Natural Language Processing: Computer programming techniques designed to aid in processing human language.

learn more… | top users | synonyms

1
vote
1answer
53 views

Two sentences with the same meaning

I am looking for a statistical or linguistic method that could give the degree of similarity between the meaning of two sentences. I have found in literature many distance measures (euclidean ...
1
vote
1answer
28 views

Where to study probability and natural language processing from?

I am a programmer and I am interested in Natural Language Processing. I studied it a bit in college, but it was years ago and anyway it wasn't enough for a good knowledge of the field. I'm ...
-1
votes
0answers
29 views

Question about Good Turing Discounting [migrated]

I've got a question about Good Turing discounting. I understand the how and the why, but I'm having trouble wrapping my head around it. Say we're discounting the probability of each n-gram that ...
2
votes
2answers
130 views

How to generate grammatically correct sentences?

I'd like to give something like this: # John # eat + past # apple and get back the grammatically correct sentence: John ate an apple. Which software can I use for such generation?
0
votes
0answers
31 views

Node level with Stanford dependency parser

I am trying to find a way to select the node(word) level using Stanford dependency parser. But, i haven't found any method that help to get the node level. I will be very grateful for your help
1
vote
1answer
50 views

annotation tool to work with XML Schema

Is there an annotation tool which can create annotation tasks automatically using an XML schema? The desirable annotation markup may be specified with an XML schema file. I'd like to be able to ...
1
vote
1answer
138 views

Filling in incomplete sentences using NLP and Python

I am trying to leverage NLTK and Python to perform some sentence completion. The sentences I'm working with are incomplete and pretty much just read as garbage. An example sentence would be something ...
4
votes
1answer
66 views

Which part of speech are 's' and 'r' in Wordnet?

From taking the synset of the word 'fantastic', I got a list of senses below: [Synset('antic.s.01'), Synset('fantastic.s.02'), Synset('fantastic.s.03'), Synset('fantastic.s.04'), ...
2
votes
1answer
101 views

Help understanding “degree of overall vocabulary divergence”

There was an article published with a diagram showing Lexical Difference: http://elms.wordpress.com/2008/03/04/lexical-distance-among-languages-of-europe/. It cites a Russian source "K. Tyshchenko ...
1
vote
1answer
51 views

Is perplexity in SRILM normalized for sentence length?

If I generate a language model with SRILM's ngram-count and then use ngram -unk -ppl text -lm model to get log probabilities and perplexity values, are the perplexities normalized for sentence length? ...
0
votes
0answers
42 views

Is there a corpus of English adjective, adverb, etc metadata?

For example. In the sentence fragment "red leather stool", red is a color, leather is a covering of the stool, and stool is a chair. Is there any database, corpus or repository, that lists the ...
3
votes
0answers
65 views

Where can I find Japanese-English (manually) word-aligned corpora?

I'm looking for as many very reliable Japanese-English corpora as possible so I'd like to ask: Are there any other manually aligned corpora besides KFFT's and Utiyama's? What are the most accurate ...
2
votes
1answer
112 views

List of words in Hebrew

Where can I found a list of all the words in Hebrew including plurals, inflections, etc.? I have only found some lists that are based on wikipedia corpus or subtitles curpus, which include many errors ...
0
votes
0answers
39 views

Determining interests from Twitter text

I am not sure if this is the right place to post or if I should be posting CompSci so please feel free to redirect me to the most appropriate StackExchange. I would like to determine interests or ...
2
votes
0answers
38 views

Semi-automatic annotation tool like '@nnotate'

Is there an annotation tool for linguistic structure that compares to @nnotate? One of the major features of annotate is the annotation is semi-automatic, i.e., it uses a language model to make ...
4
votes
2answers
196 views

Expressing Context Free Grammar from academic article with Python's NLTK

Please forgive the potentially noob question, but I'm trying to get started with semantic text analysis, particularly in the legal space. I found a very good paper which describes a context free ...
0
votes
0answers
169 views

Extracting subjective phrases from sentences

I have a set of sentences from which I want to extract all the subjective phrases. For eg., from I am pleased to learn that the president has been reelected., I want to extract am pleased. What is ...
1
vote
2answers
141 views

Studying Linguistics for a Programmer

It isn't definitely a "linguistic" question, but I hope there're some people who solved the same problems like me. Since of my childhood I was very curious in languages and linguistics, but I hadn't ...
1
vote
0answers
49 views

Algorithm for determining the subject of a NL sentence / question [duplicate]

I'm trying to write code that takes in a natural language sentence and determines what that sentence is about. Not from a list of possible subjects, but just from the input text, the NL sentence. ...
1
vote
3answers
367 views

How would I parse the sentence, “I am not the alien here.”?

I am trying to construct a first-order logic representation of the following sentence. My general approach for constructing the representation is to parse the sentence into a phrase structure tree ...
6
votes
2answers
392 views

Is there a favoured data structure for storing ambiguous parse trees in Natural Language Processing?

I know a bit about parsing computer languages. Generally they try to resolve all ambiguities when parsing or abort the parse and throw an error. This means you either got nothing because there was an ...
2
votes
1answer
280 views

Word Sense Disambiguation for common groups of words

Let's say the dictionary has two definitions for live: Live: I live by the sea. Live: The match was shown live on the sports channel. and also contains the following definition: ...
1
vote
1answer
107 views

Algorithm for converting an English sentence or phrase into a function call [closed]

Let's say I have a command line app that has the following functions: function createABox() { console.log("hey"); }; function deleteABox() { console.log("wutsup"); }; The command line app can take ...
1
vote
0answers
35 views

Automatic evaluation of written English - e.g. item descriptions

I'm looking for S/W that evaluates the quality of short English texts, e.g. in terms of grammar, syntax, maybe style or ethnicity. My interest is, for example, in descriptions of items offered for ...
-1
votes
1answer
101 views

What factors should I consider when setting a Linguistic Corpus price?

What are the factors that must be considered when setting a linguistic corpus price? Is there any standard model or something else I should follow?
3
votes
2answers
86 views

What is the definition of “oracle information”?

Can anybody provide me with a definition of "oracle information" as it's used in NLP and machine learning? I've come across the term in in sentiment analysis, wsd, mt, and in a number of other areas ...
4
votes
3answers
182 views

Which language has verb/noun compounding features?

Often languages have compounding phrases with the same Part Of Speech (POS) and it becomes a morphological analysis problem in Natural Language Processing (NLP). The most notorious being infinite ...
3
votes
2answers
113 views

sentiment analytics

I've recently been tasked with programming a web crawler that searches through news articles for certain keywords--company names, for example--and then tries to determine if the article has a positive ...
0
votes
0answers
71 views

links in Explicit Semantic Analysis (ESA) of Wikipedia articles

I understand the need to take the links to other articles into account while generating the interpretation vector for an article (for Explicit Semantic Analysis (ESA)). I don't know how exactly it is ...
0
votes
0answers
42 views

What is the role of syntax in semantic role labling?

For semantic role labeling process, is it enough to just using some corpora like FrameNet and PropBank, or we must have some syntactic annotated corpora using dependency grammar?
2
votes
2answers
190 views

Checking grammar of non-English text (NLP)

I am writing a program that will take input from users in non-English languages (German, French, Spanish, Italian, and Portuguese) and will need to determine whether the input is grammatically ...
10
votes
3answers
295 views

Can parsing be classified to some complexity class (e.g. NP-complete)?

In computer science (especially computational complexity theory), problems can be classified to some complexity theory. For example, we say the travelling salesman problem belongs to NP-complete. ...
5
votes
1answer
516 views

Automatically Converting Natural Language to First-Order Logic

I'm trying to find a way to automatically convert arbitrary natural language sentences into first-order logic predicates. Although complex, this seems to be feasible to me, through inverse lambda ...
3
votes
0answers
116 views

Calculating margin of error for precision and recall

I commonly calculate the precision and recall for information pulled from text but I'm not sure how to calculate the margin of error for those precision and recall values. So for example, if I have a ...
2
votes
2answers
247 views

Text parsing: Distinguish between “dictionary words” and names

I have texts in English and German containing "dictionary words" and names. e.g. "... In Florence the painter Leonardo built ..." I have a Java program where need to determine for each word if ...
6
votes
3answers
283 views

Mathematical preparation for postgraduate studies in Linguistics

I posted this question in http://math.stackexchange.com/ and it was suggested to me that it would be a good idea to submit the question here, too, as there might be more specialists on the matter. I ...
8
votes
1answer
146 views

State-of-the-art spelling correction algorithms

According to Wikipedia The most successful algorithm to date is Andrew Golding and Dan Roth's "Winnow-based spelling correction algorithm", published in 1999, which is able to recognize about 96% ...
6
votes
1answer
341 views

Are there sentence boundary disambiguation algorithms which can handle punctuation errors with decent accuracy?

Most algorithms for splitting text into sentences which I've found rely on punctuation being correct. However, in many real world applications, there will be substantial numbers of punctuation errors ...
7
votes
3answers
107 views

Looking for bi-/tri-lingual dictionaries or corpora

I will be attempting to solve the problem of automatic language identification/detection (and later translation), and I'm in a need of free digital dictionaries or corpora. I'm looking for ...
3
votes
2answers
152 views

Defining an idea

I am currently writing my master thesis about extracting "ideas" for innovation from text stored digitally. Thus the project is a combination of "Marketing", "Datamining/statistics" and "Linguistics". ...
2
votes
1answer
154 views

ISO 639 3 (or ISO-639 2) Language Names Translation

A part of ISO 639-3 Language Names follows: fan fan fan I L Fang (Equatorial Guinea) fao fao fao fo I L Faroese fap I L Palor far I L Fataleka ...
4
votes
2answers
119 views

Multilingual POS tagging set

As you know: Almost all languages have the lexical categories noun and verb, but beyond these there are significant variations in different languages. We want tag POS of some text of a lot of ...
3
votes
1answer
114 views

Useful Features of Semantic Graphs

If this question is too general, please let me know, and I will revise it. I am developing a program that measures all sorts of "features" of a sentence, everything from sentence length, to average ...
3
votes
1answer
65 views

How can we perform WSD using semantic relatedness measures?

I am focusing on knowledge based on Word-sense disambiguation (WSD). I have come across algorithms like Lesk, extended Lesk, etc., which perform WSD based on gloss definitions of senses of each word ...
0
votes
0answers
63 views

Which layers of the language is dealing with co-reference resolution and how to solve it computationaly?

Which layers of the language is dealing with co-reference resolution and what are the steps to solve this problem in NLP?
4
votes
2answers
215 views

IDE for context free grammars for natural languages?

Is there any such thing as a Integrated Development Environment for context free grammars (or any variant on a formal, machine parsable grammar) that target natural languages? The ones for BNF ...
4
votes
2answers
273 views

Locating a sentence's topic

I am trying to get the topic of a sentence, i.e what a sentence is talking about (not the grammatical subject which may be different). So far I have got: OpenNLP in Java which is giving me sentence ...
-1
votes
2answers
125 views

concept/name extraction rules

I'm doing an NLP research, trying to extract concepts/names from phrases, I need your help defining all rules for doing so, so i can feed them onto the computer. example rules I observed:if a ...
2
votes
1answer
92 views

How do I get 'hosted' from 'He had a party at his house'?

I'm new to NLP so bear with me if this isn't possible yet. I am interested in taking a sentence like 'He had a party at his house' to 'He hosted a party at his house' or simply the verb 'hosted'. Is ...
2
votes
1answer
235 views

Entity level Sentiment Analysis

I've been working on document level sentiment analysis over the last year. Document level sentiment analysis provides the sentiment of the complete document. For example - The text "Nokia is good but ...