Word Embeddings

1096 papers with code • 0 benchmarks • 52 datasets

Word embedding is the collective name for a set of language modeling and feature learning techniques in natural language processing (NLP) where words or phrases from the vocabulary are mapped to vectors of real numbers.

Techniques for learning word embeddings can include Word2Vec, GloVe, and other neural network-based approaches that train on an NLP task such as language modeling or document classification.

( Image credit: Dynamic Word Embedding for Evolving Semantic Discovery )

Most implemented papers

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

julianser/hed-dlg-truncated 17 Jul 2015

We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models.

emoji2vec: Learning Emoji Representations from their Description

uclmr/emoji2vec WS 2016

Many current natural language processing applications for social media rely on representation learning and utilize pre-trained word embeddings.

Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

ofirpress/attention_with_linear_biases ICLR 2022

Since the introduction of the transformer model by Vaswani et al. (2017), a fundamental question has yet to be answered: how does a model achieve extrapolation at inference time for sequences that are longer than it saw during training?

ConceptNet 5.5: An Open Multilingual Graph of General Knowledge

commonsense/conceptnet-numberbatch 12 Dec 2016

It is designed to represent the general knowledge involved in understanding language, improving natural language applications by allowing the application to better understand the meanings behind the words people use.

BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs

lopezbec/COVID19_Tweets_Dataset SEMEVAL 2017

In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks.

Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks

UKPLab/emnlp2017-bilstm-cnn-crf 21 Jul 2017

Selecting optimal parameters for a neural network architecture can often make the difference between mediocre and state-of-the-art performance.

word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method

MLBurnham/word_embeddings 15 Feb 2014

The word2vec software of Tomas Mikolov and colleagues (https://code. google. com/p/word2vec/ ) has gained a lot of traction lately, and provides state-of-the-art word embeddings.

Document Embedding with Paragraph Vectors

inejc/paragraph-vectors 29 Jul 2015

Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts.

Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec

cemoody/lda2vec 6 May 2016

Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents.

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

epfml/sent2vec NAACL 2018

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i. e. semantic representations) of word sequences as well.