Hot answers tagged

19

from nltk.corpus import wordnet try: wordnet.synsets('test') except LookupError: import nltk nltk.download('wordnet') # For more information see: https://www.nltk.org/data.html def anti(word, fallback=None): for i in wordnet.synsets(word): for j in i.lemmas(): for k in j.antonyms(): return k.name() ...


6

Using the Corpus Query Processor or a similar corpus engine with a suitable corpus to answer your question, the query [word="[Ii]ron.*"][word=".*"] and a frequency breakdown on the types does the job. The more difficult thing is finding a "suitable" corpus, news, science, or literary texts will give different ranking lists.


5

Most of these aren’t CELT-specific, but commonly used in manuscript editions everywhere. MS is a common English abbreviation for manuscript. The Latin is part of the manuscript. A very large percentage of mediaeval European manuscripts – and more or less all the Irish ones – are written either entirely in Latin or in some mixture of Latin and a local ...


5

The other answers have hit the highlights, going so far as to suggest that it is impossible in principle. Contrariwise, I argue that it could be done in principle, as long as you don't overstate what IPA does. IPA is a conventional system (conventions can be voted in or out) for grouping a range of acoustic events to letters, with a coarse enough granularity ...


5

The linked page is prominently open source. You can probably download the sources to your own computer and tweak the parameters to make it speak more slowly. It links to http://www.masswerk.at/mespeak/ which displays detailed controls for amplitude, pitch, speed, word gap, etc. The same controls are hardcoded into mespeak.js in the fragment $speed=175;$amp=...


4

There are 3 steps in doing this task: Identifying the languages in webpages Building a crawler that downloads the web page Doing linguistics analysis since my primary NLP language is python and there are a lot of NLP libraries written for Python we use Python here. For identifying the language you can use some great language identifiers like this (based ...


4

The IMS Open Corpus Workbench might work for you.


3

Take a look at 2Hz Noise Suppression API. It's language-agnostic and is a REST API so you can use it from any programming language. Currently the API isn't designed for real time however this will be added down the road. (full disclosure - I work at 2Hz)


3

Here is a script I quickly assembled from pieces of code I had lying around: https://trinket.io/python3/a33a025467?toggleCode=true&showInstructions=true Beware that this script parses your tree very naively; it just processes the input symbol by symbol and does some formatting when it encounters opening or closing brackets; it will not warn you if you ...


3

Using a BYU corpus, you can search for iron* _nn* where the first part matches words starting with “iron” and the second part matches nouns. It’s as simple as typing that into the search box, though there are more complicated options available. The two BYU corpora I use the most are the Corpus of Contemporary American English and the British National ...


2

A single program that supports both alignment and adding morphological annotation is impossible in the next 10 years. Having a fully annotated and sentence-aligned version is everybody's goal. I'm working on a Sanskrit-Russian corpus and so I build upon http://kjc-fs-cluster.kjc.uni-heidelberg.de/dcs/index.php?contents=texte and add Russian parallel texts. ...


2

There is a library called Unidecode that translates any unicode (that includes IPA) to ascii. It is available in python and .net as far as I know. From what I see, you are using php in that site. I have not tried it, but there is a PHP-version of it here: https://github.com/alexei/silverstripe-unidecode


2

From your additional comments I see that you want to have some LaTeX input that can be rendered in two ways: Cyrillic orthography and IPA. I suggest the following approach: Design some LaTeX macros, one Macro for each possible pair (Cyrillic letter(s), IPA representation). There will be easy cases and complicated ones. Then use some switches to the macros to ...


2

The Open Corpus Workbench originally developed at IMS Stuttgart has such a tool, called cqp (Corpus Query Processor). There are other implementation of similar tools, to mention one, there is Poliqarp. The tool can do really amazing things when your corpus is annotated (e.g., for part-of-speech), you can issuer mixed queries for word forms and part-of-...


2

For French: https://tophonetics.com Languages: English, Español, Français, Português, 日本語, 中文, Русский No Italian or German IPA For German: http://tom.brondsted.dk/text2phoneme Languages: Danish, English, German. For Italian: -> You can use Wordreference.com, for instance: https://www.wordreference.com/iten/ampio: > [ˈampjo] It should give IPA ...


2

Removing noise usually corrupts the speech and harms the performance. It is frequently more accurate to decode noisy speech than noise-cleaned speech, in particular because recognizer does noise cleaning or noise compensation by itself. For other cases except speech recognition, rnnnoise is reasonable.


1

There is hunalign available from github. It is the current standard tool for multilingual aligned corpora.


1

As others have said, there's a reason linguists use the IPA (or a variant such as X-SAMPA or Americanist) instead of English spelling—if English spelling could clearly indicate pronunciation, you wouldn't be needing this tool in the first place! (Apart from that, ē-thē-ˈō-pē-ə isn't IPA; it looks a bit like the system the American Heritage Dictionary uses? ...


1

You'll need a parser to identify objects automatically. There are a few online interfaces to natural language parsers. For example, you could use the Stanford parser (link) and look for "dobj" to find direct objects.


1

I would definitely recommend using AntConc (download here) for the purpose you have described because AntConc is free, you are indeed able to copy and past concordance lines into a spreadsheet, and there are many tutorials and publications available about specifically using AntConc for language learning. I would highly recommend this book which was ...


1

Considering manual annotation, there is WebAnno, a very flexible annotation tool that allows you to define your own annotation layers. It has a web user interface and allows for collaborative annotation.


1

In Computational linguistics, there are tools called "Stemmer" or "Lemmatizer" that perform the task you are asking for. Entering "hebrew lemmatizer" into duckduckgo search reveals the following first hit http://code972.com/blog/2013/08/129-hebrew-search-with-elasticsearch-and-hebmorph with a reference to GitHub https://github.com/synhershko/HebMorph ...


1

Another GUI interface tool for annotation you can use is MAE (Multi-document Annotation Environment) written by Amber Stubbs. It requires you to supply your own .DTD file (essentially .xml), which defines the possible annotation tags and links for the annotator. It also allows the creation of non-consuming tags, which are for links that do not have any ...


1

GATE is a fairly well known and widely used annotation tool. It allows users to specify customized annotation schemas using XML. I also believe it natively lets you export your corpus to XML. I would caution you that GATE is very much a tool by engineers for engineers. The interface is a bit clunky and the GATE server requires quite a bit of initial set up. ...


1

You can use : https://the.sketchengine.co.uk/auth/corpora/ It's practical and at first, it makes you understand what's what over there.


1

Although you are asking for a tool to do it yourself, you should not neglect the existence of corpora in many languages on the web, e.g., the Leipzig Wortschatz project at http://corpora.informatik.uni-leipzig.de/ that features 219 languages.


1

Well, I'll add my non-answer to the other two. :-) I'd like such a tool myself. One thing that would make it harder than text-to-speech is that text-to-speech depends on context to better guess the right spelling of a word that can have many different sounds (depends on the speaker). Other questions mention tools that do it for specific languages, but ...


1

This is Stanford NLP Software for .NET The Stanford NLP Group makes parts of Natural Language Processing software available to everyone. These are statistical NLP toolkits for various major computational linguistics problems. They can be incorporated into applications with human language technology needs https://github.com/sergey-tihon/Stanford.NLP.NET ...


Only top voted, non community-wiki answers of a minimum length are eligible