Which Stanford NLP package to use for content categorization - machine-learning

I have about 5000 terms in a table and I want to group them into categories that make sense.
For example some terms are:
Nissan
Ford
Arrested
Jeep
Court
The result should be that Nissan, Ford, Jeep get grouped into one category and that Arrested and Court are in another category. I looked at the Stanford Classifier NLP. Am I right to assume that this is the right one to choose to do this for me?

I would suggest you to use NLTK if there weren't many proper nouns. You can use the semantic similarity from WordNet as features and try to cluster the words. Here's a discussion about how to do that.
To use the Stanford Classifier, you need to know how many buckets (classes) of words you want. Besides I think that is for documents rather than words.

That's an interesting problem that the word2vec model that Google released may help with.
In a nutshell, a word is represented by an N-dimensional vector generated by a model. Google provides a great model that returns a 300-dimensional vector from a model trained on over 100 billion words from their news division.
The interesting thing is that there are semantics encoded in these vectors. Suppose you have the vectors for the words King, Man, and Woman. A simple expression (King - Man) + Woman will yield a vector that is exceedingly close to the vector for Queen.
This is done via a distance calculation (cosine distance is their default, but you can use your own on the vectors) to determine similarity between words.
For your example, the distance between Jeep and Ford would be much smaller than between Jeep and Arrested. Through this you could group terms 'logically'.

Related

Word Embedding Model

I have been searching and attempting to implement a word embedding model to predict similarity between words. I have a dataset made up 3,550 company names, the idea is that the user can provide a new word (which would not be in the vocabulary) and calculate the similarity between the new name and existing ones.
During preprocessing I got rid of stop words and punctuation (hyphens, dots, commas, etc). In addition, I applied stemming and separated prefixes with the hope to get more precision. Then words such as BIOCHEMICAL ended up as BIO CHEMIC which is the word divided in two (prefix and stem word)
The average company name length is made up 3 words with the following frequency:
The tokens that are the result of preprocessing are sent to word2vec:
#window: Maximum distance between the current and predicted word within a sentence
#min_count: Ignores all words with total frequency lower than this.
#workers: Use these many worker threads to train the model
#sg: The training algorithm, either CBOW(0) or skip gram(1). Default is 0s
word2vec_model = Word2Vec(prepWords,size=300, window=2, min_count=1, workers=7, sg=1)
After the model included all the words in the vocab , the average sentence vector is calculated for each company name:
df['avg_vector']=df2.apply(lambda row : avg_sentence_vector(row, model=word2vec_model, num_features=300, index2word_set=set(word2vec_model.wv.index2word)).tolist())
Then, the vector is saved for further lookups:
##Saving name and vector values in file
df.to_csv('name-submission-vectors.csv',encoding='utf-8', index=False)
If a new company name is not included in the vocab after preprocessing (removing stop words and punctuation), then I proceed to create the model again and calculate the average sentence vector and save it again.
I have found this model is not working as expected. As an example, calculating the most similar words pet is getting the following results:
ms=word2vec_model.most_similar('pet')
('fastfood', 0.20879755914211273)
('hammer', 0.20450574159622192)
('allur', 0.20118337869644165)
('wright', 0.20001833140850067)
('daili', 0.1990675926208496)
('mgt', 0.1908089816570282)
('mcintosh', 0.18571510910987854)
('autopart', 0.1729743778705597)
('metamorphosi', 0.16965581476688385)
('doak', 0.16890916228294373)
In the dataset, I have words such as paws or petcare, but other words are creating relationships with pet word.
This is the distribution of the nearer words for pet:
On the other hand, when I used the GoogleNews-vectors-negative300.bin.gz, I could not add new words to the vocab, but the similarity between pet and words around was as expected:
ms=word2vec_model.most_similar('pet')
('pets', 0.771199643611908)
('Pet', 0.723974347114563)
('dog', 0.7164785265922546)
('puppy', 0.6972636580467224)
('cat', 0.6891531348228455)
('cats', 0.6719794869422913)
('pooch', 0.6579219102859497)
('Pets', 0.636363685131073)
('animal', 0.6338439583778381)
('dogs', 0.6224827170372009)
This is the distribution of the nearest words:
I would like to get your advice about the following:
Is this dataset appropriate to proceed with this model?
Is the length of the dataset enough to allow word2vec "learn" the relationships between the words?
What can I do to improve the model to make word2vec create relationships of the same type as GoogleNews where for instance word pet is correctly set among similar words?
Is it feasible to implement another alternative such as fasttext considering the nature of the current dataset?
Do you know any public dataset that can be used along with the current dataset to create those relationships?
Thanks
3500 texts (company names) of just ~3 words each is only around 10k total training words, with a much smaller vocabulary of unique words.
That's very, very small for word2vec & related algorithms, which rely on lots of data, and sufficiently-varied data, to train-up useful vector arrangements.
You may be able to squeeze some meaningful training from limited data by using far more training epochs than the default epochs=5, and far smaller vectors than the default size=100. With those sorts of adjustments, you may start to see more meaningful most_similar() results.
But, it's unclear that word2vec, and specifically word2vec in your averaging-of-a-name's-words comparisons, is matched to your end goals.
Word2vec needs lots of data, doesn't look at subword units, and can't say anything about word-tokens not seen during training. An average-of-many-word-vectors can often work as an easy baseline for comparing multiword texts, but might also dilute some word's influence compared to other methods.
Things to consider might include:
Word2vec-related algorithms like FastText that also learn vectors for subword units, and can thus bootstrap not-so-bad guess vectors for words not seen in training. (But, these are also data hungry, and to use on a small dataset you'd again want to reduce vector size, increase epochs, and additionally shrink the number of buckets used for subword learning.)
More sophisticated comparisons of multi-word texts, like "Word Mover's Distance". (That can be quite expensive on longer texts, but for names/titles of just a few words may be practical.)
Finding more data that's compatible with your aims for a stronger model. A larger database of company names might help. If you just want your analysis to understand English words/roots, more generic training texts might work too.
For many purposes, a mere lexicographic comparison - edit distances, count of shared character-n-grams – may be helpful too, though it won't detect all synonyms/semantically-similar words.
Word2vec does not generalize to unseen words.
It does not even work well for wards that are seen but rare. It really depends on having many many examples of word usage. Furthermore a you need enough context left and right, but you only use company names - these are too short. That is likely why your embeddings perform so poorly: too little data and too short texts.
Hence, it is the wrong approach for you. Retraining the model with the new company name is not enough - you still only have one data point. You may as well leave out unseen words, word2vec cannot work better than that even if you retrain.
If you only want to compute similarity between words, probably you don't need to insert new words in your vocabulary.
By eye, I think you can also use FastText without the need to stem the words. It also computes vectors for unknown words.
From FastText FAQ:
One of the key features of fastText word representation is its ability
to produce vectors for any words, even made-up ones. Indeed, fastText
word vectors are built from vectors of substrings of characters
contained in it. This allows to build vectors even for misspelled
words or concatenation of words.
FastText seems to be useful for your purpose.
For your task, you can follow FastText supervised tutorial.
If your corpus proves to be too small, you can build your model starting from availaible pretrained vectors (pretrainedVectors parameter).

Recent methods for finding semantic similarity between two short sentences or articles (on a concept level)

I'm working on finding similarities between short sentences and articles. I used many existing methods such as tf-idf, word2vec etc but the results are just okay. The most relevant measure which I found was word moving distance, however, its results are not that better than the other measures. I know it's a challenging problem, however, I am wondering if there are any new methods to find an approximate similarity more on a higher or concept level than just matching words. Especially, any alternative new methods like word moving distance which looks at slightly higher semantic of a sentence or article?
This is the most recent basing on a paper published 4 months ago.
Step 1:
Load the suitable model using gensim and calculate the word vectors for words in the sentence and store them as a word list
Step 2 : Computing the sentence vector
The calculation of semantic similarity between sentences was difficult before but recently a paper named "A SIMPLE BUT TOUGH-TO-BEAT BASELINE FOR SENTENCE EMBEDDINGS" was proposed which suggests a simple approach by computing the weighted average of word vectors in the sentence and then remove the projections of the average vectors on their first principal component.Here the weight of a word w is a/(a + p(w)) with a being a parameter and p(w) the (estimated) word frequency called smooth inverse frequency.this method performing significantly better.
A simple code to calculate the sentence vector using SIF(smooth inverse frequency) the method proposed in the paper has been given here
Step 3: using sklearn cosine_similarity load two vectors for the sentences and compute the similarity.
This is the most simple and efficient method to compute the semantic similarity of sentences.
Obviously, this is a huge and busy research area, but I'd say there are two broad types of approaches you could look into:
First, there are some methods that learn sentence embeddings in an unsupervised manner, such as Le and Mikolov's (2014) Paragraph Vectors, which are implemented in gensim, or Kiros et al.'s (2015) SkipThought vectors, with an implementation on Github.
Then there also exist supervised methods that learn sentence embeddings from labelled data. The most recent one is Conneau et al.'s (2017), which trains sentence embeddings on the Stanford Natural Language Inference dataset, and shows these embeddings can be used successfully across a range of NLP tasks. The code is available on Github.
You might also find some inspiration in a blog post I wrote earlier this year on the topic of embeddings.
To be honest the best thing I know to use for this at the moment is AMR:
About AMR here: https://amr.isi.edu/
Documentation here: https://github.com/amrisi/amr-guidelines/blob/master/amr.md
You can use a system like JAMR (see here: https://github.com/jflanigan/jamr) to generate AMRs for your sentence and then you can use Smatch (see here: https://amr.isi.edu/eval/smatch/tutorial.html) to compare the similarity of the two generated AMRs.
What you are trying to do is very difficult and is an active ongoing area of research.
You can use semantic similarity with WordNet for each pair of nouns.
To have a quick look you can enter bird-noun-1 and chair-noun-1 and select wordnet at http://labs.fc.ul.pt/dishin/ it gives you:
Resnik 0.315625756544
Lin 0.0574161071905
Jiang&Conrath 0.0964964414156
The Python code is at: https://github.com/lasigeBioTM/DiShIn

LSA - Feature selection

I have this SVD decomposition of the document
I've read this page, but I don't understand how can I compute the best feature for document separation.
I know that:
S x Vt gives me relation between documents and features
U x S gives me relation between terms and features
But what is the key for the best feature selection?
SVD is concerned only with inputs, and not with their labels. In other words, it can be seen as an unsupervised technique. As such, it cannot tell you what features are good for separation, without making any further assumptions.
What it does tell you, is what 'basis vectors' are more important then others, in terms of reconstructing the original data using only a subset of the basis vectors.
Nevertheless, you can think about LSA in the following manner (this is only interpretation, the math is what important): A document is generated by a mixture of topics. Each topic is represented by a vector of length n, which tells you how likely is each word in this topic. For example, if the topic is sports, then words like football or game are more likely than bestseller or movie. These topic-vectors are the columns of U. In order to generate a document (a column of A), you take a linear combination of topics. The coefficients of the linear combination are the columns of Vt - each column tells you what proportion of topics to take in order to generate a document. In addition, each topic has an overall 'gain' factor, which tells you how much this topic is important in your set of documents (maybe you have just one document about sports out of 1000 total documents). These are the singular values == the diagonal of S. If you throw away the smaller ones, you can represent your original matrix A with less topics, and small amount of information lost. Of course, 'small' is a matter of application.
One drawback of LSA is that it is not entirely clear how to interpret the numbers - they are not probabilities, for example. It makes sense to have "0.5" units of sports in a document, but what does it mean to have "-1" units?

Using C4.5 classifier with multiple outcomes

I'm looking at C4.5 classifier for a machine learning task. I have a large dataset containing city names, and need to differentiate between e.g. London Ontario, London England or even London in Burgundy in France, but looking at features from the surrounding text: E.g. Zip codes, state names, even when "Canada" or "England" are not mentioned. I also have access to meta data such as dialing codes which can help determine which country it is.
Subsequently once trained I want to run the classifier on the large dataset.
In all the examples I have found here there are only 2 states for the result (in this golf example play or don't play).
Can the c4.5 classifier handle London (Canada), London (England), London (France) as result classes or do I need to have different classifiers for London (Canada) True/False etc?
I see two options in your case.
The first approach is a straightforward extension to c4.5. In each leaf node, you keep all the labels instead of just the majority label. For example, as shown in the figure below, red labels actually present in three different leafs. When you have a query at the data point pointed by the arrow, the outputs are 3 labels (green, red and blue) together with their corresponding conditional probability p(c|v) (given feature x1 and x2, what is the probability of data x belongs to class c).
The 2nd approach is to generate multiple decision trees hence a random forest. The randomness can be injected by randomly sampling subset of training data made available to each individual tree. At classification time, you can aggregate the vote from all decision trees to get multi-class classification results.
The figures are borrowed from this excellent tutorial on multi-class classification by Andrew Zisserma.

Feature extraction from a single word

Usually one wants to get a feature from a text by using the bag of words approach, counting the words and calculate different measures, for example tf-idf values, like this: How to include words as numerical feature in classification
But my problem is different, I want to extract a feature vector from a single word. I want to know for example that potatoes and french fries are close to each other in the vector space, since they are both made of potatoes. I want to know that milk and cream also are close, hot and warm, stone and hard and so on.
What is this problem called? Can I learn the similarities and features of words by just looking at a large number documents?
I will not make the implementation in English, so I can't use databases.
hmm,feature extraction (e.g. tf-idf) on text data are based on statistics. On the other hand, you are looking for sense (semantics). Therefore no such a method like tf-idef will work for you.
In NLP exists 3 basic levels:
morphological analyses
syntactic analyses
semantic analyses
(higher number represents bigger problems :)). Morphology is known for majority languages. Syntactic analyses is a bigger problem (it deals with things like what is verb, noun in some sentence,...). Semantic analyses has the most challenges, since it deals with meaning which is quite difficult to represent in machines, have many exceptions and are language-specific.
As far as I understand you want to know some relationships between words, this can be done via so-called dependency tree banks, (or just treebank): http://en.wikipedia.org/wiki/Treebank . It is a database/graph of sentences where a word can be considered as a node and relationship as arc. There is good treebank for czech language and for english there will be also some, but for many 'less-covered' languages it can be a problem to find one ...
user1506145,
Here is a simple idea that I have used in the past. Collect a large number of short documents like Wikipedia articles. Do a word count on each document. For the ith document and the jth word let
I = the number of documents,
J = the number of words,
x_ij = the number of times the jth word appears in the ith document, and
y_ij = ln( 1+ x_ij).
Let [U, D, V] = svd(Y) be the singular value decomposition of Y. So Y = U*D*transpose(V)), U is IxI, D is diagonal IxJ, and V is JxJ.
You can use (V_1j, V_2j, V_3j, V_4j) as a feature vector in R^4 for the jth word.
I am surprised the previous answers haven't mentioned word embedding. Word embedding algorithm can produce word vectors for each word a given dataset. These algorithms can nfer word vectors from the context. For instance, by looking at the context of the following sentences we can say that "clever" and "smart" is somehow related. Because the context is almost the same.
He is a clever guy
He is a smart guy
A co-occurrence matrix can be constructed to do this. However, it is too inefficient. A famous technique designed for this purpose is called Word2Vec. It can be studied from the following papers.
https://arxiv.org/pdf/1411.2738.pdf
https://arxiv.org/pdf/1402.3722.pdf
I have been using it for Swedish. It is quite effective in detecting similar words and completely unsupervised.
A package could be find in gensim and tensorflow.

Resources