Natural language processing (NLP)

learn more… | top users | synonyms (1)

1
vote
1answer
20 views

Question about bigram model

I am trying to build a bigram letter model. I obtain a sequence of words in a form of ['hello','I','am','Johnny']. Firstly, I lower all the words to obtain : ['hello','i','am','johnny']. I am ...
1
vote
1answer
20 views

NLP Classification: rule-based approach providing high precision but low recall

In NLP, rule-based/linguistic approaches are usually said to provide relatively high precision but low recall compared to for example machine learning approaches. I think this is often true for almost ...
0
votes
0answers
33 views

How can feature structures be applied to text summarization?

I'm looking for innovative ways to create text summaries and I was wondering whether feature structures can be used for such a task. Is it possible to create subsume and unification methods that ...
1
vote
0answers
82 views

Is English Recursively enumerable? [closed]

The title says it all. I've tried digging up debate on this issue to see a proof one way or the other but it doesn't look like anyone is able to say whether or not it is. Clearly there are recursive ...
0
votes
1answer
34 views

How to extract best illustrative sentences from documents for a given word? [closed]

I want to extract "best" sentences from the given (html) documents. Let me illustrate this with an example. I have a word "determine". Now I have hundreds of html files having paragraphs and sentences ...
1
vote
1answer
41 views

What's this type of semantic analysis called in NLP?

I'm speculating that this is very much known in NLP, but as I've not studied NLP, I don't know what concepts are related to this: Basically I have entities that are connected by some strings. I ...
0
votes
1answer
20 views

In NLP, does the lexer have to tag the tokens before the parser?

In NLP, does the lexer have to tag the tokens before the parser? I.e. does the lexer have to classify the tokens to morphological categories before the parser? I'm thinking yes, but is this also the ...
0
votes
1answer
40 views

Where can I find a reasonable NLP CFG or CSG for English?

I'm looking to do natural language parsing and looking for how the CFG (or CSG) should be defined for English. Surely one'd expect to find one from the internet already, but do you know where? It ...
0
votes
0answers
24 views

Common models for inferring semantics (truth/factuality of statements)?

What are common models for creating rules for inferring meanings (e.g. truth values) of natural language statements such as if one wanted to infer the truth value of the input statement John ...
-1
votes
1answer
20 views

Context-free grammar for “member of”/set membership?

I'm wondering whether context-free grammars (or what else) can be used to implement "member of" structures, which are structures for describing that something is a member of something. E.g. I want to ...
0
votes
1answer
24 views

How to detect plurals in English sentences?

I'm wondering how to detect English plurals in natural language sentences. Such as: fish computers houses ... Using Earley parsing I'm able to get to the s or no-s, but I have difficulties in ...
1
vote
0answers
32 views

Parsing based on logical connectives and quantifiers?

What techniques exist for parsing sentences based on logical connectives and quantifiers? That is, for parsing sentences that are structured "around" logical connectives and quantifiers. E.g. [A] ...
1
vote
0answers
25 views

Algorithm to change article reading level

I was wondering, are there any famous algorithms in NLP or NLG that can take some text (say a news article online) and transform it to a lower reading level?
1
vote
0answers
28 views

Language grammar correction with supervised learning

I want to work on automatic grammar correction using machine learning (possibly using recurrent or deep neural networks). The algorithm will be supplied with both corrected and initial documents for ...
1
vote
1answer
21 views

NLP: Automatically categorize words semantically into non-predefined classes

I am looking for a method to categorize a given word into semantically into classes. A simple example would be: chair -> furniture The most reasonable way to ...
8
votes
0answers
69 views

What are some efficient ways to find the differences between two large corpuses of text that have similar, but differently ordered content?

I have two large files containing paragraphs of English text: The first text is about 200 pages long and has about 10 paragraphs per page (each paragraph is 5 sentences long). The second text ...
2
votes
1answer
55 views

Scientific soundness of computer science papers [closed]

First of all, this question relates to an issue that affects several areas of science, but since StackExchange doesn't have a meta science section I'll make it specific to computer science, which is ...
1
vote
2answers
57 views

Computing probability of sentence using N-grams

I have implemented N-grams by constructing a tree (or a trie, technically) that stores frequencies of each N-gram. Each path in the tree represents an N-gram and its frequency: the path consists of N ...
2
votes
0answers
17 views

Standard training and test corpuses for POS tagging

I'm wondering if there is a standard corpus that people use to evaluate their part-of-speech taggers. I am implementing my own tagger, and would like a meaningful way to measure its performance, ...
3
votes
0answers
31 views

Infer probabilities, for concatenation of words

Fix an alphabet $\Sigma$, and a set of words, $W = \{w_1,\dots,w_n\} \subseteq \Sigma^*$. I have a randomized model that works like this: Alice generates a random sequence of words, using some ...
3
votes
2answers
134 views

Are syntax and semantic just 2 structures such that one is a model of the other?

The syntax of a language is a structure. The semantic of a language is a structure. The semantic of a language is a model of its syntax. And that's all ? The duality syntax/semantic is just model ...
0
votes
0answers
92 views

Most frequently auto-tagging algorithms for text documents

Please if it's possible introduce the newest and most frequently auto-tagging algorithms for auto-tag text document. I want to get one text document and export tag for that. I also saw TF-IDF but it ...
2
votes
0answers
23 views

How to compute the TF-IDF scores for a handful of documents, but without my own corpus?

I have a small number of documents (I could probably get 4 or 5 documents) and want to assign terms in these documents a score based on its importance to the document. I want to find which terms are ...
2
votes
0answers
27 views

How to store linguistic data?

I'm both interested in practical and theoretical aspects of the problem. How do you store linguistic data. Suppose you have stemmed, parsed, tagged and, perhaps even did some preliminary analysis, ...
3
votes
1answer
64 views

Choice of machine learning algorithms frequency of parts of speech

I'm new to machine learning. I have text, and I tag the text according to their parts of speech tag ie walk is tagged as verb, etc. I tag entire sentences, and then convert them into a vector based on ...
2
votes
0answers
16 views

How do IR researchers evaluate the ranks of documents?

I am developing a new IR system in a specialized context. I understand that a traditional IR system (like a search engine) should rank documents in terms of their relevance for a query. The most ...
2
votes
1answer
55 views

Most frequently tools or programming language for implementation text processing and nlp algorithms in academic papers and journals [closed]

I want to prototype and try some idea (some algorithm) in the field of text processing and nlp and if the results was good I want to publish some paper or journal article about that. I am familiar ...
1
vote
2answers
187 views

Detect if a sentence is in passive voice

Given an English sentence, I am looking for a programmatic way to tell whether the sentence is written in passive voice. Currently, I just check if there is a was ...
2
votes
1answer
43 views

Looking for a paper comparing NLP methods with Data Mining techniques

I've recently attended a conference, where one of the participants mentioned a recent paper published by a Google employee, which showed that using data mining techniques in application to NLP might ...
1
vote
1answer
41 views

NLP - Deep belief neural networks or logic?

The NLP progresses seems to me that has split in two big group of thoughts: Deep learning have a neural network with multiple layers that has been trained and learned to represent knowledge and ...
1
vote
1answer
19 views

Where can I find a study on the amount of different word frequencies in a corpus? [closed]

I need to know how many different values the frequency of a certain word in a corpus can there be for a natural language processing problem. Is there any study or site that has such estimation?
2
votes
1answer
86 views

Natural Language Parser that can handle syntactic and lexical errors

I have some background in natural language processing and I know that all parsers (top down or bottom up, or mix), at least when I studied just about a few years ago, cannot handle any error. A small ...
3
votes
1answer
65 views

Natural language query processing

I am trying to implement a natural language query preprocessing module which would, given a query formulated in natural language, extract the keywords from that query and submit it to an IR ...
5
votes
3answers
441 views

Complexity of natural language processing problems [closed]

Which natural language processing problems are NP-Complete or NP-Hard? I've searched the natural-lang-processing and complexity-theory tags (and related complexity tags), but have not turned up any ...
2
votes
1answer
24 views

How is wordnet curated?

I use Princeton's WordNet in NLP applications. I always read that it is "human-curated." But how is it curated? Who decides that words belong in a synset? How does the process work? Wikipedia does not ...
2
votes
3answers
234 views

Does programming language detection need more input than natural language detection?

I wonder which one of the two needs a larger input to achieve a decent accuracy: programming language detection or natural language detection? More details: Definition of Language detection: ...
2
votes
0answers
54 views

What are recent, high-quality surveys on NLP topics?

In particular POS tagging, dependency and constituent parsing. This is not really my field of study but I would really like to be able to make informed claims on what precisions current top systems ...
2
votes
2answers
613 views

What are the definitions of syntax and semantics?

For a formal language $L \subseteq \Sigma^*$ over an alphabet $\Sigma$. From https://proofwiki.org/wiki/Definition:Syntax The syntax of a formal language is its structure, and is specified by a ...
2
votes
2answers
106 views

Generative Machine Learning algorithms on tree structure

I'm looking into PCFG sentence grammar dependency structure parsing using StanfordNLP PCFG parser. It generates tree structures represented as a string like this: ...
2
votes
0answers
50 views

Two classes of documents. Find weighted relations between them

I have an NLP problem and a potential solution, but I’m a bit green here, so I’m looking for some validation or alternative suggestions. Background I have two types of documents: one is a set of ...
1
vote
0answers
65 views

Translation of natural language to logic [closed]

Given a statement in natural language, what can be said about how many possible translations there are in first-order-logic? What happen if we take a more complex logic like second-order logic and ...
3
votes
2answers
61 views

How do learn the most important nodes in a tree?

I have a list of 20000 words and how often they appeared in a set of 500 newspaper articles. I am trying to build a stemmer which chops off suffuxes from each words, so ...
3
votes
0answers
54 views

What are some of the methods that NLP practitioners use to automatically learn linguistic features from text? [closed]

I am learning about NLP, with an eye to starting some practical NLP projects. I see that many of the algorithms for relation extraction and named entity recognition require you to identify linguistic ...
2
votes
0answers
18 views

What are ways that you might analyze relations extracted from text [closed]

In the coursera NLP course, Dan Jurofsky says you might want to extract relations from text to serve as input to other algorithms. What are examples of ways that researchers have used or might use ...
3
votes
0answers
45 views

Document clustering for summarization

I am curious as to what steps one would reasonably need to take to perform an extraction-based text summarizer. I've taken a look at some papers I've found on Google such as this one, which explains ...
0
votes
0answers
25 views

Is there a paper/implementation/tool on automatically finding/suggesting similar questions for a given question?

I would like to know whether there is a method to find similar questions for a given question, just like this stackexchange.com does. Is there any paper or tools? I tried keywords such as ...
0
votes
0answers
132 views

NLP: in practice, what should I choose as Start and End symbol?

I'm writing a small program that implements a trigram HMM model and apply it by using Viterbi Algorithm. It's very standardized. However, I have never written anything like this before, and I get ...
1
vote
0answers
29 views

In NLP, tokens not seen in training sample, but you know or don't know what they are

In NLP, do you distinguish tokens that you don't observe in a training sample and still expect that they may occur in a test sample, between those you know what they are, and those you don't what ...
2
votes
4answers
278 views

What aspects of linguistics are necessary or good for natural language processing? [closed]

What aspects of linguistics are necessary or good to know for natural language processing? What references do you recommend for studying those aspects? Thanks!
2
votes
1answer
88 views

Solving the part-of-speech tagging problem with HMM

There is a famous part-of-speech tagging problem in Natural Language Processing. The popular solution is to use Hidden Markov Models. So that, given the sentence $x_1 \dots x_n$ we want to find the ...