paper-with-me

홈 › Papers

Context Vectors are Reflections of Word Vectors in Half the Dimensions

2019-02-26 · Zhenisbek Assylbekov, Rustem Takhanov

This paper takes a step towards theoretical analysis of the relationship between word embeddings and context embeddings in models such as word2vec. We start from basic probabilistic assumptions on the nature of word vectors, context vectors, and text generation. These assumptions are well supported either empirically or theoretically by the existing literature. Next, we show that under these assumptions the widely-used word-word PMI matrix is approximately a random symmetric Gaussian ensemble. This, in turn, implies that context vectors are reflections of word vectors in approximately half the dimensions. As a direct application of our result, we suggest a theoretically grounded way of tying weights in the SGNS model.

📄 PDF Abstract BibTeX arXiv:1902.09859

Code (0)

등록된 구현이 없습니다.

Tasks

Text GenerationWord Embeddings

Similar Papers 제목 키워드 기반

Causally Denoise Word Embeddings Using Half-Sibling Regression

2019-11-24 · Zekun Yang, Tianlin Liu

Distributional representations of words, also known as word vectors, have become crucial for modern natural language processing tasks due to their wide applications. Recently, a growing body of word vector postprocessing…

Causal InferenceregressionSentiment AnalysisWord Embeddings

Word and Document Embedding with vMF-Mixture Priors on Context Word Vectors

2019-07-01 · ACL 2019 7 · Shoaib Jameel, Steven Schockaert

Word embedding models typically learn two types of vectors: target word vectors and context word vectors. These vectors are normally learned such that they are predictive of some word co-occurrence statistic, but they ar…

Document Embedding

Learning Word Embeddings without Context Vectors

2019-08-01 · WS 2019 8 · Alexey Zobnin, Evgenia Elistratova

Most word embedding algorithms such as word2vec or fastText construct two sort of vectors: for words and for contexts. Naive use of vectors of only one sort leads to poor results. We suggest using indefinite inner produc…

Learning Word EmbeddingsWord EmbeddingsWord Similarity

A Rule-based/BPSO Approach to Produce Low-dimensional Semantic Basis Vectors Set

2021-11-24 · Atefe Pakzad, Morteza Analoui

We intend to generate low-dimensional explicit distributional semantic vectors. In explicit semantic vectors, each dimension corresponds to a word, so word vectors are interpretable. In this research, we propose a new ap…

Word Similarity

Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddings

2020-12-04 · Na Li, Zied Bouraoui, Jose Camacho Collados, Luis Espinosa-Anke 외

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to…

Knowledge Base Completion