I have an algorithm (that I can't change) that outputs a list of phrases. These phrases are intended to be "topics". However, some of them are meaningless on their own. Take this list:
is the fear
freesat
are more likely to
first sight
an hour of
sue apple
depression and
itunes
How can I filter out those phrases that don't make sense on their own, to leave a list like the following?
freesat
first sight
sue apple
itunes
This will be applied to sets of phrases in many languages, but English is the priority.
It's got to be grammatically acceptable in that it can't rely on other words in the original sentence that it was extracted from; e.g. it can't end in 'and'.
Although this is still an underspecified question, it sounds like you want some kind of grammar checker. I suggest you try applying a part-of-speech tagger to each phrase, compile a list of patterns of POS tags that are acceptable (e.g. anything that ends in a preposition would be unacceptable) and use that to filter your input.
At a high level, it seems that phrases which were only nouns or adjective-noun combos would give much better results.
Examples:
"Blue Shirt"
"Happy People"
"Book"
First of all, this problem can be as complex as you want it to be. For third-party reading/solutions, I came across:
http://en.wikipedia.org/wiki/List_of_natural_language_processing_toolkits
http://research.microsoft.com/en-us/groups/nlp/
http://sharpnlp.codeplex.com/ (note the part of speech tagger)
If you need 100% accuracy, then I wouldn't write such a tool myself.
However, if the problem domain is limited...
I would start by throwing out conjunctions, prepositions, contractions, state-of-being verbs, etc. This is a fairly short list in English (and looks very similar to the stopwords which #HappyTimeGopher suggested).
After that, you could create a dictionary (as an indexed structure, of course) of all acceptable nouns and adjectives and compare each word in the raw phrases to that. Anything which didn't occur in the dictionary and occur in the correct sequence could be thrown out or ranked lower.
This could be useful if you were given 100 input values and wanted to select the best 5. Finding the values in the dictionary would mean that it's likely the word/phrase was good.
I've auto-generated such a dictionary before by building a raw index from thousands of documents pertaining to a vertical industry. I then spent a few hours with SQL and Excel stripping out problems easily spotted by a human. The resulting list wasn't perfect but it eliminated most of the blatantly dumb/pointless terminology.
As you may have guessed, none of this is foolproof, although checking adjective-to-noun sequence would help somewhat. Consider the case of "Greatest Hits" versus "Car Hits [Wall]".
Proper nouns (e.g. person names) don't work well with the dictionary approach, since it's probably not feasible to build a dictionary of all variations of given/surnames.
To summarize:
use a list of stopwords
generate a dictionary of words, classifying them with a part of speech(s)
run raw phrases through dictionary and stopwords
(optional) rank on how confident you are on a match
if needed, accept phrases which didn't violate known patterns (this would handle many proper nouns)
If you've access to the text these phrases were generated from, it may be easier to just create your own topic tags.
Failing that, I'd probably just remove anything that contained a stop word. See this list, for example:
http://www.ranks.nl/resources/stopwords.html
I wouldn't break out POS tagging or anything stronger for this.
It seems you could create a list that filters out three things:
Prepositions: https://en.wikipedia.org/wiki/List_of_English_prepositions
Conjunctions: https://en.wikipedia.org/wiki/Conjunction_(grammar)
Verb forms of to-be: http://www.englishplus.com/grammar/00000040.htm
If you filter on these things you'd get pretty far. Are you more concerned with false negatives or positives? If false negatives aren't a huge problem, this is how I would approach it.
Related
I wonder why words like "therefore" or "however" or "etc" are not included for instance.
Can you suggest a strategy to make this list automatically more general?
One obvious solution is to include every word that arises in all documents. However, maybe in some documents "therefore" cannot arise.
Just to be clear I am not talking about augment the list by including words of specific data sets. For instance, in some data sets, it may be interested to filter some proper names. I am not talking about this. I am talking about the inclusion of general words that can appear in any english text.
The problem with tinkering with a stop word list is that there is no good way to gather all texts about a certain topic and then automatically discard everything that occurs too frequent. It may lead to inadvertently removing just the topic that you were looking for – because in a limited corpus it occurs relatively frequent. Also, any list of stop words may already contain just the phrase you are looking for. As an example, automatically creating a list of 1980s music groups would almost certainly discard the group The The.
The NLTK documentation refers to where their stopword list came from as:
Stopwords Corpus, Porter et al.
However, that reference is not very well written. It seems to state this was part of the 1980's Porter Stemmer (PDF: http://stp.lingfil.uu.se/~marie/undervisning/textanalys16/porter.pdf; thanks go to alexis for the link), but this actually does not mention stop words. Another source states that:
The Porter et al refers to the original Porter stemmer paper I believe - Porter, M.F. (1980): An algorithm for suffix stripping. Program 14 (3): 130—37. - although the et al is confusing to me. I remember being told the stopwords for English that the stemmer used came from a different source, likely this one - "Information retrieval" by C. J. Van Rijsbergen (Butterworths, London, 1979).
https://groups.google.com/forum/m/#!topic/nltk-users/c8GHEA8mq8A
The full text of Van Rijsbergen can be found online (PDF: http://openlib.org/home/krichel/courses/lis618/readings/rijsbergen79_infor_retriev.pdf); it mentions several approaches to preprocessing text and so may well be worth a full read. From a quick glance-through it seems the preferred algorithm to generate a stop word list goes all the way back to research such as
LUHN, H.P., 'A statistical approach to mechanised encoding and searching of library information', IBM Journal of Research and Development, 1, 309-317 (1957).
dating back to the very early stages of automated text processing.
The title of your question asks about the criteria that were used to compile the stopwords list. A look at stopwords.readme() will point you to the Snowball source code, and based on what I read there I believe the list was basically hand-compiled, and its primary goal was the exclusion of irregular word forms in order to provide better input to the stemmer. So if some uninteresting words were excluded, it was not a big problem for the system.
As for how you could build a better list, that's a pretty big question. You could try computing a TF-IDF score for each word in your corpus. Words that never get a high tf-idf score (for any document) are uninteresting, and can go in the stopword list.
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 have some texts in different languages and, potentially, with some typo or other mistake, and I want to retrieve their own vocabulary. I'm not experienced with NLP in general, so maybe I use some word improperly.
With vocabulary I mean a collection of words of a single language in which every word is unique and the inflections for gender, number, or tense are not considered (e.g. think, thinks and thought are are all consider think).
This is the master problem, so let's reduce it to the vocabulary retrieving of one language, English for example, and without mistakes.
I think there are (at least) three different approaches and maybe the solution consists of a combination of them:
search in a database of words stored in relation with each others. So, I could search for thought (considering the verb) and read the associated information that thought is an inflection of think
compute the "base form" (a word without inflections) of a word by processing the inflected form. Maybe it can be done with stemming?
use a service by any API. Yes, I accept also this approach, but I'd prefer to do it locally
For a first approximation, it's not necessary that the algorithm distinguishes between nouns and verbs. For instance, if in the text there were the word thought like both noun and verb, it could be considered already present in the vocabulary at the second match.
We have reduced the problem to retrieve a vocabulary of an English text without mistakes, and without consider the tag of the words.
Any ideas about how to do that? Or just some tips?
Of course, if you have suggestions about this problem also with the others constraints (mistakes and multi-language, not only Indo-European languages), they would be much appreciated.
You need lemmatization - it's similar to your 2nd item, but not exactly (difference).
Try nltk lemmatizer for Python or Standford NLP/Clear NLP for Java. Actually nltk uses WordNet, so it is really combination of 1st and 2nd approaches.
In order to cope with mistakes use spelling correction before lemmatization. Take a look at related questions or Google for appropriate libs.
About part of speech tag - unfortunately, nltk doesn't consider POS tag (and context in general), so you should provide it with the tag that can be found by nltk pos tagging. Again, it is already discussed here (and related/linked questions). I'm not sure about Stanford NLP here - I guess it should consider context, but I was sure that NLTK does so. As I can see from this code snippet, Stanford doesn't use POS tags, while Clear NLP does.
About other languages - google for lemmatization models, since algorithm for most languages (at least from the same family) is almost the same, differences are in training data. Take a look here for example of German; it is a wrapper for several lemmatizers, as I can see.
However, you always can use stemmer at cost of precision, and stemmer is more easily available for different languages.
Topic Word has become an integral part of the rising debate in the present world. Some people perceive that Topic Word (Synonyms) beneficial, while opponents reject this notion by saying that it leads to numerous problems. From my point of view, Topic Word (Synonyms) has more positive impacts than negative around the globe. This essay will further elaborate on both positive and negative effects of this trend and thus will lead to a plausible conclusion.
On the one hand, there is a myriad of arguments in favour of my belief. The topic has a plethora of merits. The most prominent one is that the Topic Word (Synonyms). According to the research conducted by Western Sydney University, more than 70 percentages of the users were in favour of the benefits provided by the Topic Word (Synonyms). Secondly, Advantage of Essay topic. Thus, it can say that Topic Word (Synonyms) plays a vital role in our lives.
On the flip side, critics may point out that one of the most significant disadvantages of the Topic Word (Synonyms) is that due to Demerits relates to the topic. For instance, a survey conducted in the United States reveals that demerit. Consequently, this example explicit shows that it has various negative impacts on our existence.
As a result, after inspection upon further paragraphs, I profoundly believe that its benefits hold more water instead of drawbacks. Topic Word (Synonyms) has become a crucial part of our life. Therefore, efficient use of Topic Word (Synonyms) method should promote; however, excessive and misuse should condemn.
What are the recommended methods for extracting locations from free text?
What I can think of is to use regex rules like "words ... in location". But are there better approaches than this?
Also I can think of having a lookup hash table table with names for countries and cities and then compare every extracted token from the text to that of the hash table.
Does anybody know of better approaches?
Edit: I'm trying to extract locations from tweets text. So the issue of high number of tweets might also affect my choice for a method.
All rule-based approaches will fail (if your text is really "free"). That includes regex, context-free grammars, any kind of lookup... Believe me, I've been there before :-)
This problem is called Named Entity Recognition. Location is one of the 3 most studied classes (with Person and Organization). Stanford NLP has an open source Java implementation that is extremely powerful: http://nlp.stanford.edu/software/CRF-NER.shtml
You can easily find implementations in other programming languages.
Put all of your valid locations into a sorted list. If you are planning on comparing case-insensitive, make sure the case of your list already is normalized.
Then all you have to do is loop over individual "words" in your input text and at the start of each new word, start a new binary search in your location list. As soon as you find a no-match, you can skip the entire word and proceed with the next.
Possible problem: multi-word locations such as "New York", "3rd Street", "People's Republic of China". Perhaps all it takes, though, is to save the position of the first new word, if you find your bsearch leads you to a (possible!) multi-word result. Then, if the full comparison fails -- possibly several words later -- all you have to do is revert to this 'next' word, in relation to the previous one where you started.
As to what a "word" is: while you are preparing your location list, make a list of all characters that may appear inside locations. Only phrases that contain characters from this list can be considered a valid 'word'.
How fast are the tweets coming in? As in is it the full twitter fire hose or some filtering queries?
A bit more sophisticated approach, that is similar to what you described is using an NLP tool that is integrated to a gazetteer.
Very few NLP tools will keep up to twitter rates, and very few do very well with twitter because of all of the leet speak. The NLP can be tuned for precision or recall depending on your needs, to limit down performing lockups in the gazetteer.
I recommend looking at Rosoka(also Rosoka Cloud through Amazon AWS) and GeoGravy
Are there any recourses on determining the countability of nouns? Either some way to work it out or a dictionary that records whether a noun is likely to countable or not countable?
I'm not interested in whether the noun can be countable but more is it likely to be countable. for instance rice can go to rices which means it can be countable but in most cases it wont be.
This is a tough one. Many English words can be both (beer, time, glass, language, etc etc) depending on the context/meaning.
Figuring out (un)countability from the word alone or from a regular dictionary is impossible or impractical.
You can try to figure it out from a large text corpus by seeing how the word is used:
if there's a plural form or not
if there's an indefinite article before it or none
if it's used with many/few, much/little, a piece of(?), etc
But many words can function as both nouns and adjectives and that complicates matters. For example in an air pump, air functions as an adjective and an refers to pump, not to air.
Likewise, many words can function as both nouns and verbs and have identical forms. For example, in she pressures him, pressures isn't a plural of pressure.
Also, some uncountable nouns can have an indefinite article before them when they are made more specific, e.g. knowledge vs a good practical knowledge.
You can gather statistics from an analyzed corpus and based on it judge whether or not a word is more likely to be countable or uncountable.
There are several existing English lexica that contain information about count/mass/etc. distinctions, none of which quite agree with each other because they focus on slightly different distinctions and it's a complicated task. Two are ComLex and CUVPlus (which I can't find a download link for at the moment, although you can find it mentioned in many places).
Check out the work by Timothy Baldwin and Francis Bond in 2003 on learning noun countability from corpora. If you have many occurrences of an unfamiliar noun in a corpus, you can do fairly well at the task of figuring out whether this noun can possibly be a count noun, can possibly be a mass noun, etc. however individual instances are still be quite difficult to classify. If you have the sentence "the wug was white" and according to your lexicon "wug" can be either count or mass, there's not enough information in the immediate context to help you classify it.
I'm not sure if there is an 'official' dictionary saying if a noun is likely to be countable or not, but I can come up with two ways you could go about this:
Either assuming that a noun is likely to be uncountable if somebody put it in a 'list of mass nouns' or 'list of uncountable nouns' (you find quite a lot if you google for those phrases, for example this).
Or make a little corpus study and see how often the word is used in which way: searching "rice" in the Corpus of contemporary american English gives us 22265 hits, while the word "rices" is only found 69 times.
It depends on the context and whether the noun may have plural on its own. Different senses of the same word may differ, e.g.:
expectation: the feeling vs. what is being expected
salt: table salt vs. a type of a chemical element
Our API, GlobalNLP, returns the countability of nouns (among other things) in a particular context in this method: https://nlp.linguasys.com/docs/services/53fccbb15cfea30d9c48f8d6/operations/542a6da01c78d80a3cd6692a