paper-with-me

Papers

Autoencoding Improves Pre-trained Word Embeddings

2020-10-25 · COLING 2020 8 · Masahiro Kaneko, Danushka Bollegala

Prior work investigating the geometry of pre-trained word embeddings have shown that word embeddings to be distributed in a narrow cone and by centering and projecting using principal component vectors one can increase the accuracy of a given set of pre-trained word embeddings. However, theoretically, this post-processing step is equivalent to applying a linear autoencoder to minimise the squared l2 reconstruction error. This result contradicts prior work (Mu and Viswanath, 2018) that proposed to remove the top principal components from pre-trained embeddings. We experimentally verify our theoretical claims and show that retaining the top principal components is indeed useful for improving pre-trained word embeddings, without requiring access to additional linguistic resources or labelled data.

📄 PDF Abstract BibTeX arXiv:2010.13094

Code (0)

등록된 구현이 없습니다.

Tasks

Word Embeddings

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Learning Word Meta-Embeddings by Autoencoding

2018-08-01 · COLING 2018 8 · Danushka Bollegala, Cong Bao

Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different tasks, implying that the word embeddings l…

Dependency ParsingMachine TranslationPart-Of-Speech TaggingSentiment Analysis+1

MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding

2019-08-01 · WS 2019 8 · Nils Rethmeier, Barbara Plank

Word embeddings have undoubtedly revolutionized NLP. However, pretrained embeddings do not always work for a specific task (or set of tasks), particularly in limited resource setups. We introduce a simple yet effective, …

Word Embeddings

Structured Neural Topic Models for Reviews

2018-12-12 · Babak Esmaeili, Hongyi Huang, Byron C. Wallace, Jan-Willem van de Meent

We present Variational Aspect-based Latent Topic Allocation (VALTA), a family of autoencoding topic models that learn aspect-based representations of reviews. VALTA defines a user-item encoder that maps bag-of-words vect…

SentenceTopic Models

Named Entity Recognition Only from Word Embeddings

2019-08-31 · EMNLP 2020 11 · Ying Luo, Hai Zhao, Junlang Zhan

Deep neural network models have helped named entity (NE) recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts ha…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Reinforcement Learning+2

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,…