It's common to add a custom dictionary to a machine translator to ensure that terminology from a specific domain is correctly translated. For example, the term server should be translated differently when the document is about data centers, vs when the document is about restaurants.
With a transformer model, this is not very obvious to do, since words are not aligned 1:1. I've seen a couple of papers on this topic, but I'm not sure which would be the best one to use. What are the best practices for this problem?
I am afraid you cannot easily do that. You cannot easily add new words to the vocabulary because you don't know what embedding it would get during training. You can try to remove some words, or alternatively you can manually change the bias in the final softmax layer to prevent some words from appearing in the translation. Anything else would be pretty difficult to do.
What you want to do is called domain adaptation. To get an idea of how domain adaptation is usually done, you can have a look at a survey paper.
The most commonly used approaches are probably model finetuning or ensembling with a language model. If you want to have parallel data in your domain, you can try to fine-tune your model on that parallel data (with simple SGD, small learning rate).
If you only have monolingual data in the target language, you train a language model on that data. During the decoding, you can mix the probabilities from the domain-specific language and the translation model. Unfortunately, I don't know of any tool that could do this out of the box.
I have a lot of texts (millions), ranging from 100 to 4000 words. The texts are formatted as written work, with punctuation and grammar. Everything is in English.
The problem is simple: How to extract every WikiData entity from a given text?
An entity is defined as every noun, proper or regular. I.e., names of people, organizations, locations and things like chair, potatoes etc.
So far I've tried the following:
Tokenize the text with OpenNLP, and use the pre-trained models to extract people, location, organization and regular nouns.
Apply Porter Stemming where applicable.
Match all extracted nouns with the wmflabs-API to retrieve a potential WikiData ID.
This works, but I feel like I can do better. One obvious improvement would be to cache the relevant pieces of WikiData locally, which I plan on doing. However, before I do that, I want to check if there are other solutions.
Suggestions?
I tagged the question Scala because I'm using Spark for the task.
Some suggestions:
consider Stanford NER in comparison to OpenNLP to see how it compares on your corpus
I wonder at the value of stemming for most entity names
I suspect you might be losing information by dividing the task into discrete stages
although Wikidata is new, the task isn't, so you might look at papers for Freebase|DBpedia|Wikipedia entity recognition|disambiguation
In particular, DBpedia Spotlight is one system designed for exactly this task.
http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/38389.pdf
http://ceur-ws.org/Vol-1057/Nebhi_LD4IE2013.pdf
Looking at all the examples of Operational Transformation Frameworks out there, they all seem to resolve around the transformation of changes to plain text documents. How would an OT framework be used for more complex objects?
I'm wanting to dev a real-time sticky notes style app, where people can co-create sticky notes, change their positon and text value. Would I be right in assuming that the position values wouldn't be transformed? (I mean, how would they, you can't merge them right?). However, I would want to use an OT framework to resolve conflicts with the posit-its value, correct?
I do not see any problem to use Operational Transformation to work with Complex Objects, what you need is to define what operations your OT system support and how concurrency is solved for them
For instance, if you receive two Sticky notes "coordinates move operation" from two different users from same 'client state', you need to make both states to converge, probably cancelling out second operation.
This is exactly the same behaviour with text when two users generate two updates to delete a text range that overlaps completely, (or maybe partially), the second update processed must be transformed against the previous and the resultant operation will only effectively delete a portion of the original one, (or completely cancelled with a 'no-op')
You can take a look on this nice explanation about how Google Wave Operational Transformation works and guess from this point how it should work your own implementation
See the following paper for an approach to using OT with trees if you want to go down that route:
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.100.74
However, in your particular case, I would use a separate plain text OT document for each stickynote and use an existing library, eg: etherPad, to do the heavy lifting. The positions of the notes could then be broadcast on a last-committer-wins basis.
Operation Transformation is a general technique, it works for any data type. The point is you need to define your transformation functions. Also, there are some atomic attributes that you cannot merge automatically like (position and background color) those will be mostly "last-update wins" or the user solves them manually when there is a conflict.
there are some nice libs and frameworks that provide OT for complex data already out there:
ShareJS : library for Node which provides all operations on JSON objects
DerbyJS: framework for NodeJS, it uses ShareJS for OT stuff.
Open Coweb framework : Dojo foundation project for cooperative web applications using OT
I am working with some really large databases of newspaper articles, I have them in a MySQL database, and I can query them all.
I am now searching for ways to help me tag these articles with somewhat descriptive tags.
All these articles is accessible from a URL that looks like this:
http://web.site/CATEGORY/this-is-the-title-slug
So at least I can use the category to figure what type of content that we are working with. However, I also want to tag based on the article-text.
My initial approach was doing this:
Get all articles
Get all words, remove all punctuation, split by space, and count them by occurrence
Analyze them, and filter common non-descriptive words out like "them", "I", "this", "these", "their" etc.
When all the common words was filtered out, the only thing left is words that is tag-worthy.
But this turned out to be a rather manual task, and not a very pretty or helpful approach.
This also suffered from the problem of words or names that are split by space, for example if 1.000 articles contains the name "John Doe", and 1.000 articles contains the name of "John Hanson", I would only get the word "John" out of it, not his first name, and last name.
Automatically tagging articles is really a research problem and you can spend a lot of time re-inventing the wheel when others have already done much of the work. I'd advise using one of the existing natural language processing toolkits like NLTK.
To get started, I would suggest looking at implementing a proper Tokeniser (much better than splitting by whitespace), and then take a look at Chunking and Stemming algorithms.
You might also want to count frequencies for n-grams, i.e. a sequences of words, instead of individual words. This would take care of "words split by a space". Toolkits like NLTK have functions in-built for this.
Finally, as you iteratively improve your algorithm, you might want to train on a random subset of the database and then try how the algorithm tags the remaining set of articles to see how well it works.
You should use a metric such as tf-idf to get the tags out:
Count the frequency of each term per document. This is the term frequency, tf(t, D). The more often a term occurs in the document D, the more important it is for D.
Count, per term, the number of documents the term appears in. This is the document frequency, df(t). The higher df, the less the term discriminates among your documents and the less interesting it is.
Divide tf by the log of df: tfidf(t, D) = tf(t, D) / log(df(D) + 1).
For each document, declare the top k terms by their tf-idf score to be the tags for that document.
Various implementations of tf-idf are available; for Java and .NET, there's Lucene, for Python there's scikits.learn.
If you want to do better than this, use language models. That requires some knowledge of probability theory.
Take a look at Kea. It's an open source tool for extracting keyphrases from text documents.
Your problem has also been discussed many times at http://metaoptimize.com/qa:
http://metaoptimize.com/qa/questions/1527/what-are-some-good-toolkits-to-get-lda-like-tagging-of-my-documents
http://metaoptimize.com/qa/questions/1060/tag-analysis-for-document-recommendation
If I understand your question correctly, you'd like to group the articles into similarity classes. For example, you might assign article 1 to 'Sports', article 2 to 'Politics', and so on. Or if your classes are much finer-grained, the same articles might be assigned to 'Dallas Mavericks' and 'GOP Presidential Race'.
This falls under the general category of 'clustering' algorithms. There are many possible choices of such algorithms, but this is an active area of research (meaning it is not a solved problem, and thus none of the algorithms are likely to perform quite as well as you'd like).
I'd recommend you look at Latent Direchlet Allocation (http://en.wikipedia.org/wiki/Latent_Dirichlet_allocation) or 'LDA'. I don't have personal experience with any of the LDA implementations available, so I can't recommend a specific system (perhaps others more knowledgeable than I might be able to recommend a user-friendly implementation).
You might also consider the agglomerative clustering implementations available in LingPipe (see http://alias-i.com/lingpipe/demos/tutorial/cluster/read-me.html), although I suspect an LDA implementation might prove somewhat more reliable.
A couple questions to consider while you're looking at clustering systems:
Do you want to allow fractional class membership - e.g. consider an article discussing the economic outlook and its potential effect on the presidential race; can that document belong partly to the 'economy' cluster and partly to the 'election' cluster? Some clustering algorithms allow partial class assignment and some do not
Do you want to create a set of classes manually (i.e., list out 'economy', 'sports', ...), or do you prefer to learn the set of classes from the data? Manual class labels may require more supervision (manual intervention), but if you choose to learn from the data, the 'labels' will likely not be meaningful to a human (e.g., class 1, class 2, etc.), and even the contents of the classes may not be terribly informative. That is, the learning algorithm will find similarities and cluster documents it considers similar, but the resulting clusters may not match your idea of what a 'good' class should contain.
Your approach seems sensible and there are two ways you can improve the tagging.
Use a known list of keywords/phrases for your tagging and if the count of the instances of this word/phrase is greater than a threshold (probably based on the length of the article) then include the tag.
Use a part of speech tagging algorithm to help reduce the article into a sensible set of phrases and use a sensible method to extract tags out of this. Once you have the articles reduced using such an algorithm, you would be able to identify some good candidate words/phrases to use in your keyword/phrase list for method 1.
If the content is an image or video, please check out the following blog article:
http://scottge.net/2015/06/30/automatic-image-and-video-tagging/
There are basically two approaches to automatically extract keywords from images and videos.
Multiple Instance Learning (MIL)
Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), and the variants
In the above blog article, I list the latest research papers to illustrate the solutions. Some of them even include demo site and source code.
If the content is a large text document, please check out this blog article:
Best Key Phrase Extraction APIs in the Market
http://scottge.net/2015/06/13/best-key-phrase-extraction-apis-in-the-market/
Thanks, Scott
Assuming you have pre-defined set of tags, you can use the Elasticsearch Percolator API like this answer suggests:
Elasticsearch - use a "tags" index to discover all tags in a given string
Are you talking about the name-entity recognition ? if so, Anupam Jain is right. it;s research problem with using deep learning & CRF. In 2017, the name-entity recognition problem is force on semi-surprise learning technology.
The below link is related ner of paper:
http://ai2-website.s3.amazonaws.com/publications/semi-supervised-sequence.pdf
Also, The below link is key-phase extraction on twitter:
http://jkx.fudan.edu.cn/~qzhang/paper/keyphrase.emnlp2016.pdf
I am looking for tools to aid in the visualization of custom business logic used to perform document generation. The logic is expressed as an object-oriented model consisting of a graph of decision points and rendering actions. The basic building blocks are relatively simple, but the overall decision tree is quite large and complex making it hard to visualize.
We are looking for suggestions on tools and/or graphing libraries that can be used to visually represent the decision tree and rendering actions. The choice of programming language is not critical (Delphi, C#, Java would be great) and we are able to easily extract the logic to XML or other data format as required. The preference is for something that will run under Windows and enable printing or PDF output of portions of the resulting diagram.
Requirements
Decision points can be simple yes/no or multiple outputs e.g. (yes, not, sometimes, always etc).
The decision points are linked to external business logic that exist elsewhere in the runtime environment. We need to label the graph node with the type of decision point (e.g. boolean) and string describing the business rule being used.
Rendering actions are linked to named content objects with optional merge variables and inline rendering logic. At a minimum we need to be able to label nodes with the name of the element and ideally also information about variables used to render the content.
We have considered building something around Visio or WinGraphViz, or perhaps using a third-party graphing/flowchart library. Any ideas or pointers would be greatly appreciated.
After some more digging I found WinGraphViz and DotXML to be the closest match to my requirements. I was previously unaware of the "record" element which allows me to render decisions in the logic flow in a clean and legible manner.
You can consider Morphir with the Elm frontend.
It is a solid tool for business logic modeling, and code generation.
Visualization is coming along as well.