Metadata-Version: 2.1
Name: lexsub
Version: 1.1.3
Summary: State of the art Lexical Substitution in Context
Home-page: https://github.com/anishacharya/LexSub
Author: Anish Acharya
Author-email: anishacharya@utexas.edu
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown

## Setup 
``` 
pip3 install lexsub
Release: https://pypi.org/project/lexsub/   
```

## Background
The Lexical Substitution task involves selecting and ranking lexical paraphrases for a target word in a given sentential context. In the task, annotators and systems find an alternative substitute word or phrase for a target word in context.
The task involves both finding the synonyms and disambiguating the context.
To give an example:
```
Context: The wine was too strong to drink.
Target Word: strong

Predicted Candidates (Ranked): 
powerful 
potent 
warm
hot 
solid 
hard 
```

*Powerful* and *potent* are much better replacements as indicated by 
the score next to them as well. Whereas, all are viable 
replacement candidates given the context from a language modeling
perspective.   
Now notice two important things that is interesting: 
* Not all synonyms fit in the context.  
(direct lexical substitutions aka synonyms won’t always work)
* Not all words that fit in the context preserve the meaning 
of the sentence. (LM score doesn’t always correlate)  

## Datasets: 
A. *Lexical Substitution*:
* [SEMEVAL-2007](http://www.dianamccarthy.co.uk/task10index.html)
* [Coinco](https://www.ims.uni-stuttgart.de/en/research/resources/corpora/coinco/)

B. *Word Sense Disambiguation:*
* [WIC](https://pilehvar.github.io/wic/)
* [WSD](http://lcl.uniroma1.it/wsdeval/home)


## References: 
1. [SOTA-BERT](https://www.aclweb.org/anthology/P19-1328.pdf)
2. [Pre-BERT-SOTA,Melamud](https://www.aclweb.org/anthology/N16-1131.pdf) 
3. [PIC- Katrin](https://u.cs.biu.ac.il/~melamuo/publications/melamud_vsm15.pdf)
4. [SemBERT, AAAI 2020](https://arxiv.org/pdf/1909.02209.pdf)
5. [LIBERT](https://arxiv.org/pdf/1909.02339.pdf) 
6. [Morgifier LSTM, ICLR 2020](https://arxiv.org/pdf/1909.01792.pdf)


