Natural language processing draws knowledge from a diverse collection of fields including computer science, linguistics, and statistics in order to extract pertinent information from the spoken or written word.

learn more… | top users | synonyms

4
votes
1answer
115 views

How can I test a search engine for an uncommon human language?

We are writing a search engine from scratch in a quite uncommon language, Aramaic, mostly for learning purposes but also because few resources are available in given language. The engine is/will be ...
0
votes
2answers
144 views

How could an expert system get some meaning from a sentence? [closed]

How could an expert system tell following scenarios apart? How could we include some meaning of a sentence, if at all? A machine needs 1 day to produce x units, and, we know that two machines like ...
1
vote
0answers
102 views

Algorithmic approach for text analysis of ingredients and instructions [closed]

Background Looking to separate lists of ingredients from instructions. Users scan recipes from 3x5 cards, magazines, cookbooks, etc. OCR software converts scanned images into plain text--typically a ...
0
votes
1answer
89 views

Natural Language to Search Criteria - Date Ranges

Consider an application that stores a set of records that contain: Description Cost Purchase Date I'd like to be able to allow users to utilize natural language to search the dataset. For ...
2
votes
6answers
384 views

Are there any algorithms for splitting or combining words into their more common form?

Are there any existing algorithms which can look through a list of words and split or combine words into their more common form? For example, I have a list of many business names in the health care ...
1
vote
0answers
127 views

What is the purpose of chunking strings in natural language processing?

I see many examples of libraries that use a 'chunker' and also people asking how to write chunkers, but what is this for and why do we need it? Isn't it enough to split a text by whitespace or other ...
3
votes
1answer
145 views

Sentence Tree v/s Words List

I was recently tasked with building a Name Entity Recognizer as part of a project. The objective was to parse a given sentence and come up with all the possible combinations of the entities. One ...
2
votes
1answer
110 views

How to do simple natural language categorization

How would you go about parsing a sentence like "Bought two kilos of steak from Acme supermarket" into a data structure like the following JSON representation: { item: {name: "steak", tags: ...
-2
votes
1answer
226 views

building a chat bot for an e-commerce site

I was recently talking to a couple of friends who run a modest e-commerce website (Daily visitors: approx. 100,000,). They plan to have an in-site chat module to engage customers. Since the whole ...
2
votes
1answer
208 views

How can I distinguish between one-worded expressions and two-worded expressions?

I was told to create two lists concerning most frequently used words from a plain text (10 Mb arbitrary texts) as monograms (for single worded expressions such as human, water, is) and bigrams (for ...
3
votes
2answers
359 views

NLP - Queries using semantic wildcards in full text searching, maybe with Lucene?

Let's say I have a big corpus (for example in english or an arbitrary language), and I want to perform some semantic search on it. For example I have the query: "Be careful: [art] armada of [sg] is ...
8
votes
2answers
575 views

Persisting natural language processing parsed data

I've recently started experimenting with natural language processing (NLP) using Stanford's CoreNLP, and I'm wondering what are some of the standard ways to store NLP parsed data for something like a ...
3
votes
3answers
1k views

Separating words in a string

How do I separate words in a string? In the following I have a random sample of words in a string extracted from text file with over a million words. Here's the string: "intervene Pockets ...
1
vote
2answers
881 views

How to create a Semantic Network like wordnet based on Wikipedia?

I am an undergraduate student and I have to create a Semantic Network based on Wikipedia. This Semantic Network would be similar to Wordnet(except for it is based on Wikipedia and is concerned with ...
-2
votes
2answers
367 views

NLP as a job requirement

When an employer points out that NLP is required in a position what does he expect? Can I teach myself natural language processing theory or must know specific frameworks or what?
6
votes
3answers
1k views

What algorithm(s) can be used to achieve reasonably good next word prediction?

What is a good way of implementing "next-word prediction"? For example, the user types "I am" and the system suggests "a" and "not" (or possibly others) as the next word. I am aware of a method that ...
3
votes
2answers
304 views

Available options for classifying words in text?

I am researching ways to classify words in text and I'm wondering what options there are and which are best suited to this job. I'm mostly interested in keywords which are most often nouns. So far I ...
1
vote
1answer
437 views

Is Agile Development used in Machine Learning and Natural Language Processing?

I've been developing web apps for a while now and it is standard practice in our team to use agile development techniques and principles to implement the software. Recently, I've also become involved ...
4
votes
1answer
2k views

Starting point for learning natural language processing in Java [closed]

Currently I am a high school student and new to the natural language processing field. I am trying to write a Java program that can provide answers that can be understood by humans to the questions ...
7
votes
2answers
153 views

Guess if a time is AM or PM

I'm currently in the process of writing a human date parser. By human date, I mean it should be able to interpret strings as "tomorrow at 2" and return a valid date depending on the current time. The ...
125
votes
14answers
6k views

Simple method for reliably detecting code in text?

GMail has this feature where it will warn you if you try to send an email that it thinks might have an attachment. Because GMail detected the string see the attached in the email, but no actual ...