Git Product home page Git Product logo

emanuelegiona / nlp2019_hw2 Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 0.0 262 KB

Neural Sense Embeddings, replicating "SENSEMBED: Learning Sense Embeddings for Word and Relational Similarity", Iacobacci, Pilehvar and Navigli, 2015

License: GNU Affero General Public License v3.0

Python 100.00%
sense-embeddings word2vec sense2vec neural-networks nlp tensorflow python navigli sapienza-university

nlp2019_hw2's Introduction

NLP 2018/2019 (more)

Homework 2

Sense embedding is a technique for language modeling and feature learning applied in order to obtain dense vectors for words senses, instead of relying on large sparse vectors as the ones produced via a one-hot enconding approach.

The need for vectors representing the different senses of a word is driven by the high degree of polysemy that is proper of natural languages, which a single vector per word fails to address when such word is ambiguous.

Similarly to word vectors, sense embeddings can be built through neural approaches equivalent to Word2Vec, and an example of this technique is the one presented in SensEmbed: Learning Sense Embeddings for Word and Relational Similarity, which is the reference paper for this homework assignment. The authors implement a Word2Vec model in the Continuous Bag of Words (CBOW) variant, for which a held-out word has to be predicted based on a context window. The aforementioned model is then trained on a corpus which is automatically annotated with BabelNet synsets representing word senses, being able to also exploit a large structured knowledge source additionally to raw text corpora.

Continue reading

nlp2019_hw2's People

Contributors

emanuelegiona avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.