,CCCodeManip!$A:$C,3,false))
CCCodeManip!C:C includes the created text (based on the dynamic standards and question codes, etc), here's an example of what would be found there:
'M-ADI'!M17, 'M-ADI'!N17, 'M-ADI'!O17, 'M-ADI'!P17, 'M-ADI'!Q17, 'M-ADI'!R17, 'M-ADI'!J17
I need these to be dynamic so that teachers can input different sets of standards, question, and student data and the sheet automatically collates and reports it in uniform ways (with an upward bound of 20 standards as I currently have it built)
Here is a link to the sheet I built, with names and ID anonymized. There's a CRAP TON of sub-tabs, and that's really just being able to split apart and re-combine data neatly without things error-ing out due to data overlapping, aside from a few different attempts and different approaches to parse the cell reference strings.
The first two tabs are the current status of the data views. I plan to hide a bunch of the functional stuff that is there to help pull data accurately.
The 3rd and 4th tab are the source data sets. 5th is a modified version of source data that allows me to reference things better, and I've tried to arrange the sheets most relevant towards the front of the set.
https://docs.google.com/spreadsheets/d/1fR_2n60lenxkvjZSzp2VDGyTUO6l-3wzwaV4P-IQ_5Y/edit?usp=sharing
Some have a different approach? I am aware that I might be as far as I cn go with this and perhaps should consider scripts - my coding experience is a bit out of date and my strength is more with the formulas, but I can dig into things with some direction, if anyone can help.
Ok so I noticed something.
It seems the failure is in the indirect reference:
=indirect(CCCodeManip!C3)
The string I am trying to parse via indirect is going to be generated into something like this, dynamic from reference to other data:
'M-ADI'!M17, 'M-ADI'!N17, 'M-ADI'!O17, 'M-ADI'!P17, 'M-ADI'!Q17, 'M-ADI'!R17, 'M-ADI'!J17
The indirect returns the error that the above string is not a cell reference with the #REF code.
Can someone give me a clue as to what is causing this? I am going to dig into the docs on Indirect() from google and will post anything that I find.
Perhaps it is that indirect() can't handle lists, but only specific references and arrays, which may require me a to build a sheet to do the SUM formula on for each question set (?)
So I think I figured it out, but i Ended up parsing the data differently, basically doing the sum based on individual cell references and a separate sum formula, bypassing the need to do it all at once, it jsut makes my sheets a lot dirtier! I am eventually going to see if code could do it better if I need to, but this is closed for now.
Basically, I did individual cell references to recall scores in a row, then used a separate SUM formula, and created references / structures to be able to pull those sum() results. Achieves the same end, but with extra crap on the sheet.
I am developing a search engine modeled after google in my spare time.
I am using the original google research paper located at http://infolab.stanford.edu/~backrub/google.html as my guideline.
As i am developing a very very simplified version of google i am not using pagerank algorithm at all for now.
So far i have developed a simple parser and indexer whose result is that i have an inverted index containing number of hits, hit location and document hash against each unique word.
Now i am trying to develop a query engine. However i am finding it hard to identify the most relevant document for a multi token query.
Specifically lets say i am having difficulty in calculating the proximity of the query words to each other in a document.
I have thought of a algorithm that scans each document for the query words and calculates the proximity score based on how much the query words are close to each other however i suspect this would take a long time, and i think there is a better way to do this of which i am not aware and the research paper is too general to get an answer.
I am just looking for a pointer in the right direction.
Any sort of help would be very very very appreciated.
Look at the inverted index section of "Search Engine Indexing" on Wikipedia http://en.wikipedia.org/wiki/Search_engine_indexing#Inverted_indices
Basically, you want to save the position information of a given word within a document, this makes it easy to compute proximity. This information is saved in the index.
The key point is to index your documents so you don't need to scan them every time. The search for keywords is done on the index that points to the documents containing those keywords.
P.S. don't forget that you're trying to keep the index as small as possible, so storing gaps or differences for word positions will save same memory (as explained in: J. Zobel, A. Moffat - Inverted Files for Search Text Engines at page 23).
Looking for a way to get a list of telephone area codes for a given latitude and longitude (and if necessary a given intl. code.) Note, I'm not talking about international dialing prefixes but the area codes within them.
For example, Denver Colorado is covered by the area codes 303 and 720. It's at 39.739 -104.985 and is in NANP 1. So given 39.739,-104.985,1 I'd like to get back [303,720].
Libraries, web services, DB's, or raw data that needs to be parsed into a DB, e.g., a web page of shape points, are all fine and the more global coverage the better, but just NANP 1 would be a great help.
Note I already use MaxMind and could turn the lat-lng into a fake IP and use that as the lookup key, but MaxMind claims only U.S. area codes (whether they truly mean U.S. or actually NANP I haven't tested) and seemingly only 1 per location (e.g. just 303 for Denver.) So it's a possibility, just not a great one.
UPDATE: I found some more relevant information, but no definitive solutions so I'm listing it here rather than in an answer:
I was able to find two U.S. databases http://www.area-codes.com/area-code-database.asp and http://www.nationalnanpa.com/area_codes/index.html (50% down the page, MS Access file.) The former includes lat/lng for $450 and the latter would require nearest-neighbor matching as KeithS talks about (it's probably the same DB underlying the NANPA City Query he found.)
Additionally I found information that implies Teleatlas has area code boundary maps and that ESRI includes area code shape files with copies of ArcGIS. Maponics seems to have data available: there's a Google Maps implementation of Maponics' data at http://www.usnaviguide.com/areacode.htm.
Wow. You'll definitely need some sort of pre-existing database of points. My first thought was ZIPList5 Geocode. It includes lat-long data for each active U.S. ZIP code, so you can throw this data in a DB table, index the hell out of it, and search by just about any geographic info you'd have access to. You can buy one copy for $40, with enterprise-level use for $100. Only problem is that this DB has only the "primary" area code for each ZIP code, so metro areas that have more than one (Dallas, Chicago, NYC) aren't going to show all of them.
You could try a two-pronged approach with some free data I found: for a given latitude and longitude, do a nearest-neighbors search of the data in the USGS Geographic Names Information System; it includes information on every human habitation center, and every named landmark feature, with lat/long coordinates of their centers. You now have your lat/long point mapped to the nearest town/city, ZIP code, county, and state. Now, you can compare that against this list of U.S. Area Codes, to find area codes matching any or all of the identifying information from the USGS. This is all free, and will eventually get you what you need, but you'll probably have to do some work to "massage" the two sets of data into something you can efficiently cross-reference, and/or you'll need to implement a good "search engine" that will accurately find nearest-neighbor named points, and then find area codes for locations matching the names.
One more thing to look at is NANPA, which administers area code assignment to begin with. I'm sure they have a more comprehensive downloadable DB, but the only free public access I could find was this search page, which will find area codes for any city with >20k people. You could turn your lat/long data into a city and state, and then hit this search page: NANPA City Query
Here is an option:
http://geocoder.ca/39.739,-104.985?geoit=xml
<TimeZone>America/Denver</TimeZone>
<AreaCode>720,303</AreaCode
I have already asked a similar question earlier but I have notcied that I have big constrain: I am working on small text sets suchs as user Tweets to generate tags(keywords).
And it seems like the accepted suggestion ( point-wise mutual information algorithm) is meant to work on bigger documents.
With this constrain(working on small set of texts), how can I generate tags ?
Regards
Two Stage Approach for Multiword Tags
You could pool all the tweets into a single larger document and then extract the n most interesting collocations from the whole collection of tweets. You could then go back and tag each tweet with the collocations that occur in it. Using this approach, n would be the total number of multiword tags that would be generated for the whole dataset.
For the first stage, you could use the NLTK code posted here. The second stage could be accomplished with just a simple for loop over all the tweets. However, if speed is a concern, you could use pylucene to quickly find the tweets that contain each collocation.
Tweet Level PMI for Single Word Tags
As also suggested here, For single word tags, you could calculate the point-wise mutual information of each individual word and the tweet itself, i.e.
PMI(term, tweet) = log [ P(term, tweet) / (P(term)*P(tweet))
Again, this will roughly tell you how much less (or more) surprised you are to come across the term in the specific document as appose to coming across it in the larger collection. You could then tag the tweet with a few terms that have the highest PMI with the tweet.
General Changes for Tweets
Some changes you might want to make when tagging with tweets include:
Only use a word or collocation as a tag for a tweet, if it occurs within a certain number or percentage of other tweets. Otherwise, PMI will tend to tag tweets with odd terms that occur in just one tweet but that are not seen anywhere else, e.g. misspellings and keyboard noise like ##$##$%!.
Scale the number of tags used with the length of each tweet. You might be able to extract 2 or 3 interesting tags for longer tweets. But, for a shorter 2 word tweet, you probably don't want to use every single word and collocation to tag it. It's probably worth experimenting with different cut-offs for how many tags you want to extract given the tweet length.
I have used a method earlier, for small text content such as SMSes, where I would just repeat the same line two times. Surprisingly, that works well for such content where a noun could well be the topic. I mean, you don't need it to repeat for it to be the topic.