My documents often include sentences like:
Had I known about this, I would have prevented this problem
or
If John was informed, this wouldn't happen
or
this wouldn't be a problem if Jason was smart
I'm interested in extracting these sort of information (not sure what they are called, linguistically). So I would like to extract either the whole sentence, or ideally, a summary like:
(inform John) (prevent)
Most, if not all, the examples of relation extraction, and information extraction that I've come across, follow fairly standard flow:
do NER, then relation extraction looks for relations like "in" or "at", etc (ch7 of nltk book for example).
Do these type of sentences fall under a certain category in NLP? Are there any papers/tutorials on something like this?
When you are asking for a suggestion on a topic which is pretty open, give more examples. I mean to say, if you just give one example and explain what are you targeting doesn't give enough information. For example, if you have sentences which following specific patterns, then it becomes easier to extract information (in your desired format) from them. Otherwise, it becomes broad and complex research problem!
From your example, it looks like you want to extract the head words of a sentence and other words which modify those heads. You can use dependency parsing for this task. Look at Stanford Neural Network Dependency Parser. A dependency parser analyzes the grammatical structure of a sentence, establishing relationships between "head" words and words which modify those heads. So, i believe it should help you in your desired task.
If you want to make it more general, then this problem aligns well with Open Information Extraction. You may consider looking into Stanford OpenIE api.
You may also consider Stanford Relation Extractor api in your task. But i strongly believe relation extraction through dependency parsing best suits your problem definition. You can read this paper to get some idea and utilize them in your task.
Related
I am looking into extracting the meaning of expressions used in everyday speaking. For an instance, it is apparent to a human that the sentence The meal we had at restaurant A tasted like food at my granny's. means that the food was tasty.
How can I extract this meaning using a tool or a technique?
The method I've found so far is to first extract phrases using Stanford CoreNLP POS tagging, and use a Word Sense Induction tool to derive the meaning of the phrase. However, as WSI tools are used to get the meaning of words when they have multiple meanings, I am not sure if it would be the best tool to use.
What would be the best method to extract the meanings? Or is there any tool that can both identify phrases and extract their meanings?
Any help is much appreciated. Thanks in advance.
The problem you pose is a difficult one. You should use tools from Sentiment Analysis to get a gist of the sentence emotional message. There are more sophisticated approaches which attempt at extracting what quality is assigned to what object in the sentence (this you can get from POS-tagged sentences + some hand-crafted Information Extraction rules).
However, you may want to also explore paraphrasing the more formal language to the common one and look for those phrases. For that you would need to a good (exhaustive) dictionary of common expressions to start with (there are sometimes slang dictionaries available - but I am not aware of any for English right now). You could then map the colloquial ones to some more formal ones which are likely to be caught by some embedding space (frequently used in Sentiment Analysis).
I am a graduate student focusing on ML and NLP. I have a lot of data (8 million lines) and the text is usually badly written and contains so many spelling mistakes.
So i must go through some text cleaning and vectorizing. To do so, i considered two approaches:
First one:
cleaning text by replacing bad words using hunspell package which is a spell checker and morphological analyzer
+
tokenization
+
convert sentences to vectors using tf-idf
The problem here is that sometimes, Hunspell fails to provide the correct word and changes the misspelled word with another word that don't have the same meaning. Furthermore, hunspell does not reconize acronyms or abbreviation (which are very important in my case) and tends to replace them.
Second approache:
tokenization
+
using some embeddings methode (like word2vec) to convert words into vectors without cleaning text
I need to know if there is some (theoretical or empirical) way to compare this two approaches :)
Please do not hesitate to respond If you have any ideas to share, I'd love to discuss them with you.
Thank you in advance
I post this here just to summarise the comments in a longer form and give you a bit more commentary. No sure it will answer your question. If anything, it should show you why you should reconsider it.
Points about your question
Before I talk about your question, let me point a few things about your approaches. Word embeddings are essentially mathematical representations of meaning based on word distribution. They are the epitome of the phrase "You shall know a word by the company it keeps". In this sense, you will need very regular misspellings in order to get something useful out of a vector space approach. Something that could work out, for example, is US vs. UK spelling or shorthands like w8 vs. full forms like wait.
Another point I want to make clear (or perhaps you should do that) is that you are not looking to build a machine learning model here. You could consider the word embeddings that you could generate, a sort of a machine learning model but it's not. It's just a way of representing words with numbers.
You already have the answer to your question
You yourself have pointed out that using hunspell introduces new mistakes. It will be no doubt also the case with your other approach. If this is just a preprocessing step, I suggest you leave it at that. It is not something you need to prove. If for some reason you do want to dig into the problem, you could evaluate the effects of your methods through an external task as #lenz suggested.
How does external evaluation work?
When a task is too difficult to evaluate directly we use another task which is dependent on its output to draw conclusions about its success. In your case, it seems that you should pick a task that depends on individual words like document classification. Let's say that you have some sort of labels associated with your documents, say topics or types of news. Predicting these labels could be a legitimate way of evaluating the efficiency of your approaches. It is also a chance for you to see if they do more harm than good by comparing to the baseline of "dirty" data. Remember that it's about relative differences and the actual performance of the task is of no importance.
I'm embarking on a project for a non-profit organization to help process and classify 1000's of reports annually from their field workers / contractors the world over. I'm relatively new to NLP and as such wanted to seek the group's guidance on the approach to solve our problem.
I'll highlight the current process, and our challenges and would love your help on the best way to solve our problem.
Current process: Field officers submit reports from locally run projects in the form of best practices. These reports are then processed by a full-time team of curators who (i) ensure they adhere to a best-practice template and (ii) edit the documents to improve language/style/grammar.
Challenge: As the number of field workers increased the volume of reports being generated has grown and our editors are now becoming the bottle-neck.
Solution: We would like to automate the 1st step of our process i.e., checking the document for compliance to the organizational best practice template
Basically, we need to ensure every report has 3 components namely:
1. States its purpose: What topic / problem does this best practice address?
2. Identifies Audience: Who is this for?
3. Highlights Relevance: What can the reader do after reading it?
Here's an example of a good report submission.
"This document introduces techniques for successfully applying best practices across developing countries. This study is intended to help low-income farmers identify a set of best practices for pricing agricultural products in places where there is no price transparency. By implementing these processes, farmers will be able to get better prices for their produce and raise their household incomes."
As of now, our approach has been to use RegEx and check for keywords. i.e., to check for compliance we use the following logic:
1 To check "states purpose" = we do a regex to match 'purpose', 'intent'
2 To check "identifies audience" = we do a regex to match with 'identifies', 'is for'
3 To check "highlights relevance" = we do a regex to match with 'able to', 'allows', 'enables'
The current approach of RegEx seems very primitive and limited so I wanted to ask the community if there is a better way to solving this problem using something like NLTK, CoreNLP.
Thanks in advance.
Interesting problem, i believe its a thorough research problem! In natural language processing, there are few techniques that learn and extract template from text and then can use them as gold annotation to identify whether a document follows the template structure. Researchers used this kind of system for automatic question answering (extract templates from question and then answer them). But in your case its more difficult as you need to learn the structure from a report. In the light of Natural Language Processing, this is more hard to address your problem (no simple NLP task matches with your problem definition) and you may not need any fancy model (complex) to resolve your problem.
You can start by simple document matching and computing a similarity score. If you have large collection of positive examples (well formatted and specified reports), you can construct a dictionary based on tf-idf weights. Then you can check the presence of the dictionary tokens. You can also think of this problem as a binary classification problem. There are good machine learning classifiers such as svm, logistic regression which works good for text data. You can use python and scikit-learn to build programs quickly and they are pretty easy to use. For text pre-processing, you can use NLTK.
Since the reports will be generated by field workers and there are few questions that will be answered by the reports (you mentioned about 3 specific components), i guess simple keyword matching techniques will be a good start for your research. You can gradually move to different directions based on your observations.
This seems like a perfect scenario to apply some machine learning to your process.
First of all, the data annotation problem is covered. This is usually the most annoying problem. Thankfully, you can rely on the curators. The curators can mark the specific sentences that specify: audience, relevance, purpose.
Train some models to identify these types of clauses. If all the classifiers fire for a certain document, it means that the document is properly formatted.
If errors are encountered, make sure to retrain the models with the specific examples.
If you don't provide yourself hints about the format of the document this is an open problem.
What you can do thought, is ask people writing report to conform to some format for the document like having 3 parts each of which have a pre-defined title like so
1. Purpose
Explains the purpose of the document in several paragraph.
2. Topic / Problem
This address the foobar problem also known as lorem ipsum feeling text.
3. Take away
What can the reader do after reading it?
You parse this document from .doc format for instance and extract the three parts. Then you can go through spell checking, grammar and text complexity algorithm. And finally you can extract for instance Named Entities (cf. Named Entity Recognition) and low TF-IDF words.
I've been trying to do something very similar with clinical trials, where most of the data is again written in natural language.
If you do not care about past data, and have control over what the field officers write, maybe you can have them provide these 3 extra fields in their reports, and you would be done.
Otherwise; CoreNLP and OpenNLP, the libraries that I'm most familiar with, have some tools that can help you with part of the task. For example; if your Regex pattern matches a word that starts with the prefix "inten", the actual word could be "intention", "intended", "intent", "intentionally" etc., and you wouldn't necessarily know if the word is a verb, a noun, an adjective or an adverb. POS taggers and the parsers in these libraries would be able to tell you the type (POS) of the word and maybe you only care about the verbs that start with "inten", or more strictly, the verbs spoken by the 3rd person singular.
CoreNLP has another tool called OpenIE, which attempts to extract relations in a sentence. For example, given the following sentence
Born in a small town, she took the midnight train going anywhere
CoreNLP can extract the triple
she, took, midnight train
Combined with the POS tagger for example; you would also know that "she" is a personal pronoun and "took" is a past tense verb.
These libraries can accomplish many other tasks such as tokenization, sentence splitting, and named entity recognition and it would be up to you to combine all of these tools with your domain knowledge and creativity to come up with a solution that works for your case.
I have a collection of "articles", each 1 to 10 sentences long, written in a noisy, informal english (i.e. social media style).
I need to extract some information from each article, where available, like date and time. I also need to understand what the article is talking about and who is the main "actor".
Example, given the sentence: "Everybody's presence is required tomorrow morning starting from 10.30 to discuss the company's financial forecast.", I need to extract:
the date/time => "10.30 tomorrow morning".
the topic => "company's financial forecast".
the actor => "Everybody".
As far as I know, the date and time could be extracted without using NLP techniques but I haven't found anything as good as Natty (http://natty.joestelmach.com/) in Python.
My understanding on how to proceed after reading some chapters of the NLTK book and watching some videos of the NLP courses on Coursera is the following:
Use part of the data to create an annotated corpus. I can't use off-the-shelf corpus because of the informal nature of the text (e.g. spelling errors, uninformative capitalization, word abbreviations, etc...).
Manually (sigh...) annotate each article with tags from the Penn TreeBank tagset. Is there any way to automate this step and just check/fix the results ?
Train a POS tagger on the annotated article. I've found the NLTK-trainer project that seems promising (http://nltk-trainer.readthedocs.org/en/latest/train_tagger.html).
Chunking/Chinking, which means I'll have to manually annotate the corpus again (...) using the IOB notation. Unfortunately according to this bug report n-gram chunkers are broken: https://github.com/nltk/nltk/issues/367. This seems like a major issue, and makes me wonder whether I should keep using NLTK given that it's more than a year old.
At this point, if I have done everything correctly, I assume I'll find actor, topic and datetime in the chunks. Correct ?
Could I (temporarily) skip 1,2 and 3 and produce a working, but possibly with a high error rate, implementation ? Which corpus should I use ?
I was also thinking of a pre-process step to correct common spelling mistakes or shortcuts like "yess", "c u" and other abominations. Anything already existing I can take advantage of ?
THE question, in a nutshell, is: is my approach at solving this problem correct ? If not, what am I doing wrong ?
Could I (temporarily) skip 1,2 and 3 and produce a working, but
possibly with a high error rate, implementation ? Which corpus should
I use ?
I was also thinking of a pre-process step to correct common spelling
mistakes or shortcuts like "yess", "c u" and other abominations.
Anything already existing I can take advantage of ?
I would suggest you first have a go at processing standard language text. The pre-processing you refer to is an NLP task in its own right, known as normalization. Here is a resource for Twitter normalization: http://www.ark.cs.cmu.edu/TweetNLP/ , additionally, you can use spell checking, sentence boundary detection, ...
THE question, in a nutshell, is: is my approach at solving this
problem correct ? If not, what am I doing wrong ?
If you make abstraction of normalization, I think your approach is valid. With regard to automating the annotation process: you can bootstrap the process by using off-the-shelf components first, after which you correct, retrain, and so on, ... during different iterations. To get acceptable results, you will need to do your steps 2, 3, and 4 a couple of times.
If you are interested in understanding the problem and being able to optimize existing solutions, I would suggest you focus on tools that allow you to develop your own models. If you prioritize getting results over being able to develop your own models, I would recommend looking into existing open source text engineering frameworks such as Gate (https://gate.ac.uk/) UIMA (http://uima.apache.org/) and DKPro (which extends UIMA) (https://code.google.com/p/dkpro-core-asl/). All three frameworks wrap existing components, so you have a wide range of possible solutions.
I'd suggesting giving a try to NER and Temporal Normalizer.
Here is what I see for your example sentence:
You can try the demo here:
http://deagol.cs.illinois.edu:8080/
I need to do an experiment and I am new in NLP. I have read books that explain the theoritical issues but when it comes to practical I found it hard to find a guide. so please who knows anything in NLP especially the practical issues tell me and point me to the right path because I feel I am lost (useful books, useful tools and useful websites)
what I am trying to do is to take a text and find specific words for example animals such as dogs, cats,...etc in it then I need to extract this word and 2 words on each side.
For example
I was watching TV with my lovely cat last night.
the extracted text will be
(my lovely cat last night)
This will be my training example to the machine tool
Q1: there will be around 100 training examples similar to what I explained above. I used tocknizer to extracts words but how can I extract specific words(for our example all types of animals) with 2 words on each side. do I need to use tags for example or what is your idea?
Q2: If I have these training examples how can I prepare appropriate datasets that I can give it to the machine tool to train it? what should I write in this dataset to specify the animal and should I need to give other features? and how can I arrange it in a dataset .
many words from you might help me a lot please do not hesitate to tell what you know
What you are attempting to do is sometimes known as "Ontology Acquisition" or "Automated Ontology", and is a pretty difficult problem. Most approaches come down to "Words that are similar will tend to be used in similar contexts." The problem with this is that while there are algorithms that successfully extract semantically meaningful relationships from data such as yours, going from "Here are a bunch of terms that statistically share a common distribution with your seed terms" to "your seed terms are animal names, here are some other animal names" is challenging. For example, training on cat,dog, snake, bird, might end up giving you results like "mammal, dachshund, creature, biped" are used in similar contexts, but depending on your requirements, may not be exactly what you need.
Below is a link to a research paper that implemented exactly what you are trying to do. They describe their approach to data representation and algorithms used, and perform with at least some level of success on the animal name problem. In addition, tracking down their references may be a fruitful exercise..
http://www.cl.cam.ac.uk/~ah433/cluk.pdf
Let me begin by saying that being a self-taught engineer when I started working in NLP several years ago, I completely understand your frustration. I would suggest that you read the NLTK book which is a wonderful introduction to applied NLP. In particular, read Chapters 3-7 which deal with processing raw text data to extract information and use it for tagging. The book is available online.
With regards to your specific question:
I think that it might be much easier to create a small list of animals and then extract sentences from a corpus that contain these animal names. Wikipedia sentences is one obvious example. You can build your corpus using this method because you already know the names of the animals in each sentence.
// PSEUDO CODE
Dictionary animals = ["dog","dogs,"cat","cats","pig","pigs","cow","cows","lion","lions","lioness","lionesses"];
String[] sentences = getWikipediaSentences();
for(sent: sentences){
for(token: Tokenizer.getTokens(sent)){
if(animals.contains(token){
addSentenceToCorpus(sent)
} // else ignore sentence
}
}
You can then train your algorithm on these sentences so that you can use the trained model to extract newer animal names. There are caveats with this approach since your "training data" is artificially collected but it will be a good first experience nonetheless.