[HN Gopher] An Open Version of WordNet
___________________________________________________________________
An Open Version of WordNet
Author : syats
Score : 49 points
Date : 2020-07-30 13:50 UTC (1 days ago)
(HTM) web link (en-word.net)
(TXT) w3m dump (en-word.net)
| rohan1024 wrote:
| A fun way to access WordNet hosted by dict.org
| nc dict.org 2628 DEFINE wn hacker
|
| Don't think it's open though.
| minerjoe wrote:
| It's open. You can install your own copy locally.
|
| Arch has an AUR dict-wn that does this. For those not using
| arch you can still clone the PKGBUILD and see how it grabs and
| compiles and installs.
|
| git clone https://aur.archlinux.org/dict-wn
| frank2 wrote:
| I remember installing the Wordnet database on my Arch Linux
| install 17 years ago so I would have a dictionary I could use
| without internet connectivity. Wordnet can be used as a
| traditional dictionary although it is not very good compared
| to, e.g., the dictionary that comes with any Mac or iPhone.
| Yeroc wrote:
| Is there a similar API with the etymology of the words? I played
| with this a bit and it doesn't seem to cover this area.
| jatsign wrote:
| An animated graph of wordnet links may help explain why it's
| useful: https://www.wordsapi.com/
| syats wrote:
| Wordnet is like a dictionary in that it contains definitions and
| synonyms of words. It goes beyond a dictionary in that it also
| records relationships like hypernym (broader) and hyponym
| (narrower), which can be useful for "understanding" (what ever
| that means) text. It is a graph, that connects different senses
| (called synsets), and also senses to words. It used to be
| released under some close license and poorly maintained, now
| there's a fork of it on github to which all can contribute.
| tasogare wrote:
| Wordnet has a "gloss" field but it's very lacking if used as a
| traditional dictionary. Its value lies in the graph of synsets.
| compressedgas wrote:
| The problem with the gloss or example field is that it is per
| synnet and not per (word, sense or synnet) pair as it would
| be in a normal dictionary.
|
| This means if you try to use it as a normal dictionary the
| glosses tend to not contain the word for which you are
| listing the senses.
| Isamu wrote:
| Wordnet is already open, I think the advantage of this is that it
| is being actively maintained.
|
| From Wordnet:
|
| > Permission to use, copy, modify and distribute this software
| and database and its documentation for any purpose and without
| fee or royalty is hereby granted, provided that you agree to
| comply with the following copyright notice and statements,
| including the disclaimer, and that the same appear on ALL copies
| of the software, database and documentation, including
| modifications that you make for internal use or for distribution.
| rrose wrote:
| it... doesn't know the word "how"? literally like the second word
| i typed in. it seems like this must have some holes in it?
| Bellamy wrote:
| What exactly can you do/produce with this graph and connection of
| words? I can't understand the benefits.
| suyash wrote:
| yes, I'm also interested in use cases for the same.
| abhgh wrote:
| Using WordNet used to be a very popular way to perform
| "knowledge-rich" NLP around late 90s upto around 2010
| (approximate timeline). "Knowledge-rich" meant you could start
| with some understanding of the language and not rely solely on
| the data at hand. Much like the use-case that pretrained models
| like GloVe serve today (WordNet probably is closer to
| Dependency based word vectors [1]). Some interesting uses were
| query expansion [2], sense disambiguation [3], word
| similarities (popular: wu-Palmer similarity, check out NLTK),
| and in an interesting area called "lexical chains" [4]: group
| of related words running through a text, with their "weave"
| signifying topics.
|
| The arrival of WordNet on the scene, when it happened, was a
| big deal, since there weren't many ways to perform knowledge-
| rich NLP back then. The common ones were using a dictionary or
| a thesaurus. There was some effort to tie topic models with
| WordNet too, like LDAWN [5]. And extending it, based on
| collocation information you could glean from the gloss -
| "eXtended WordNet" [6].
|
| You still (occasionally) see its uses where you need some kind
| of rich prior knowledge. For ex, the "Hierarchical
| Probabilistic Neural Network Language Model" by Morin and
| Bengio [7], or cluster labeling (which uses embeddings with
| WordNet) [8]. To quote an example from the latter, 'a word
| cluster containing words "dog" and "wolf" should not be labeled
| with either word, but as "canids"'. And you know "canids" is a
| super-category here, by looking up the precise relationships in
| WordNet.
|
| My own Master's research looked at combining WordNet based
| lexical chaining with more "ML"-ish techniques like Hidden
| Markov Models [9]. Which is why I know, or rather, vaguely
| remember, some of the stuff that was happening back then :-)
|
| I think the primary reason why WordNet did not retain its
| popularity was it was a good "one off" solution. Worked well
| with "correct" English. You want to adapt it to your domain
| vocabulary? Heuristics. You want to use WordNet in another
| language? Well, someone needs to build one first. You want to
| use it to process text in internet lingo? Nope, hybrid models
| and heuristics. Also, at this time the amount of text available
| to train on was increasing by leaps and bounds, so the field
| moving toward ML heavy techniques made sense.
|
| [1] https://www.aclweb.org/anthology/P14-2050.pdf
|
| [2] https://www.aclweb.org/anthology/P08-1017.pdf
|
| [3]
| https://pdfs.semanticscholar.org/7f2c/b3e390c5e539ef9089014a...
|
| [4]
| http://www.cs.columbia.edu/nlp/papers/2003/galley_mckeown_03...
|
| [5] https://wordnet.cs.princeton.edu/papers/jbg-EMNLP07.pdf
|
| [6] https://en.wikipedia.org/wiki/EXtended_WordNet
|
| [7] https://www.iro.umontreal.ca/~lisa/pointeurs/hierarchical-
| nn...
|
| [8] https://www.aclweb.org/anthology/U18-1008/
|
| [9]
| https://pdfs.semanticscholar.org/e7ce/34e5acdbb7a91e28fdafa9...
| defen wrote:
| You can build a company called Applied Semantics and then sell
| your tech to Google so they can develop products called
| "AdSense" and "AdWords" and make trillions of dollars of
| revenue. However, first you'll need to invent a time machine
| that can take you back in time 20 years.
| azinman2 wrote:
| It used to be used in NLP, but never to great success. Word
| embeddings are a far more powerful way to achieve a lot of
| similar goals, but with easier computation, easier scalability
| to other languages, and accommodation for new/personal words
| that aren't (yet) in the dictionary.
___________________________________________________________________
(page generated 2020-07-31 23:00 UTC)