#wordnet

[allthingslinguistic]

Robot Mind Meld is a game of exploring word map relationships. From the description:

I was designed by Alex Lew, and am powered by Conceptnet Numberbatch, a set of “word embeddings” that allow me to think quantitatively about words and their relationships. Constructed by analyzing millions of documents for patterns, these “numberbatches” now play a role in most programs that process language, from speech recognition to machine translation.

Play it yourself here.

[ijtsrd]

Automatic Query Expansion Using Word Embedding Based on Fuzzy Graph Connectivity Measures

by Tarun Goyal | Ms. Shalini Bhadola | Ms. Kirti Bhatia "Automatic Query Expansion Using Word Embedding Based on Fuzzy Graph Connectivity Measures"

Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-5 , August 2021,

URL: https://www.ijtsrd.com/papers/ijtsrd45074.pdf

Paper URL: https://www.ijtsrd.com/computer-science/artificial-intelligence/45074/automatic-query-expansion-using-word-embedding-based-on-fuzzy-graph-connectivity-measures/tarun-goyal

callforpapercommerce, ugcapprovedjournalsincommerce, commercejournal

The aim of information retrieval systems is to retrieve relevant information according to the query provided. The queries are often vague and uncertain. Thus, to improve the system, we propose an Automatic Query Expansion technique, to expand the query by adding new terms to the user s initial query so as to minimize query mismatch and thereby improving retrieval performance. Most of the existing techniques for expanding queries do not take into account the degree of semantic relationship among words. In this paper, the query is expanded by exploring terms which are semantically similar to the initial query terms as well as considering the degree of relationship, that is, “fuzzy membership- between them. The terms which seemed most relevant are used in expanded query and improve the information retrieval process. The experiments conducted on the queries set show that the proposed Automatic query expansion approach gave a higher precision, recall, and F measure then non fuzzy edge weights. 

[alexainslie]

“WordNet goes one step further by using this classification model to compute similarity between two words. In this way, it can figure out that a cat and a dog are similar, a phone and a computer are similar, but a cat and a phone are not similar!” -WordNet

[bluegreenjackiechan]

Book cover design from 5 most used words in each book.

It’s quite interesting that most used words in a book shows the character of original text.

I used RiWordNet from RiTa plugin( http://rednoise.org/rita/ ) and WordNet(https://wordnet.princeton.edu/) to analyse original text and picked 5 most used words(nouns) from them.

Original texts are from Project Gutenberg (https://www.gutenberg.org).

Please note that more frequently used but meaningless words (such as he, it, me, who, and so on) have been excluded.

[a1paul-blog]

python code to find all synonym of a given word from wordnet

Finding a synonym from wordnet is easy and hard at the same time. Although it takes a few lines of code, knowing what to look for is the hard part! So here is a code to find all synonym of a given word and export as list. https://gist.github.com/cdtavijit/431135aa6da53d47bc72

<script src="https://gist.github.com/cdtavijit/431135aa6da53d47bc72.js" type="text/javascript"></script>

[aatallah]

Hackathon project: Saurus, the automatic thesaurus

This past weekend, my friends Doug Safreno and Clay Schubiner won the “best API integration” award with me at the 2014 Meteor Hackathon. We built Saurus, a word processor with real-time natural language processing. It finds synonyms and Wikipedia articles for you as you type:

Saurus uses context-aware parsing and part-of-speech tagging to recognize named entities in order to provide smart Wikipedia results, word synonyms from WordNet, background themes from Flickr using AlchemyAPI, and more.

Check it out at http://thesaurus.meteor.com

The code is written with extensibility in mind, so you can pipe-in new APIs to create new semantic helpers and customize them. It's open sourced and available at https://github.com/alexanderatallah/saurus.

[coquisuda]

WordNetのデータから関連性を可視化する

[allthingslinguistic]

WordNet® is a large lexical database of English. Nouns, verbs, adjectives and adverbs are grouped into sets of cognitive synonyms (synsets), each expressing a distinct concept. Synsets are interlinked by means of conceptual-semantic and lexical relations. The resulting network of meaningfully related words and concepts can be navigated with the browser. WordNet is also freely and publicly available for download. WordNet's structure makes it a useful tool for computational linguistics and natural language processing.

Here's an example of some of the types of information you can get from WordNet, based on a search for "linguistics" (play around with this example here).

The structured data from WordNet is great for use in other projects (attention: anyone interested in computational linguistics!).

One example of another use is ImageNet, which maps a subset of the relations in WordNet along with pictures. Here's an example of the results that I got for "cat" (play around with these examples here and here). 

There are also several sites where you can visualize the relationships among difference entries in WordNet, including GraphWords and VisuWords. For example, here's "cat" again: 

WordNet itself is English-only, but the Related Projects page also has links to WordNets in other languages and multilingual WordNets, including Global WordNet and Open Multilingual WordNet.