paper-with-me

Papers

Are Word Embedding Methods Stable and Should We Care About It?

2021-04-17 · Angana Borah, Manash Pratim Barman, Amit Awekar

A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs. Word Embedding Methods (WEMs) are a class of representation learning methods that generate dense vector representation for each word in the given text data. The central idea of this paper is to explore the stability measurement of WEMs using intrinsic evaluation based on word similarity. We experiment with three popular WEMs: Word2Vec, GloVe, and fastText. For stability measurement, we investigate the effect of five parameters involved in training these models. We perform experiments using four real-world datasets from different domains: Wikipedia, News, Song lyrics, and European parliament proceedings. We also observe the effect of WEM stability on three downstream tasks: Clustering, POS tagging, and Fairness evaluation. Our experiments indicate that amongst the three WEMs, fastText is the most stable, followed by GloVe and Word2Vec.

📄 PDF Abstract BibTeX arXiv:2104.08433

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringFairnessPOSPOS TaggingRepresentation LearningWord Similarity

Methods 이 논문이 사용한 방법론

GloVe GloVe Embeddings are a type of word embedding that encode the co-occurrence probability ratio between two words as vector differences. GloVe uses a weighted least squares…
fastText fastText embeddings exploit subword information to construct word embeddings. Representations are learnt of character $n$-grams, and words represented as the sum of the…

Similar Papers 제목 키워드 기반

Poincare Glove: Hyperbolic Word Embeddings

2019-05-01 · ICLR 2019 5 · Alexandru Tifrea*, Gary Becigneul*, Octavian-Eugen Ganea*

Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical structure that the next generation of unsupervised learned word embeddings should reveal. In this paper, justified by the n…

Learning Word EmbeddingsWord Embeddings

Old Optimizer, New Norm: An Anthology

2024-09-30 · Jeremy Bernstein, Laker Newhouse

Deep learning optimizers are often motivated through a mix of convex and approximate second-order theory. We select three such methods -- Adam, Shampoo and Prodigy -- and argue that each method can instead be understood …

Twitter Sentiment on Affordable Care Act using Score Embedding

2019-08-19 · Mohsen Farhadloo

In this paper we introduce score embedding, a neural network based model to learn interpretable vector representations for words. Score embedding is a supervised method that takes advantage of the labeled training data a…

Factors Influencing the Surprising Instability of Word Embeddings

2018-04-25 · NAACL 2018 6 · Laura Wendlandt, Jonathan K. Kummerfeld, Rada Mihalcea

Despite the recent popularity of word embedding methods, there is only a small body of work exploring the limitations of these representations. In this paper, we consider one aspect of embedding spaces, namely their stab…

Word Embeddings

A Robust Classification Method using Hybrid Word Embedding for Early Diagnosis of Alzheimer's Disease

2025-10-16 · Yangyang Li arxiv

Early detection of Alzheimer's Disease (AD) is greatly beneficial to AD patients, leading to early treatments that lessen symptoms and alleviating financial burden of health care. As one of the leading signs of AD, langu…