I am parsing contract announcements into columns to capture the company, the amount awarded, the description of the project awarded, etc. A raw example can be found here.
I wrote a script using regular expressions to do this but over time contingencies arise that I have to account for which bar the regexp method from being a long term solution. I have been reading up on NLTK and it seems there are two ways to go about using NLTK to solve my problem:
chunk the announcements using RegexpParser expressions - this might be a weak solution if two different fields I want to capture have the same sentence structure.
take n announcements, tokenize and run the n announcements through the pos tagger, manually tag the parts of the announcements I want to capture using the IOB format and then use those tagged announcements to train an NER model. A method discussed here
Before I go about manually tagging announcements I want to gauge
that 2 is a reasonable solution
if there are existing tagged corpus that might be useful to train my model
knowing that accuracy improves with training data size, how many manually tagged announcements I should start with.
Here's an example of how I am building the training set. If there are any apparent flaws please let me know.
Trying to get company names and project descriptions using just POS tags will be a headache. Definitely go the NER route.
Spacy has a default English NER model that can recognize organizations; it may or may not work for you but it's worth a shot.
What sort of output do you expect for "the description of the project awarded"? Typically NER would find items several tokens long, but I could imagine a description being several sentences.
For tagging, note that you don't have to work with text files. Brat is an open-source tool for visually tagging text.
How many examples you need depends on your input, but think of about a hundred as the absolute minimum and build up from there.
Hope that helps!
Regarding the project descriptions, thanks to your example I now have a better idea. It looks like the language in the first sentence of the grants is pretty regular in how it introduces the project description: XYZ Corp has been awarded $XXX for [description here].
I have never seen typical NER methods used for arbitrary phrases like that. If you've already got labels there's no harm in trying and seeing how prediction goes, but if you have issues there is another way.
Given the regularity of language a parser might be effective here. You can try out the Stanford Parser online here. Using the output of that (a "parse tree"), you can pull out the VP where the verb is "award", then pull out the PP under that where the IN is "for", and that should be what you're looking for. (The capital letters are Penn Treebank Tags; VP means "verb phrase", PP means "prepositional phrase", IN means "preposition.)
Related
I have ~138k records of user feedback that I'd like to analyze to understand broad patterns in what our users are most often saying. Each one has a rating between 1-5 stars, so I don't need to do any sort of sentiment analysis. I'm mostly interested in splitting the dataset into >=4 stars to see what we're doing well and <= 3 stars to see what we need to improve upon.
One key problem I'm running into is that I expect to see a lot of n-grams. Some of these I know, like "HOV lane", "carpool lane", "detour time", "out of my way", etc. But I also want to detect common bi- and tri-grams programmatically. I've been playing around with Spacy a bit, but it doesn't seem to have any capability to do analysis on the corpus level, only on the document level.
Ideally my pipeline would look something like this (I think):
Import a list of known n-grams into the tokenizer
Process each string into a tokenized document, removing punctuation,
stopwords, etc, while respecting the known n-grams during
tokenization (ie, "HOV lane" should be a single noun token)
Identify the most common bi- and tri- grams in the corpus that I
missed
Re-tokenize using the found n-grams
Split by rating (>=4 and <=3)
Find the most common topics for each split of data in the corpus
I can't seem to find a single tool, or even a collection of tools, that will allow me to do what I want here. Am I approaching this the wrong way somehow? Any pointers on how to get started would be greatly appreciated!
Bingo State of the art results for your problem!
Its called - Zero-Short learning.
State-of-the-art NLP models for text classification without annotated data.
For Code and details read the blog - https://joeddav.github.io/blog/2020/05/29/ZSL.html
Let me know if it works for you or for any other help.
VADER tool is perfect with sentiment analysis and NLP based applications.
I think the proposed workflow is fine with this case study. Closely work with your feature extraction as it matters a lot.
Most of the time tri-grams make a sound sense on these use cases.
Using Spacy would be a better decision as SpaCy's rules-based match engines and components not only help you to find what the terms and sentences are searching for but also allow you to access the tokens inside a text and its relationships compared with regular expressions.
Is there any efficient way to extract sub topic explanations of a review using python and NLTK library.As an example an user review regarding mobile phone could be "This phone's battery is good but display is a bullshit"
I wanna extract above two features like
"Battery is good"
"display is a bullshit"
The purpose of above is em gonna develop a rating system for products with respect to features of the product.
Analyzing polarity part has done.
But extracting features of review is some difficult for me.But I found a way to extract features using POS tag patterns with regular expressions like
<NN.?><VB.?>?<JJ.?>
this pattern as sub topic.But the problem is there could be lots of patterns in a review according to users description patterns.
Is there any way to solve my problem efficiently???
Thank you !!
The question you posed is multi-faceted and not straightforward to answer.
Conceptually, you may want to go through the following steps:
Identify the names of the features of phones (+ maybe creating an ontology based on these features).
Create a lists of synonyms to the feature names (similarly for evaluative phrases, e.g. nice, bad, sucks, etc.).
Use one of NLTK taggers to parse the reviews.
Create rules for extraction of features and their evaluation (Information Extraction part). I am not sure if NLTK can directly support you with this.
Evaluate and refine the approach.
Or: create a larger annotated corpus and train a Deep learning model on it using TensorFlow, Theano, or anything else alike.
I want to parse a text and categorize the sentences according to their grammatical structure, but I have a very small understanding of NLP so I don't even know where to start.
As far as I have read, I need to parse the text and find out (or tag?) the part-of-speech of every word. Then I search for the verb clause or whatever other defining characteristic I want to use to categorize the sentences.
What I don't know is if there is already some method to do this more easily or if I need to define the grammar rules separately or what.
Any resources on NLP that discuss this would be great. Program examples are welcome as well. I have used NLTK before, but not extensively. Other parsers or languages are OK too!
Python Natural Language Toolkit is a library which is suitable for doing such a work. As with any NLP library, you will have to download the dataset for training separately and corpus(data) and scripts for training are available too.
There are also certain example tutorials which will help you identify parts of the speech for words. By all means, I think nltk.org should be the place to go for what you are looking for.
Specific questions could be posted here again.
May be you need simply define patterns like "noun verb noun" etc for each type of grammatical structure and search matches in part-of-speach tagger output sequence.
I'm doing a project on mining blog contents and I need help differentiating on which tool to uses. When do I use a parser, when do I use a tagger, and when do I need to use a NER tool?
For instance, I want to find out the most talked about topics/subjects between several blogs; do I use a part-of-speech tagger to grab the nouns and do a frequency count? That would probably be insufficient because very generic terms can pop up right? Or do I have a list of categories and these synonyms that I can match on?
BTW, I'm using nltk, but am looking at stanford tagger or parser since a couple of dudes said that it was good.
Instead of trying to reinvent the wheel, you might want to read up on Topic Models, which basically creates clusters of words that frequently occur together. Mallet has a readily available toolkit for doing such a task: http://mallet.cs.umass.edu/topics.php .
To answer your original question, POS tagger, parsers, and NER tools are not typically used for topic identification, but are more heavily used for tasks like information extraction where the goal is to identify within a document the specific actors, events, locations, times, etc... For example if you had a simple sentence like "John gave the apple to Mary." you might use a dependency parser to figure out that John is the subject, the apple is the object, and Mary is the prepositional object; thus you know John is the giver and Mary is the receiver and not vice-versa.
I was wondering how as semantic service like Open Calais figures out the names of companies, or people, tech concepts, keywords, etc. from a piece of text. Is it because they have a large database that they match the text against?
How would a service like Zemanta know what images to suggest to a piece of text for instance?
Michal Finkelstein from OpenCalais here.
First, thanks for your interest. I'll reply here but I also encourage you to read more on OpenCalais forums; there's a lot of information there including - but not limited to:
http://opencalais.com/tagging-information
http://opencalais.com/how-does-calais-learn
Also feel free to follow us on Twitter (#OpenCalais) or to email us at team#opencalais.com
Now to the answer:
OpenCalais is based on a decade of research and development in the fields of Natural Language Processing and Text Analytics.
We support the full "NLP Stack" (as we like to call it):
From text tokenization, morphological analysis and POS tagging, to shallow parsing and identifying nominal and verbal phrases.
Semantics come into play when we look for Entities (a.k.a. Entity Extraction, Named Entity Recognition). For that purpose we have a sophisticated rule-based system that combines discovery rules as well as lexicons/dictionaries. This combination allows us to identify names of companies/persons/films, etc., even if they don't exist in any available list.
For the most prominent entities (such as people, companies) we also perform anaphora resolution, cross-reference and name canonization/normalization at the article level, so we'll know that 'John Smith' and 'Mr. Smith', for example, are likely referring to the same person.
So the short answer to your question is - no, it's not just about matching against large databases.
Events/Facts are really interesting because they take our discovery rules one level deeper; we find relations between entities and label them with the appropriate type, for example M&As (relations between two or more companies), Employment Changes (relations between companies and people), and so on. Needless to say, Event/Fact extraction is not possible for systems that are based solely on lexicons.
For the most part, our system is tuned to be precision-oriented, but we always try to keep a reasonable balance between accuracy and entirety.
By the way there are some cool new metadata capabilities coming out later this month so stay tuned.
Regards,
Michal
I'm not familiar with the specific services listed, but the field of natural language processing has developed a number of techniques that enable this sort of information extraction from general text. As Sean stated, once you have candidate terms, it's not to difficult to search for those terms with some of the other entities in context and then use the results of that search to determine how confident you are that the term extracted is an actual entity of interest.
OpenNLP is a great project if you'd like to play around with natural language processing. The capabilities you've named would probably be best accomplished with Named Entity Recognizers (NER) (algorithms that locate proper nouns, generally, and sometimes dates as well) and/or Word Sense Disambiguation (WSD) (eg: the word 'bank' has different meanings depending on it's context, and that can be very important when extracting information from text. Given the sentences: "the plane banked left", "the snow bank was high", and "they robbed the bank" you can see how dissambiguation can play an important part in language understanding)
Techniques generally build on each other, and NER is one of the more complex tasks, so to do NER successfully, you will generally need accurate tokenizers (natural language tokenizers, mind you -- statistical approaches tend to fare the best), string stemmers (algorithms that conflate similar words to common roots: so words like informant and informer are treated equally), sentence detection ('Mr. Jones was tall.' is only one sentence, so you can't just check for punctuation), part-of-speech taggers (POS taggers), and WSD.
There is a python port of (parts of) OpenNLP called NLTK (http://nltk.sourceforge.net) but I don't have much experience with it yet. Most of my work has been with the Java and C# ports, which work well.
All of these algorithms are language-specific, of course, and they can take significant time to run (although, it is generally faster than reading the material you are processing). Since the state-of-the-art is largely based on statistical techniques, there is also a considerable error rate to take into account. Furthermore, because the error rate impacts all the stages, and something like NER requires numerous stages of processing, (tokenize -> sentence detect -> POS tag -> WSD -> NER) the error rates compound.
Open Calais probably use language parsing technology and language statics to guess which words or phrases are Names, Places, Companies, etc. Then, it is just another step to do some kind of search for those entities and return meta data.
Zementa probably does something similar, but matches the phrases against meta-data attached to images in order to acquire related results.
It certainly isn't easy.