Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing 2016
DOI: 10.18653/v1/d16-1063
|View full text |Cite
|
Sign up to set email alerts
|

WordRank: Learning Word Embeddings via Robust Ranking

Abstract: Embedding words in a vector space has gained a lot of attention in recent years. While stateof-the-art methods provide efficient computation of word similarities via a low-dimensional matrix embedding, their motivation is often left unclear. In this paper, we argue that word embedding can be naturally viewed as a ranking problem due to the ranking nature of the evaluation metrics. Then, based on this insight, we propose a novel framework WordRank that efficiently estimates word representations via robust ranki… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
10
0
2

Year Published

2018
2018
2020
2020

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 26 publications
(12 citation statements)
references
References 16 publications
0
10
0
2
Order By: Relevance
“…• CBOW-a [Chen et al, 2017]: a CBOW variant which adaptively sample negative words by ranking scores. • WordRank [Ji et al, 2015]: a ranking model that puts more weights on positive words by rank values. • OptRank: our ranking model with the optimization in both positive word ranking and negative word sampling.…”
Section: Comparison Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…• CBOW-a [Chen et al, 2017]: a CBOW variant which adaptively sample negative words by ranking scores. • WordRank [Ji et al, 2015]: a ranking model that puts more weights on positive words by rank values. • OptRank: our ranking model with the optimization in both positive word ranking and negative word sampling.…”
Section: Comparison Methodsmentioning
confidence: 99%
“…We set ε as 0.5 in five subsets and 1.0 in Wiki2017(14G). For the WordRank model, we adopt the settings given by [Ji et al, 2015]: logarithm as the objective function, initial value of scale parameter is α = 100 and offset parameter β = 99. The dimension of word vectors is also set to 300.…”
Section: Parameter Settingsmentioning
confidence: 99%
See 1 more Smart Citation
“…Das aktuellste Word-Embedding mit Namen BERT (1032 Zitationen), ist zum Zeitpunkt der Erstellung des Beitrages von keiner frei zugänglichen Bibliothek bereitgestellt worden und ist demnach nicht für ein Benchmarking geeignet. [10], [13], [16], [17], [18], [19], [20], [5], [6], [14] Abbildung…”
Section: Relevanz Verschiedener Word-embeddingsunclassified
“…In this subsection, we provide an intuitive example to explain the merits of popularity oversampling from ranking perspective. The reason is that training word embedding can also be naturally viewed as a ranking task that ranks an observed context word c P higher than any non-observed context word c N [14]. To illustrate this, we give a schematic of a ranked list for a target word w as below, where +1 and -1 denote an observed and non-observed context word respectively.…”
Section: Learning Optimal Ranking For Embeddingsmentioning
confidence: 99%