En-Ar Bilingual word Embeddings without Word Alignment: Factors Effects

Simon O'Keefe; Taghreed Alqaisi

En-Ar Bilingual word Embeddings without Word Alignment: Factors Effects

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper introduces the first attempt to investigate morphological segmentation on En-Ar bilingual word embeddings using bilingual word embeddings model without word alignment (BilBOWA). We investigate the effect of sentence length and embedding size on the learning process. Our experiment shows that using the D3 segmentation scheme improves the accuracy of learning bilingual word embeddings up to 10 percentage points compared to the ATB and D0 schemes in all different training settings.

Original language	English
Pages	97-107
Number of pages	11
Publication status	Published - 2019

Bibliographical note

Access to Document

W19-4611
© 2019 Association for Computational Linguistics. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Final published version, 446 KB

Cite this

@conference{728e5136151f4f52b22099f74d4457ba,

title = "En-Ar Bilingual word Embeddings without Word Alignment: Factors Effects",

abstract = "This paper introduces the first attempt to investigate morphological segmentation on En-Ar bilingual word embeddings using bilingual word embeddings model without word alignment (BilBOWA). We investigate the effect of sentence length and embedding size on the learning process. Our experiment shows that using the D3 segmentation scheme improves the accuracy of learning bilingual word embeddings up to 10 percentage points compared to the ATB and D0 schemes in all different training settings.",

author = "Simon O'Keefe and Taghreed Alqaisi",

note = "{\textcopyright} 2019 Association for Computational Linguistics. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details ",

year = "2019",

language = "English",

pages = "97--107",

}

TY - CONF

T1 - En-Ar Bilingual word Embeddings without Word Alignment

T2 - Factors Effects

AU - O'Keefe, Simon

AU - Alqaisi, Taghreed

PY - 2019

Y1 - 2019

N2 - This paper introduces the first attempt to investigate morphological segmentation on En-Ar bilingual word embeddings using bilingual word embeddings model without word alignment (BilBOWA). We investigate the effect of sentence length and embedding size on the learning process. Our experiment shows that using the D3 segmentation scheme improves the accuracy of learning bilingual word embeddings up to 10 percentage points compared to the ATB and D0 schemes in all different training settings.

AB - This paper introduces the first attempt to investigate morphological segmentation on En-Ar bilingual word embeddings using bilingual word embeddings model without word alignment (BilBOWA). We investigate the effect of sentence length and embedding size on the learning process. Our experiment shows that using the D3 segmentation scheme improves the accuracy of learning bilingual word embeddings up to 10 percentage points compared to the ATB and D0 schemes in all different training settings.

M3 - Paper

SP - 97

EP - 107

ER -