paper-with-me

Papers

Towards Lower Bounds on Number of Dimensions for Word Embeddings

2017-11-01 · IJCNLP 2017 11 · Kevin Patel, Pushpak Bhattacharyya

Word embeddings are a relatively new addition to the modern NLP researcher{'}s toolkit. However, unlike other tools, word embeddings are used in a black box manner. There are very few studies regarding various hyperparameters. One such hyperparameter is the dimension of word embeddings. They are rather decided based on a rule of thumb: in the range 50 to 300. In this paper, we show that the dimension should instead be chosen based on corpus statistics. More specifically, we show that the number of pairwise equidistant words of the corpus vocabulary (as defined by some distance/similarity metric) gives a lower bound on the the number of dimensions , and going below this bound results in degradation of quality of learned word embeddings. Through our evaluations on standard word embedding evaluation tasks, we show that for dimensions higher than or equal to the bound, we get better results as compared to the ones below it.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Named Entity Recognition (NER)Part-Of-Speech TaggingSarcasm DetectionSentence ClassificationSentiment AnalysisWord Embeddings

Similar Papers 제목 키워드 기반

Compact Geometric Representations of Hierarchies

2026-06-16 · Prashant Gokhale, Piotr Indyk, Yuhao Liu, Sandeep Silwal 외 arxiv

Computing geometric representations of data is a cornerstone of modern machine learning, typically achieved by training dual encoders which map queries and documents into a shared embedding space. Recent work of You et a…

Embeddings and labeling schemes for A*

2021-11-19 · Talya Eden, Piotr Indyk, Haike Xu

A* is a classic and popular method for graphs search and path finding. It assumes the existence of a heuristic function $h(u,t)$ that estimates the shortest distance from any input node $u$ to the destination $t$. Tradit…

A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity

2025-09-24 · Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin arxiv

We study gapped scale-sensitive dimensions of a function class in both sequential and non-sequential settings. We demonstrate that covering numbers for any uniformly bounded class are controlled above by these gapped dim…

Binary Encoded Word Mover’s Distance

2022-05-01 · RepL4NLP (ACL) 2022 5 · Christian Johnson

Word Mover’s Distance is a textual distance metric which calculates the minimum transport cost between two sets of word embeddings. This metric achieves impressive results on semantic similarity tasks, but is slow and di…

Semantic SimilaritySemantic Textual SimilarityWord Embeddings

Representation Tradeoffs for Hyperbolic Embeddings

2018-04-10 · ICML 2018 7 · Christopher De Sa, Albert Gu, Christopher Ré, Frederic Sala

Hyperbolic embeddings offer excellent quality with few dimensions when embedding hierarchical data structures like synonym or type hierarchies. Given a tree, we give a combinatorial construction that embeds the tree in h…