paper-with-me

Papers

Bayesian Neural Word Embedding

2016-03-21 · Oren Barkan

Recently, several works in the domain of natural language processing presented successful methods for word embedding. Among them, the Skip-Gram with negative sampling, known also as word2vec, advanced the state-of-the-art of various linguistics tasks. In this paper, we propose a scalable Bayesian neural word embedding algorithm. The algorithm relies on a Variational Bayes solution for the Skip-Gram objective and a detailed step by step description is provided. We present experimental results that demonstrate the performance of the proposed algorithm for word analogy and similarity tasks on six different datasets and show it is competitive with the original Skip-Gram method.

📄 PDF Abstract BibTeX arXiv:1603.06571

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation

2017-04-24 · Murathan Kurfali, Ahmet Üstün, Burcu Can

In this paper, we introduce a trie-structured Bayesian model for unsupervised morphological segmentation. We adopt prior information from different sources in the model. We use neural word embeddings to discover words th…

SegmentationWord Embeddings

Embedding Words as Distributions with a Bayesian Skip-gram Model

2017-11-29 · COLING 2018 8 · Arthur Bražinskas, Serhii Havrylov, Ivan Titov

We introduce a method for embedding words as probability densities in a low-dimensional space. Rather than assuming that a word embedding is fixed across the entire text collection, as in standard word embedding methods,…

A novel Bayesian estimation-based word embedding model for sentiment analysis

2019-09-25 · Jingyao Tang, Yun Xue, Ziwen Wang, Haoliang Zhao

The word embedding models have achieved state-of-the-art results in a variety of natural language processing tasks. Whereas, current word embedding models mainly focus on the rich semantic meanings while are challenged b…

Sentiment Analysis

Kernelized Bayesian Softmax for Text Generation

2019-11-01 · NeurIPS 2019 12 · Ning Miao, Hao Zhou, Chengqi Zhao, Wenxian Shi 외

Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase. Most existing approaches adopt single point embedding for each token. However, a word may have multiple se…

SentenceText Generation

A Bayesian approach to uncertainty in word embedding bias estimation

2023-06-15 · Alicja Dobrzeniecka, Rafal Urbaniak

Multiple measures, such as WEAT or MAC, attempt to quantify the magnitude of bias present in word embeddings in terms of a single-number metric. However, such metrics and the related statistical significance calculations…

Word Embeddings