I made a knowledge base using COMET on the Atomic knowledge graph, using this tutorial.
I would like to include this knowledge in a regular pre-trained BERT model from HuggingFace to see how the model with access to this knowledge performs on a different task (sentiment analysis).
I saved the generated tuples from COMET in a pickle file.
Thanks!
I got a big problem. For my bachelor thesis I have to make a machine tranlation model with BERT.
But I am not getting anywhere right now.
Do you know a documentation or something that can help me here?
I have read some papers in that direction but maybe there is a documentation or tutorial that can help me.
For my bachelor thesis I have to translate from a summary of a text into a title.
I hope someone can help me.
BERT is not a machine translation model, BERT is designed to provide a contextual sentence representation that should be useful for various NLP tasks. Although there exist ways how BERT can be incorporated into machine translation (https://openreview.net/forum?id=Hyl7ygStwB), it is not an easy problem and there are doubts if it really pays off.
From your question, it seems that you are not really machine translation, but automatic summarization. Similarly to machine translation, it can be approached using sequence-to-sequence models, but we do not call it translation in NLP.
For sequence-to-sequence modeling, there are different pre-trained models, such as BART or MASS. These should be much more useful than BERT.
Update in September 2022: There are multilingual BERT-like models, the most famous are multilingual BERT and XLM-RoBERTa. When fine-tuned carefully, they can be used as a universal encoder for machine translation and enable so-called zero-shot machine translation. The model is trained to translate from several source languages into English, but in the end, it can translate from all languages covered by the multilingual BERT-like models. The method is called SixT.
I have two datasets. One with details of contracts and other with details of organizations. For eg: One dataset has details- Company name, description, company type. Other datasets has details- Contract name, Contract description, CPV code.
I want an algorithm that can 1) given a company can we find the top 10 contracts that are most closely related or potentially interesting to this company.
2. Or given a contract can we find the companies most likely to bid or win the contract.
This might be a one off, real time algorithm to match one row of the first dataset to a best match cluster in the second dataset.
Is it possible to do this type of row by row cross matching in two different datasets? Is it possible to use text descriptions for this kind of matching?
It would be of great help if someone has code examples. Thank you.
I am also attaching example datasets here.
Company data
Contract data
Your question is effectively "Will someone do ~10K worth of data science for me for free?" What you are looking for is a recommender system and what seems more specifically to be a content based filtering system. In order for these to work, you are going to have to look at your two datasets and develop features that can be used to quantitatively describe the contracts and the clients. If you have information about previous contracts the organizations were interested in you can use a hybrid algorithm that incorporates aspects of collaborative filtering.
R has a package recommenderlab that can help you to work on these types of problems. I haven't used it, but skimming over it, it seems to be solid. If you are wanting something a little more plug and play though with fewer options, I would recommend checking out AzureML. It uses GUI interfaces to help guide users through the data science process including a recommender tutorial. You may also be able to use some of their text classifier tutorial to help engineer features from your fields containing free form text.
Best of luck.
Which Microsoft Cognitive Services (or Azure Machine Learning services?) is best and least work to use to solve the problem of finding similar articles given an article. An article is a string of text. And assuming I do not have user interaction data about the articles.
Are there anything in Microsoft Cognitive Services that can solve this problem out-of-the-box? It seems I cannot use the Recommendations API since I don't have interaction/user data.
Anthony
I am not sure that Text Analytics API may be a good use for this scenario, at least not yet.
There are really two types of similarities:
1. Surface similarity (lexical) – Similarity by presence of words/alphabets
If we are looking for surface similarity, try fuzzy matching/lookup (SQL Server Integration Services – provides a component for this.), or approximate similarity functions (Jaro-Winkler distance, Levenshtein distance) etc. This would be easier as it would not require you to create a custom machine learning model.
2. Semantic similarity – Similarity by meaning of words
If we are looking for Semantic similarity, then you need to go for semantic clustering, word embedding, DSSM (Deep semantic similarity model) etc.
this is harder to do, as it would require you to train your own machine learning model based on an annotated corpus.
Luis Cabrera | Text Analytics Program Manager | Cloud AI Platform, Microsoft
Yes, you can use Text Analytics API.
examples are available here. https://www.microsoft.com/cognitive-services/en-us/text-analytics-api
I would suggest you use the Text Analytics API [1] as #Narasimha suggested. You would put your strings through the Topic detection API, and then come up with a metric (say, Similarity = count(Matching topics) - count(Non Matching topics)) that could order each string against the others for similarity. This would just require one API call and a little JSON parsing.
[1] https://www.microsoft.com/cognitive-services/en-us/text-analytics-api
Sentence similarity or semantic textual similarity is a measure of how similar two pieces of text are, or to what degree they express the same meaning.
This Microsoft's GitHub repo for NLP provide some sample wich could be used from Azure VM and Azure ML : https://github.com/microsoft/nlp/tree/master/examples/sentence_similarity
This folder contains examples and best practices, written in Jupyter notebooks, for building sentence similarity models. The gensen and pretrained embeddings utility scripts are used to speed up the model building process in the notebooks.
The sentence similarity scores can be used in a wide variety of applications, such as search/retrieval, nearest-neighbor or kernel-based classification methods, recommendations, and ranking tasks.
Could you recommend a training path to start and become very good in Information Extraction. I started reading about it to do one of my hobby project and soon realized that I would have to be good at math (Algebra, Stats, Prob). I have read some of the introductory books on different math topics (and its so much fun). Looking for some guidance. Please help.
Update: Just to answer one of the comment. I am more interested in Text Information Extraction.
Just to answer one of the comment. I am more interested in Text Information Extraction.
Depending on the nature of your project, Natural language processing, and Computational linguistics can both come in handy -they provide tools to measure, and extract features from the textual information, and apply training, scoring, or classification.
Good introductory books include OReilly's Programming Collective Intelligence (chapters on "searching, and ranking", Document filtering, and maybe decision trees).
Suggested projects utilizing this knowledge: POS (part-of-speech) tagging, and named entity recognition (ability to recognize names, places, and dates from the plain text). You can use Wikipedia as a training corpus since most of the target information is already extracted in infoboxes -this might provide you with some limited amount of measurement feedback.
The other big hammer in IE is search, a field not to be underestimated. Again, OReilly's book provides some introduction in basic ranking; once you have a large corpus of indexed text, you can do some really IE tasks with it. Check out Peter Norvig: Theorizing from data as a starting point, and a very good motivator -maybe you could reimplement some of their results as a learning exercise.
As a fore-warning, I think I'm obligated to tell you, that information extraction is hard. The first 80% of any given task is usually trivial; however, the difficulty of each additional percentage for IE tasks are usually growing exponentially -in development, and research time. It's also quite underdocumented -most of the high-quality info is currently in obscure white papers (Google Scholar is your friend) -do check them out once you've got your hand burned a couple of times. But most importantly, do not let these obstacles throw you off -there are certainly big opportunities to make progress in this area.
I would recommend the excellent book Introduction to Information Retrieval by Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze. It covers a broad area of issues which form a great and up-to-date (2008) basis for Information Extraction and is available online in full text (under the given link).
I would suggest you take a look at the Natural Language Toolkit (nltk) and the NLTK Book. Both are available for free and are great learning tools.
You don't need to be good at math to do IE just understand how the algorithm works, experiment on the cases for which you need an optimal result performance, and the scale with which you need to achieve target accuracy level and work with that. You are basically working with algorithms and programming and aspects of CS/AI/Machine learning theory not writing a PhD paper on building a new machine-learning algorithm where you have to convince someone by way of mathematical principles why the algorithm works so I totally disagree with that notion. There is a difference between practical and theory - as we all know mathematicians are stuck more on theory then the practicability of algorithms to produce workable business solutions. You would, however, need to do some background reading both books in NLP as well as journal papers to find out what people found from their results. IE is a very context-specific domain so you would need to define first in what context you are trying to extract information - How would you define this information? What is your structured model? Supposing you are extracting from semi and unstructured data sets. You would then also want to weigh out whether you want to approach your IE from a standard human approach which involves things like regular expressions and pattern matching or would you want to do it using statistical machine learning approaches like Markov Chains. You can even look at hybrid approaches.
A standard process model you can follow to do your extraction is to adapt a data/text mining approach:
pre-processing - define and standardize your data to extraction from various or specific sources cleansing your data
segmentation/classification/clustering/association - your black box where most of your extraction work will be done
post-processing - cleansing your data back to where you want to store it or represent it as information
Also, you need to understand the difference between what is data and what is information. As you can reuse your discovered information as sources of data to build more information maps/trees/graphs. It is all very contextualized.
standard steps for: input->process->output
If you are using Java/C++ there are loads of frameworks and libraries available you can work with.
Perl would be an excellent language to do your NLP extraction work with if you want to do a lot of standard text extraction.
You may want to represent your data as XML or even as RDF graphs (Semantic Web) and for your defined contextual model you can build up relationship and association graphs that most likely will change as you make more and more extractions requests. Deploy it as a restful service as you want to treat it as a resource for documents. You can even link it to taxonomized data sets and faceted searching say using Solr.
Good sources to read are:
Handbook of Computational Linguistics and Natural Language Processing
Foundations of Statistical Natural Language Processing
Information Extraction Applications in Prospect
An Introduction to Language Processing with Perl and Prolog
Speech and Language Processing (Jurafsky)
Text Mining Application Programming
The Text Mining Handbook
Taming Text
Algorithms of Intelligent Web
Building Search Applications
IEEE Journal
Make sure you do a thorough evaluation before deploying such applications/algorithms into production as they can recursively increase your data storage requirements. You could use AWS/Hadoop for clustering, Mahout for large scale classification amongst others. Store your datasets in MongoDB or unstructured dumps into jackrabbit, etc. Try experimenting with prototypes first. There are various archives you can use to base your training on say Reuters corpus, tipster, TREC, etc. You can even check out alchemy API, GATE, UIMA, OpenNLP, etc.
Building extractions from standard text is easier than say a web document so representation at pre-processing step becomes even more crucial to define what exactly it is you are trying to extract from a standardized document representation.
Standard measures include precision, recall, f1 measure amongst others.
I disagree with the people who recommend reading Programming Collective Intelligence. If you want to do anything of even moderate complexity, you need to be good at applied math and PCI gives you a false sense of confidence. For example, when it talks of SVM, it just says that libSVM is a good way of implementing them.
Now, libSVM is definitely a good package but who cares about packages. What you need to know is why SVM gives the terrific results that it gives and how it is fundamentally different from Bayesian way of thinking ( and how Vapnik is a legend).
IMHO, there is no one solution to it. You should have a good grip on Linear Algebra and probability and Bayesian theory. Bayes, I should add, is as important for this as oxygen for human beings ( its a little exaggerated but you get what I mean, right ?). Also, get a good grip on Machine Learning. Just using other people's work is perfectly fine but the moment you want to know why something was done the way it was, you will have to know something about ML.
Check these two for that :
http://pindancing.blogspot.com/2010/01/learning-about-machine-learniing.html
http://measuringmeasures.com/blog/2010/1/15/learning-about-statistical-learning.html
http://measuringmeasures.com/blog/2010/3/12/learning-about-machine-learning-2nd-ed.html
Okay, now that's three of them :) / Cool
The Wikipedia Information Extraction article is a quick introduction.
At a more academic level, you might want to skim a paper like Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text.
Take a look here if you need enterprise grade NER service. Developing a NER system (and training sets) is a very time consuming and high skilled task.
This is a little off topic, but you might want to read Programming Collective Intelligence from O'Reilly. It deals indirectly with text information extraction, and it doesn't assume much of a math background.