No Training Required: Exploring Random Encoders for Sentence Classification

01/29/2019
by   John Wieting, et al.
0

We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i.e., using nothing but random parameterizations. Our aim is to put sentence embeddings on more solid footing by 1) looking at how much modern sentence embeddings gain over random methods---as it turns out, surprisingly little; and by 2) providing the field with more appropriate baselines going forward---which are, as it turns out, quite strong. We also make important observations about proper experimental protocol for sentence classification evaluation, together with recommendations for future research.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2016

Word Embeddings and Their Use In Sentence Classification Tasks

This paper have two parts. In the first part we discuss word embeddings....
research
06/15/2016

Siamese CBOW: Optimizing Word Embeddings for Sentence Representations

We present the Siamese Continuous Bag of Words (Siamese CBOW) model, a n...
research
10/25/2019

Evaluation of Sentence Representations in Polish

Methods for learning sentence representations have been actively develop...
research
04/28/2023

Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?

Dense vector representations for textual data are crucial in modern NLP....
research
06/04/2019

Pitfalls in the Evaluation of Sentence Embeddings

Deep learning models continuously break new records across different NLP...
research
06/09/2016

Sentence Similarity Measures for Fine-Grained Estimation of Topical Relevance in Learner Essays

We investigate the task of assessing sentence-level prompt relevance in ...

Please sign up or login with your details

Forgot password? Click here to reset