Skip to main content

Questions tagged [nlp]

Natural language processing is the automated processing of text in human languages, typically to extract information from human speech.

Filter by
Sorted by
Tagged with
17 votes
6 answers
16k views

What is the best toolkit to parse an English sentence into a syntactic tree?

I need a tool-kit (preferably written in Java or Python) which parses an English sentence into a syntactic tree. Something like the Charniak parser.
Sina's user avatar
  • 173
11 votes
1 answer
158 views

Program to search EULA contracts for problems

I'm looking for a software that could search through the text of a EULA or other contract for suspicious clauses that you might take issue with. Does such a software exist? and if it does, Where ...
Sam I am says Reinstate Monica's user avatar
10 votes
7 answers
4k views

Library to grammatically classify English words (nouns, verbs, adverbs, etc)

I have this list with 1600 English words where I don't know the grammatical type. Now I would like to know for each word in this list whether it is a noun, verb, adverb or other grammatical type. If a ...
rubo77's user avatar
  • 536
7 votes
1 answer
145 views

Guess writer's native language

I am looking for a library or program that when given a text written in English tries to guess the writer's native language (e.g. based on the usual mistakes, phrases, etc.) : ideally, it would give ...
Franck Dernoncourt's user avatar
7 votes
0 answers
935 views

Are there any Natural Language Processing (NLP) libraries in C?

Are there any NLP libraries/toolkits similar to NLTK or OpenNLP but in C? Note that I want something in pure C and not in C++.
Morteza R's user avatar
  • 171
6 votes
3 answers
2k views

What is a good open source information retrieval library (search engine)?

So I have a Java application running on a websphere server. The server has an oracle database of boxes. Each box has a list of things in it. Each thing has a main description (input as text from ...
DFL's user avatar
  • 61
6 votes
0 answers
3k views

Convert a sentence from passive voice to active voice

I am looking for a library (Python/interpreted language/Java/C++ is preferred in descending order) or a otherwise program (CLI if possible) that can: change the voice of a sentence from passive voice ...
Franck Dernoncourt's user avatar
5 votes
2 answers
12k views

Automatic tool for resolving left-recursion within CFG

Though facing the fear that someone might not like my question but does somebody know a useful tool to either resolve left recursion or to simplify a context-free grammar automatically ? I need to ...
marc wellman's user avatar
5 votes
2 answers
723 views

Gender-Recognition API

Does anyone know of any API's out there that can determine gender based on a few of the following: Name Username Posts/Text/How they Talk Location Profile Description Picture Or if such an API ...
Ramie's user avatar
  • 153
5 votes
1 answer
58 views

Fixing cases in English text

I am looking for a program that can fix the cases in a text. Examples: "hello what's up? doing good?" -> "Hello what's up? Doing good?" "i called bob Yesterday. he's going to NYC." -> "I called Bob ...
Franck Dernoncourt's user avatar
5 votes
2 answers
2k views

Tool for drawing parse trees

Posted on Tool for drawing parse trees? [closed] by Xodarap: Does anyone have a tool for drawing parse trees arising from a context-free grammar? There is this question, but it dealt specifically ...
Franck Dernoncourt's user avatar
5 votes
0 answers
112 views

Test if two texts are likely to have been written by the same author

I am looking for a program that can test if two English-language texts are likely to have been written by the same author. Ideally it should output some confidence score, and indicate in the texts ...
Franck Dernoncourt's user avatar
4 votes
2 answers
94 views

Document Triage platform

I'm looking for some kind of software platform (or possibly open source API would do most of this) to perform document triage. Imagine you get 3,000 documents (word, pdf, powerpoint, mixed formats) ...
FrobberOfBits's user avatar
4 votes
1 answer
559 views

Library that can overlay a text with a heatmap

I am looking for a library that can overlay a text with a heatmap. I.e., add a highlight with gradient. I would simply define a value for each character: the value would define the highlight/heatmap ...
Franck Dernoncourt's user avatar
4 votes
0 answers
371 views

Open source .NET library for automatic Russian text summarization

I need a library to automatically summarize a text written in Russian. Requirements: Summarize a text (for instance from 5000 characters to 500 characters) Works with Russian Open source Usable from ...
Samat Yeshernkulov's user avatar
3 votes
1 answer
94 views

Basic algebra exercise solver

I am looking for a program that can solve basic algebra exercises such as: If Lynn can type a page in p minutes, what piece of the page can she do in 5 minutes? If Sally can paint a house in 4 ...
Franck Dernoncourt's user avatar
3 votes
1 answer
126 views

Program to automatically read Terms and Conditions

I am looking for a program that reads terms and conditions and shows me the sections that are privacy and tracking related. Requirements: free automatically detects when terms and conditions are on ...
ᔕᖺᘎᕊ's user avatar
  • 6,552
3 votes
1 answer
2k views

Open Source Dialog System Natural Language Processing Engine?

Introduction and goal I'm interested to develop (possibly in Ruby language) Conversational Commerce Chat Apps [1]. A Dialog System Engine ? Specifically I want to implement a dialog system engine, ...
Giorgio Robino's user avatar
3 votes
1 answer
144 views

Python libraries for clustering decimals

I have a collection of decimals, with each a value between 0.0 and 1.0. I would like to "cluster" them by value on two dimensions, so that decimals with near values are grouped together, yet spaced ...
Naveen Mohan's user avatar
3 votes
1 answer
63 views

affordable library for analyzing texts/sentenses gramatically

I have project, to create application, that should do following: Application should take word or sentence as an input. It should analyse the word/sentence grammatically and should give grammatical ...
Tornike Shavishvili's user avatar
3 votes
1 answer
898 views

Parse the body of a large number of emails

I am looking for server side software to parse a very large number of emails and extract the email signature. Very specifically, I want to input the body of a mail message, identify the signature, and ...
Mika's user avatar
  • 133
3 votes
0 answers
120 views

Java library to calculate the semantic distance between two documents

I am looking for any java library that calculates the semantic distance between two documents. I know that WS4J can calculate semantic distances using wikipedia data, also lingpipe has some NLP ...
user avatar
3 votes
0 answers
149 views

Natural language generation for Japanese

I am looking for tools, libraries, software or services to generate natural Japanese text from raw data. The best example of what I am trying to do is the commercial tool Wordsmith from Automated ...
Eric Platon's user avatar
3 votes
0 answers
87 views

Tool to annotate html files (preferably within web browser)

I want to annotate web pages to tag words as certain classes. I have tried brat but this only works with .txt files. I think a chrome/firefox extension would be best since the browser could easily ...
B.McCarthy's user avatar
3 votes
0 answers
39 views

Is there a tool out there that extracts the main text in an email?

What I'm looking for is a tool that detects salutations/greetings, signature, quotation of another email, legal notices and separates all of this "noise" from the main content of the email. For ...
zelandiya's user avatar
3 votes
0 answers
34 views

Adjective ordering program or library

I am looking for a program or library that can take as input one noun and a list of adjectives, and outputs the correct noun phrase comprising those noun and adjectives. E.g. if the input is purple, ...
Franck Dernoncourt's user avatar
2 votes
2 answers
263 views

Extracting the core content from a webpage

I have a list of 1,000 URLs pointing to news articles. I am looking for a program (CLI if possible) or libraries (C++/Java or interpreted languages preferred) that can take a URL as input and output ...
Franck Dernoncourt's user avatar
2 votes
3 answers
498 views

Programmable Alternative to DialogFlow

I would like to code actions and responses to gain finer control as opposed to how we do using UI in DialogFlow. But building a whole platform like DialogFlow would take a lot of time, but is there ...
Saravanabalagi Ramachandran's user avatar
2 votes
3 answers
168 views

Human-like summarization of collection of texts

Wondering if there is any tool, preferably open-source, that generates a human-like summary of a corpus of articles/tweets/books? Assuming one has lots of article abstracts, I would like to make a ...
Gonçalo Peres's user avatar
2 votes
1 answer
52 views

Javascript library to parse quantities of items

Is there a library that can preform the following transformations? "5 servings" => {num: 5, name: "servings"} "five blocks" => {num: 5, name: "blocks"} "five and a half teasopons of sugar" =>...
2426021684's user avatar
2 votes
1 answer
1k views

Chinese Sentiment Analysis Tools

I am doing a research study on some of the most recent Chinese Sentiment Analysis tools. My purpose is to evaluate the analysis results of each tool on a set of sentences – I am looking for sentence-...
Thomas Hsieh's user avatar
2 votes
2 answers
207 views

Web-based annotation tool to mark words as belonging to a predefined class

I'm looking for a web application (either the third-party hosted or hosted by myself) that can: load and display a text allow the user to mark a word or a group of words as belonging to a predefined ...
Franck Dernoncourt's user avatar
2 votes
1 answer
26 views

Looking for a programming library or command line program that parses and produces syntax trees for natural languages

Say I have a string representing text in a natural language, for example: She is an effective teacher. Most students have found her reasonably helpful. Is there a programming library or command line ...
forgodsakehold's user avatar
2 votes
1 answer
56 views

Some API or any helpful tool/repo for doing a text summary

So I wanted to start a new project of a text summarizer tool (a website). So far I found a free API for summarizing English text (smmry.com), but for other languages I want to include (French and ...
Bug Alpha's user avatar
2 votes
1 answer
1k views

Best NLP Library for German language in Python?

Hello I am facing a project where I have to analyze lots of text data. Its data is not a typical text - it is all business plans. Are there any useful libraries for Python I could use to evaluate the ...
grumpyp's user avatar
  • 121
2 votes
2 answers
1k views

API to retrieve answers for general questions

I was looking for a service (with API) where I can ask it a general question (aka, when was Einstein born?) and retrieve an answer from the Web. Is there any available service to do that? Have tried ...
user3607093's user avatar
2 votes
1 answer
371 views

Automated de-identification of free-text medical records

I am looking for a program that can perform automated de-identification of free-text medical records. The de-identification should abide by Health Insurance Portability and Accountability Act (HIPAA) ...
Franck Dernoncourt's user avatar
2 votes
1 answer
109 views

Deciphering a bash command

I am looking for a program that can take a bash command as input, e.g.: ls -lv ps aux | grep python | grep -v "grep python" | awk '{print $2}' | xargs kill -9 du -h --max-depth=1 screen -dmS gp ...
Franck Dernoncourt's user avatar
2 votes
0 answers
14 views

Text to SQL query framework

I am looking for a framework to translate text/questions/sentences to SQL queries given a relational database schema. For instance, assuming to refer to the Northwind database, the system should ...
w4bo's user avatar
  • 121
2 votes
0 answers
33 views

Identifying foreign language in text

We are meant to implement some accessibility measures on a website, including one that requires that all words in a different language are properly identified, thanks to a lang=xx attribute. Example: ...
David's user avatar
  • 121
2 votes
0 answers
155 views

Web service to parse English sentences in real-time

Are there English language parsers that I can access via web-services, which can return the format of the sentence in real-time? I have looked at the Stanford parser, but wonder what the community ...
ImTalkingCode's user avatar
2 votes
0 answers
25 views

Converting social-network-quality text into normal text

I'm looking for a program that can convert social-network-quality text into normal texts. Examples: "c u at da club 2nite" -> "see you at the club tonight". "k gr8!" ->"ok great!" "I'll c you there" ...
Franck Dernoncourt's user avatar
2 votes
0 answers
182 views

Software/API for Arabic text summarization

Are there any text summarization softwares for Arabic. By text summarization i mean the important sentences to be extracted from the entire document.Basically i'm looking for an arabic summarizer ...
user6971's user avatar
2 votes
0 answers
877 views

Generate text from other similar texts

I'm looking for a piece of software, a script or whatever that could generate text based on multiple other texts.That could be used for creating stories for instance. If the stories used as the "...
mtefi's user avatar
  • 19
2 votes
0 answers
367 views

A free Facebook sentiment analysis tool?

Wondering if there's a lightweight sentiment analysis tool out there that's free and works with Facebook. I know there are a few decent free tools that do this for Twitter (Sentiment140 comes to ...
samthebrand's user avatar
1 vote
1 answer
1k views

Generate sentences according to custom vocabulary/rules

I’m looking for a tool that can generate text (natural language) according to a list of words and their syntactic/morphological rules, both which I specify. So for example, I might add the word "...
unor's user avatar
  • 7,696
1 vote
1 answer
15 views

Text classification based on interests or topics for short texts

This question (CC BY-SA) was posted on https://stackoverflow.com/q/28181599/395857 by PS1 but was deleted, so I'm reposting it here. I have been searching for sparse text classification tool, that ...
Franck Dernoncourt's user avatar
1 vote
1 answer
829 views

Offline language detection library or script

One of my Python services was using textblob for language detection. Last month Google made a breaking change to the API service which textblob was calling. Steps have been provided on SO to update ...
user avatar
1 vote
2 answers
64 views

Text classification using Python

I am doing a text classification related task in Python using NLP and SkLearn. I need to remove random words from my text. I know I can remove stop words and punctuation using nlp. But what I am ...
Ubaid Butt's user avatar
1 vote
1 answer
47 views

Library/service/API that can be used to assign relevant tags to content

For example, let's say we feed in this content: { "title" : "Bitcoin drops 20% after $70M worth of bitcoin was stolen from Bitfinex exchange" "body" : "Bitfinex, one of the most popular ...
darkhorse's user avatar
  • 113