paper-with-me

홈 › Papers

Understanding the Downstream Instability of Word Embeddings

2020-02-29 · Megan Leszczynski, Avner May, Jian Zhang, Sen Wu, Christopher R. Aberger, Christopher Ré

Many industrial machine learning (ML) systems require frequent retraining to keep up-to-date with constantly changing data. This retraining exacerbates a large challenge facing ML systems today: model training is unstable, i.e., small changes in training data can cause significant changes in the model's predictions. In this paper, we work on developing a deeper understanding of this instability, with a focus on how a core building block of modern natural language processing (NLP) pipelines---pre-trained word embeddings---affects the instability of downstream NLP models. We first empirically reveal a tradeoff between stability and memory: increasing the embedding memory 2x can reduce the disagreement in predictions due to small changes in training data by 5% to 37% (relative). To theoretically explain this tradeoff, we introduce a new measure of embedding instability---the eigenspace instability measure---which we prove bounds the disagreement in downstream predictions introduced by the change in word embeddings. Practically, we show that the eigenspace instability measure can be a cost-effective way to choose embedding parameters to minimize instability without training downstream models, outperforming other embedding distance measures and performing competitively with a nearest neighbor-based measure. Finally, we demonstrate that the observed stability-memory tradeoffs extend to other types of embeddings as well, including knowledge graph and contextual word embeddings.

📄 PDF Abstract BibTeX arXiv:2003.04983

Code (1)

HazyResearch/anchor-stability 공식 구현

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

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

Word Embeddings: Stability and Semantic Change

2020-07-23 · Lucas Rettenmeier

Word embeddings are computed by a class of techniques within natural language processing (NLP), that create continuous vector representations of words in a language from a large text corpus. The stochastic nature of the …

Word Embeddings

Learned in Speech Recognition: Contextual Acoustic Word Embeddings

2018-10-22 · Anonymous

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models m…

Sentencespeech-recognitionSpeech RecognitionSpoken Language Understanding+1

Learned In Speech Recognition: Contextual Acoustic Word Embeddings

2019-02-18 · Shruti Palaskar, Vikas Raunak, Florian Metze

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models m…

Sentencespeech-recognitionSpeech RecognitionSpoken Language Understanding+1

Investigating the Stability of Concrete Nouns in Word Embeddings

2019-05-01 · WS 2019 5 · B{\'e}n{\'e}dicte Pierrejean, Ludovic Tanguy

We know that word embeddings trained using neural-based methods (such as word2vec SGNS) are sensitive to stability problems and that across two models trained using the exact same set of parameters, the nearest neighbors…

Word Embeddings