I have a question about latent semantic indexing,
Suppose I have set of documents collected is in English and Spanish. And I have a translation table is attached for you. The translation table is not subject to the search engine.
The words between the languages are not the same. However, sometimes there are words that are completely identical in the two languages for example: Actor, Hostpital, General and more.
I want to write a pseudo code or give an explanation how you to use LSI to enable a search in both languages when it is assumed that the query is only in one of the languages.
Related
I need some advice on the following problem.
I'm given a set of weighted keywords (by percentage) and need to find a text in a database that best matches those keywords. I will give an example.
I'm presented with these keywords
Sun(90%)
National Park(85% some keywords contain 2 words)
Landmark(60%)
Now lets say my database contains 3 entries of texts e.g
Going-to-the-Sun Road is a scenic mountain road in the Rocky Mountains of the western United States, in Glacier National Park in Montana.
Everybody has a little bit of the sun and moon in them. Everybody has a little bit of man, woman, and animal in them.
A hybrid car is one that uses more than one means of propulsion - that means combining a petrol or diesel engine with an electric motor.
Obviously the first text is the one that best describes the given set of keywords so this is what I want to recommend to the user. Following the second text that somewhat relates with the "sun" keyword and that could be an acceptable choice too.
The 3rd text is totally irrelevant and shall only be recommended as a last resort when everything else fails.
I'm totally new to that kind of stuff so I need some advice as to which technologies/algorithms I should use. Seems like there is some machine learning (nlp) involved or some kind of fuzzy logic. I'm not really sure.
You need to use a combination of query terms boosting and synonyms
Look into Is there a way to do fuzzy string matching for words on string?
I am working on developing a tool for language identification of a given text i.e. given a sample text, identify the language (for e.g. English, Swedish, German, etc.) it is written in.
Now the strategy I have decided to follow (based on a few references I have gathered) are as follows -
a) Create a character n-gram model (The value of n is decided based on certain heuristics and computations)
b) Use a machine learning classifier(such as naive bayes) to predict the language of the given text.
Now, the doubt I have is - Is creating a character N-gram model necessary. As in, what disadvantage does a simple bag of words strategy have i.e. if I use all the words possible in the respective language to create a prediction model, what could be the possible cases where it would fail.
The reason why this doubt arose was the fact that any reference document/research paper I've come across states that language identification is a very difficult task. However, just using this strategy of using the words in the language seems to be a simple task.
EDIT: One reason why N-gram should be preferred is to make the model robust even if there are typos as stated here. Can anyone point out more?
if I use all the words possible in the respective language to create a prediction model, what could be the possible cases where it would fail
Pretty much the same cases were a character n-gram model would fail. The problem is that you're not going to find appropriate statistics for all possible words.(*) Character n-gram statistics are easier to accumulate and more robust, even for text without typos: words in a language tend to follow the same spelling patterns. E.g. had you not found statistics for the Dutch word "uitbuiken" (a pretty rare word), then the occurrence of the n-grams "uit", "bui" and "uik" would still be strong indicators of this being Dutch.
(*) In agglutinative languages such as Turkish, new words can be formed by stringing morphemes together and the number of possible words is immense. Check the first few chapters of Jurafsky and Martin, or any undergraduate linguistics text, for interesting discussions on the possible number of words per language.
Cavnar and Trenkle proposed a very simple yet efficient approach using character n-grams of variable length. Maybe you should try to implement it first and move to a more complex ML approach if C&T approach doesn't meet your requirements.
Basically, the idea is to build a language model using only the X (e.g. X = 300) most frequent n-grams of variable length (e.g. 1 <= N <= 5). Doing so, you are very likely to capture most functional words/morphemes of the considered language... without any prior linguistic knowledge on that language!
Why would you choose character n-grams over a BoW approach? I think the notion of character n-gram is pretty straightforward and apply to every written language. Word, is a much much complex notion which greatly differ from one language to another (consider languages with almost no spacing marks).
Reference: http://odur.let.rug.nl/~vannoord/TextCat/textcat.pdf
The performance really depends on your expected input. If you will be classifying multi-paragraph text all in one language, a functional words list (which your "bag of words" with pruning of hapaxes will quickly approximate) might well serve you perfectly, and could work better than n-grams.
There is significant overlap between individual words -- "of" could be Dutch or English; "and" is very common in English but also means "duck" in the Scandinavian languages, etc. But given enough input data, overlaps for individual stop words will not confuse your algorithm very often.
My anecdotal evidence is from using libtextcat on the Reuters multilingual newswire corpus. Many of the telegrams contain a lot of proper names, loan words etc. which throw off the n-gram classifier a lot of the time; whereas just examining the stop words would (in my humble estimation) produce much more stable results.
On the other hand, if you need to identify short, telegraphic utterances which might not be in your dictionary, a dictionary-based approach is obviously flawed. Note that many North European languages have very productive word formation by free compounding -- you see words like "tandborstställbrist" and "yhdyssanatauti" being coined left and right (and Finnish has agglutination on top -- "yhdyssanataudittomienkinkohan") which simply cannot be expected to be in a dictionary until somebody decides to use them.
I'm making a simple search engine, and as I go through the documents that are going to be indexed, I want to automatically identify the words that should be ignored (such as "and" and "the").
The only simple method I can think of is just ignore words of up to a certain length (if they're not lengthy enough, then they're considered stop words). Any other method would probably have to require data mining (I'm open to suggestions).
I would prefer a method that I can use as i go through the documents, but I'm open to the other suggestions. I just need a simple method.
Short answer is: don't. As in don't bother, but instead strip them from the query and/or weigh them appropriately by TF-IDF.
Quoting the Xapian manual: http://xapian.org/docs/stemming.html
It has been traditional in setting up IR systems to discard the very commonest words of a language - the stopwords - during indexing. A more modern approach is to index everything, which greatly assists searching for phrases for example. Stopwords can then still be eliminated from the query as an optional style of retrieval. In either case, a list of stopwords for a language is useful.
Getting a list of stopwords can be done by sorting a vocabulary of a text corpus for a language by frequency, and going down the list picking off words to be discarded.
I am searching for information on algorithms to process text sentences or to follow a structure when creating sentences that are valid in a normal human language such as English. I would like to know if there are projects working in this field that I can go learn from or start using.
For example, if I gave a program a noun, provided it with a thesaurus (for related words) and part-of-speech (so it understood where each word belonged in a sentence) - could it create a random, valid sentence?
I'm sure there are many sub-sections of this kind of research so any leads into this would be great.
The field you're looking for is called natural language generation, a subfield of natural language processing
http://en.wikipedia.org/wiki/Natural_language_processing
Sentence generation is either really easy or really hard depending on how good you want the sentences to be. Currently, there aren't programs that will be able to generate 100% sensible sentences about given nouns (even with a thesaurus) -- if that is what you mean.
If, on the other hand, you would be satisfied with nonsense that was sometimes ungrammatical, then you could try an n-gram based sentence generator. These just chain together of words that tend to appear in sequence, and 3-4-gram generators look quite okay sometimes (although you'll recognize them as what generates a lot of spam email).
Here's an intro to the basics of n-gram based generation, using NLTK:
http://www.nltk.org/book/ch02.html#generating-random-text-with-bigrams
This is called NLG (Natural Language Generation), although that is mainly the task of generating text that describes a set of data. There is also a lot of research on completely random sentence generation as well.
One starting point is to use Markov chains to generate sentences. How this is done is that you have a transition matrix that says how likely it is to transition between every every part-of-speech. You also have the most likely starting and ending part-of-speech of a sentence. Put this all together and you can generate likely sequences of parts-of-speech.
Now, you are far from done, this will first of all not offer a very good result as you are only considering the probability between adjacent words (also called bi-grams), so what you want to do is to extend this to look for instance at the transition matrix between three parts-of-speech (this makes a 3D matrix and gives you trigrams). You can extend it to 4-grams, 5-grams, etc. depending on the processing power and if your corpus can fill such matrix.
Lastly, you need to patch up things such as object agreement (subject-verb-agreement, adjective-verb-agreement (not in English though), etc.) and tense, so that everything is congruent.
Yes. There is some work dealing with solving problems in NLG with AI techniques. As far as I know, currently, there is no method that you can use for any practical use.
If you have the background, I suggest getting familiar with some work by Alexander Koller from Saarland University. He describes how to code NLG to PDDL. The main article you'll want to read is "Sentence generating as a planning problem".
If you do not have any background in NLP, just search for the online courses or course materials by Michael Collings or Dan Jurafsky.
Writing random sentences is not that hard. Any parser textbook's simple-english-grammar example can be run in reverse to generate grammatically correct nonsense sentences.
Another way is the word-tuple-random-walk, made popular by the old BYTE magazine TRAVESTY, or stuff like
http://www.perlmonks.org/index.pl?node_id=94856
Our application is being translated into a number of languages, and we need to have a combo box that lists the possible languages. We'd like to use the name of the language in that language (e.g. Français for French).
Is there any "proper" order for listing these languages? Do we alphabetize them based on their English names?
Update:
Here is my current list (I want to explore the Unicode Collating Algorithm that Brian Campbell mentioned):
"العربية",
"中文",
"Nederlands",
"English",
"Français",
"Deutsch",
"日本語",
"한국어",
"Polski",
"Русский язык",
"Español",
"ภาษาไทย"
Update 2: Here is the list generated by the ICU Demonstration tool, sorting for an en-US locale.
Deutsch
English
Español
Français
Nederlands
Polski
Русский язык
العربية
ภาษาไทย
한국어
中文
日本語
This is a tough question without a single, easy answer. First of all, by default you should use the user's preferred language, as given to you by the operating system, if that is one of your available languages (for example, in Windows, you would use GetUserPreferredUILanguages, and find the first one on that list that you have a translation for).
If the user still needs to select a language (you would like them to be able to override their default language, or select another language if you don't support their preferred language), then you'll need to worry about how to sort the languages. If you have 5 or 10 languages, the order probably doesn't matter that much; you might go for sorting them in alphabetical order. For a longer list, I'd put your most common languages at the top, and perhaps the users preferred languages at the top as well, and then sort the rest in alphabetical order after that.
Of course, this brings up how to sort alphabetically when languages might be written in different scripts. For instance, how does Ελληνικά (Ellinika, Greek) compare to 日本語 (Nihongo, Japanese)? There are a few possible solutions. You could sort each script together, with, for instance, Roman based scripts coming first, followed by Cyrillic, Greek, Han, Hangul, and so on. Or you could sort non-Roman scripts by their English name, or by a Roman transliteration of their native name. Probably the first or third solution should be preferred; people may not know the English name for their language, but many languages have English transliterations that people may know about. The first solution (each script sorted separately) is how the Mac OS X languages selection works; the second (sorted by their Roman transliteration) appears to be how Wikipedia sorts languages.
I don't believe that there is a standard for this particular usage, though there is the Unicode Collation Algorithm which is probably the most common standard for sorting text in mixed scripts in a relatively language-neutral way.
I would say it depends on the length of your list.
If you have 5 languages (or any number which easily fits into the dropdown without scrolling) then I'd say put your most common language at the top and then alphabetize them... but just alphabetizing them wouldn't make it less user friendly IMHO.
If you have enough the you'd need to scroll I would put your top 3 or 5 (or some appropriate number of) most common languages at the top and bold them in the list then alphabetize the rest of the options.
For a long list I would probably list common languages twice.
That is, "English" would appear at the top of the list and at the point in the alphabetized list where you'd expect.
EDIT: I think you would still want to alphabetize them according so how they're listed... that is "Espanol" would appear in the E's, not in the S's as if it were "Spanish"
Users will be able to pick up on the fact that languages are listed according to their translated name.
EDIT2: Now that you've edited to show the languages you're interested in I can see how a sort routine would be a bit more challenging!
The ISO has codes for languages (here's the Library of Congress description), which are offered in order by the code, by the English name, and by the French name.
It's tricky. I think as a user I would expect any list to be ordered based on how the items are represented in the list. So as much as possible, I would use alphabetical order based on the names you are actually displaying.
Now, you can't always do that, as many will use other alphabets. In those cases there may be a roman-alphabet way of transliterating the name (for example, the Pinyin system for Mandarin Chinese) and it could make sense to alphabetize based on that. However, romanization isn't a simple subject; there are at least a dozen ways for romanizing Arabic, for example.
You could alphabetize them based on their ISO 639 language code.