Improving fast_align by Reordering Article Swipe

PDF

Chenchen Ding , Masao Utiyama , Eiichiro Sumita ·

YOU? · · 2015 · Open Access · · DOI: https://doi.org/10.18653/v1/d15-1119

fast align is a simple, fast, and efficient approach for word alignment based on the IBM model 2. fast align performs well for language pairs with relatively similar word orders; however, it does not perform well for language pairs with drastically different word orders.We propose a segmenting-reversing reordering process to solve this problem by alternately applying fast align and reordering source sentences during training.Experimental results with Japanese-English translation demonstrate that the proposed approach improves the performance of fast align significantly without the loss of efficiency.Experiments using other languages are also reported.

Related Topics

Computer Science

Ibm

Process (Computing)

Artificial Intelligence

Concepts

Computer science Word (group theory) IBM Simple (philosophy) Process (computing) Translation (biology) Artificial intelligence Parallel computing Natural language processing Speech recognition Machine translation Algorithm Programming language Linguistics Gene Messenger RNA Materials science Chemistry Philosophy Epistemology Biochemistry Nanotechnology

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.18653/v1/d15-1119
PDF: https://www.aclweb.org/anthology/D15-1119.pdf
OA Status: gold
Cited By: 6
References: 20
Related Works: 10
OpenAlex ID: https://openalex.org/W2251606747

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W2251606747

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.18653/v1/d15-1119

Digital Object Identifier
Title: Improving fast_align by Reordering

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2015

Year of publication
Publication date: 2015-01-01

Full publication date if available
Authors: Chenchen Ding, Masao Utiyama, Eiichiro Sumita

List of authors in order
Landing page: https://doi.org/10.18653/v1/d15-1119

Publisher landing page
PDF URL: https://www.aclweb.org/anthology/D15-1119.pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://www.aclweb.org/anthology/D15-1119.pdf

Direct OA link when available
Concepts: Computer science, Word (group theory), IBM, Simple (philosophy), Process (computing), Translation (biology), Artificial intelligence, Parallel computing, Natural language processing, Speech recognition, Machine translation, Algorithm, Programming language, Linguistics, Gene, Messenger RNA, Materials science, Chemistry, Philosophy, Epistemology, Biochemistry, Nanotechnology

Top concepts (fields/topics) attached by OpenAlex
Cited by: 6

Total citation count in OpenAlex
Citations by year (recent): 2020: 1, 2019: 1, 2017: 1, 2016: 2, 2015: 1

Per-year citation counts (last 5 years)
References (count): 20

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W2251606747
doi	https://doi.org/10.18653/v1/d15-1119
ids.doi	https://doi.org/10.18653/v1/d15-1119
ids.mag	2251606747
ids.openalex	https://openalex.org/W2251606747
fwci	1.25720366
type	article
title	Improving fast_align by Reordering
biblio.issue
biblio.volume
biblio.last_page	1039
biblio.first_page	1034
topics[0].id	https://openalex.org/T10181
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	1.0
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Natural Language Processing Techniques
topics[1].id	https://openalex.org/T10028
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9998000264167786
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Topic Modeling
topics[2].id	https://openalex.org/T12031
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9925000071525574
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Speech and dialogue systems
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.8686754107475281
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C90805587
concepts[1].level	2
concepts[1].score	0.715682327747345
concepts[1].wikidata	https://www.wikidata.org/wiki/Q10944557
concepts[1].display_name	Word (group theory)
concepts[2].id	https://openalex.org/C70388272
concepts[2].level	2
concepts[2].score	0.6937659978866577
concepts[2].wikidata	https://www.wikidata.org/wiki/Q5968558
concepts[2].display_name	IBM
concepts[3].id	https://openalex.org/C2780586882
concepts[3].level	2
concepts[3].score	0.5535696148872375
concepts[3].wikidata	https://www.wikidata.org/wiki/Q7520643
concepts[3].display_name	Simple (philosophy)
concepts[4].id	https://openalex.org/C98045186
concepts[4].level	2
concepts[4].score	0.5343913435935974
concepts[4].wikidata	https://www.wikidata.org/wiki/Q205663
concepts[4].display_name	Process (computing)
concepts[5].id	https://openalex.org/C149364088
concepts[5].level	4
concepts[5].score	0.5214899778366089
concepts[5].wikidata	https://www.wikidata.org/wiki/Q185917
concepts[5].display_name	Translation (biology)
concepts[6].id	https://openalex.org/C154945302
concepts[6].level	1
concepts[6].score	0.46256810426712036
concepts[6].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[6].display_name	Artificial intelligence
concepts[7].id	https://openalex.org/C173608175
concepts[7].level	1
concepts[7].score	0.46235689520835876
concepts[7].wikidata	https://www.wikidata.org/wiki/Q232661
concepts[7].display_name	Parallel computing
concepts[8].id	https://openalex.org/C204321447
concepts[8].level	1
concepts[8].score	0.4593534469604492
concepts[8].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[8].display_name	Natural language processing
concepts[9].id	https://openalex.org/C28490314
concepts[9].level	1
concepts[9].score	0.42008838057518005
concepts[9].wikidata	https://www.wikidata.org/wiki/Q189436
concepts[9].display_name	Speech recognition
concepts[10].id	https://openalex.org/C203005215
concepts[10].level	2
concepts[10].score	0.41000470519065857
concepts[10].wikidata	https://www.wikidata.org/wiki/Q79798
concepts[10].display_name	Machine translation
concepts[11].id	https://openalex.org/C11413529
concepts[11].level	1
concepts[11].score	0.33219659328460693
concepts[11].wikidata	https://www.wikidata.org/wiki/Q8366
concepts[11].display_name	Algorithm
concepts[12].id	https://openalex.org/C199360897
concepts[12].level	1
concepts[12].score	0.27285099029541016
concepts[12].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[12].display_name	Programming language
concepts[13].id	https://openalex.org/C41895202
concepts[13].level	1
concepts[13].score	0.0
concepts[13].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[13].display_name	Linguistics
concepts[14].id	https://openalex.org/C104317684
concepts[14].level	2
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q7187
concepts[14].display_name	Gene
concepts[15].id	https://openalex.org/C105580179
concepts[15].level	3
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q188928
concepts[15].display_name	Messenger RNA
concepts[16].id	https://openalex.org/C192562407
concepts[16].level	0
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q228736
concepts[16].display_name	Materials science
concepts[17].id	https://openalex.org/C185592680
concepts[17].level	0
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q2329
concepts[17].display_name	Chemistry
concepts[18].id	https://openalex.org/C138885662
concepts[18].level	0
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[18].display_name	Philosophy
concepts[19].id	https://openalex.org/C111472728
concepts[19].level	1
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q9471
concepts[19].display_name	Epistemology
concepts[20].id	https://openalex.org/C55493867
concepts[20].level	1
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q7094
concepts[20].display_name	Biochemistry
concepts[21].id	https://openalex.org/C171250308
concepts[21].level	1
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q11468
concepts[21].display_name	Nanotechnology
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.8686754107475281
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/word
keywords[1].score	0.715682327747345
keywords[1].display_name	Word (group theory)
keywords[2].id	https://openalex.org/keywords/ibm
keywords[2].score	0.6937659978866577
keywords[2].display_name	IBM
keywords[3].id	https://openalex.org/keywords/simple
keywords[3].score	0.5535696148872375
keywords[3].display_name	Simple (philosophy)
keywords[4].id	https://openalex.org/keywords/process
keywords[4].score	0.5343913435935974
keywords[4].display_name	Process (computing)
keywords[5].id	https://openalex.org/keywords/translation
keywords[5].score	0.5214899778366089
keywords[5].display_name	Translation (biology)
keywords[6].id	https://openalex.org/keywords/artificial-intelligence
keywords[6].score	0.46256810426712036
keywords[6].display_name	Artificial intelligence
keywords[7].id	https://openalex.org/keywords/parallel-computing
keywords[7].score	0.46235689520835876
keywords[7].display_name	Parallel computing
keywords[8].id	https://openalex.org/keywords/natural-language-processing
keywords[8].score	0.4593534469604492
keywords[8].display_name	Natural language processing
keywords[9].id	https://openalex.org/keywords/speech-recognition
keywords[9].score	0.42008838057518005
keywords[9].display_name	Speech recognition
keywords[10].id	https://openalex.org/keywords/machine-translation
keywords[10].score	0.41000470519065857
keywords[10].display_name	Machine translation
keywords[11].id	https://openalex.org/keywords/algorithm
keywords[11].score	0.33219659328460693
keywords[11].display_name	Algorithm
keywords[12].id	https://openalex.org/keywords/programming-language
keywords[12].score	0.27285099029541016
keywords[12].display_name	Programming language
language	en
locations[0].id	doi:10.18653/v1/d15-1119
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by
locations[0].pdf_url	https://www.aclweb.org/anthology/D15-1119.pdf
locations[0].version	publishedVersion
locations[0].raw_type	proceedings-article
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
locations[0].landing_page_url	https://doi.org/10.18653/v1/d15-1119
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5001889488
authorships[0].author.orcid	https://orcid.org/0000-0002-7523-208X
authorships[0].author.display_name	Chenchen Ding
authorships[0].countries	JP
authorships[0].affiliations[0].institution_ids	https://openalex.org/I90023481
authorships[0].affiliations[0].raw_affiliation_string	Multilingual Translation Laboratory National Institute of Information and Communications Technology 3-5 Hikaridai, Seikacho, Sorakugun, Kyoto, 619-0289, Japan
authorships[0].institutions[0].id	https://openalex.org/I90023481
authorships[0].institutions[0].ror	https://ror.org/016bgq349
authorships[0].institutions[0].type	facility
authorships[0].institutions[0].lineage	https://openalex.org/I90023481
authorships[0].institutions[0].country_code	JP
authorships[0].institutions[0].display_name	National Institute of Information and Communications Technology
authorships[0].author_position	first
authorships[0].raw_author_name	Chenchen Ding
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	Multilingual Translation Laboratory National Institute of Information and Communications Technology 3-5 Hikaridai, Seikacho, Sorakugun, Kyoto, 619-0289, Japan
authorships[1].author.id	https://openalex.org/A5021667085
authorships[1].author.orcid	https://orcid.org/0000-0003-1111-9245
authorships[1].author.display_name	Masao Utiyama
authorships[1].countries	JP
authorships[1].affiliations[0].institution_ids	https://openalex.org/I90023481
authorships[1].affiliations[0].raw_affiliation_string	Multilingual Translation Laboratory National Institute of Information and Communications Technology 3-5 Hikaridai, Seikacho, Sorakugun, Kyoto, 619-0289, Japan
authorships[1].institutions[0].id	https://openalex.org/I90023481
authorships[1].institutions[0].ror	https://ror.org/016bgq349
authorships[1].institutions[0].type	facility
authorships[1].institutions[0].lineage	https://openalex.org/I90023481
authorships[1].institutions[0].country_code	JP
authorships[1].institutions[0].display_name	National Institute of Information and Communications Technology
authorships[1].author_position	middle
authorships[1].raw_author_name	Masao Utiyama
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	Multilingual Translation Laboratory National Institute of Information and Communications Technology 3-5 Hikaridai, Seikacho, Sorakugun, Kyoto, 619-0289, Japan
authorships[2].author.id	https://openalex.org/A5033318800
authorships[2].author.orcid	https://orcid.org/0000-0002-1028-4399
authorships[2].author.display_name	Eiichiro Sumita
authorships[2].countries	JP
authorships[2].affiliations[0].institution_ids	https://openalex.org/I90023481
authorships[2].affiliations[0].raw_affiliation_string	Multilingual Translation Laboratory National Institute of Information and Communications Technology 3-5 Hikaridai, Seikacho, Sorakugun, Kyoto, 619-0289, Japan
authorships[2].institutions[0].id	https://openalex.org/I90023481
authorships[2].institutions[0].ror	https://ror.org/016bgq349
authorships[2].institutions[0].type	facility
authorships[2].institutions[0].lineage	https://openalex.org/I90023481
authorships[2].institutions[0].country_code	JP
authorships[2].institutions[0].display_name	National Institute of Information and Communications Technology
authorships[2].author_position	last
authorships[2].raw_author_name	Eiichiro Sumita
authorships[2].is_corresponding	False
authorships[2].raw_affiliation_strings	Multilingual Translation Laboratory National Institute of Information and Communications Technology 3-5 Hikaridai, Seikacho, Sorakugun, Kyoto, 619-0289, Japan
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://www.aclweb.org/anthology/D15-1119.pdf
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Improving fast_align by Reordering
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T10181
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	1.0
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Natural Language Processing Techniques
related_works	https://openalex.org/W3126131865, https://openalex.org/W4253186488, https://openalex.org/W2044344400, https://openalex.org/W1996938127, https://openalex.org/W2083611981, https://openalex.org/W2072507639, https://openalex.org/W4231814374, https://openalex.org/W2155964760, https://openalex.org/W2883671469, https://openalex.org/W2728761353
cited_by_count	6
counts_by_year[0].year	2020
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2019
counts_by_year[1].cited_by_count	1
counts_by_year[2].year	2017
counts_by_year[2].cited_by_count	1
counts_by_year[3].year	2016
counts_by_year[3].cited_by_count	2
counts_by_year[4].year	2015
counts_by_year[4].cited_by_count	1
locations_count	1
best_oa_location.id	doi:10.18653/v1/d15-1119
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://www.aclweb.org/anthology/D15-1119.pdf
best_oa_location.version	publishedVersion
best_oa_location.raw_type	proceedings-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
best_oa_location.landing_page_url	https://doi.org/10.18653/v1/d15-1119
primary_location.id	doi:10.18653/v1/d15-1119
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by
primary_location.pdf_url	https://www.aclweb.org/anthology/D15-1119.pdf
primary_location.version	publishedVersion
primary_location.raw_type	proceedings-article
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
primary_location.landing_page_url	https://doi.org/10.18653/v1/d15-1119
publication_date	2015-01-01
publication_year	2015
referenced_works	https://openalex.org/W2155607551, https://openalex.org/W1990174463, https://openalex.org/W4241645538, https://openalex.org/W2133444727, https://openalex.org/W2595715041, https://openalex.org/W2156985047, https://openalex.org/W2146574666, https://openalex.org/W2124807415, https://openalex.org/W2148708890, https://openalex.org/W2153653739, https://openalex.org/W2152803722, https://openalex.org/W22168010, https://openalex.org/W2101105183, https://openalex.org/W2294953265, https://openalex.org/W2250307129, https://openalex.org/W2437005631, https://openalex.org/W1528441900, https://openalex.org/W2112900913, https://openalex.org/W222053410, https://openalex.org/W224499596
referenced_works_count	20
abstract_inverted_index.a	3, 45
abstract_inverted_index.2.	17
abstract_inverted_index.by	53
abstract_inverted_index.is	2
abstract_inverted_index.it	31
abstract_inverted_index.of	76, 83
abstract_inverted_index.on	13
abstract_inverted_index.to	49
abstract_inverted_index.IBM	15
abstract_inverted_index.and	6, 58
abstract_inverted_index.are	88
abstract_inverted_index.for	9, 22, 36
abstract_inverted_index.not	33
abstract_inverted_index.the	14, 70, 74, 81
abstract_inverted_index.also	89
abstract_inverted_index.does	32
abstract_inverted_index.fast	0, 18, 56, 77
abstract_inverted_index.loss	82
abstract_inverted_index.that	69
abstract_inverted_index.this	51
abstract_inverted_index.well	21, 35
abstract_inverted_index.with	25, 39, 65
abstract_inverted_index.word	10, 28, 42
abstract_inverted_index.align	1, 19, 57, 78
abstract_inverted_index.based	12
abstract_inverted_index.fast,	5
abstract_inverted_index.model	16
abstract_inverted_index.other	86
abstract_inverted_index.pairs	24, 38
abstract_inverted_index.solve	50
abstract_inverted_index.using	85
abstract_inverted_index.during	62
abstract_inverted_index.source	60
abstract_inverted_index.orders;	29
abstract_inverted_index.perform	34
abstract_inverted_index.problem	52
abstract_inverted_index.process	48
abstract_inverted_index.propose	44
abstract_inverted_index.results	64
abstract_inverted_index.similar	27
abstract_inverted_index.simple,	4
abstract_inverted_index.without	80
abstract_inverted_index.applying	55
abstract_inverted_index.approach	8, 72
abstract_inverted_index.however,	30
abstract_inverted_index.improves	73
abstract_inverted_index.language	23, 37
abstract_inverted_index.performs	20
abstract_inverted_index.proposed	71
abstract_inverted_index.alignment	11
abstract_inverted_index.different	41
abstract_inverted_index.efficient	7
abstract_inverted_index.languages	87
abstract_inverted_index.orders.We	43
abstract_inverted_index.reported.	90
abstract_inverted_index.sentences	61
abstract_inverted_index.relatively	26
abstract_inverted_index.reordering	47, 59
abstract_inverted_index.alternately	54
abstract_inverted_index.demonstrate	68
abstract_inverted_index.drastically	40
abstract_inverted_index.performance	75
abstract_inverted_index.translation	67
abstract_inverted_index.significantly	79
abstract_inverted_index.Japanese-English	66
abstract_inverted_index.segmenting-reversing	46
abstract_inverted_index.training.Experimental	63
abstract_inverted_index.efficiency.Experiments	84
cited_by_percentile_year.max	96
cited_by_percentile_year.min	89
countries_distinct_count	1
institutions_distinct_count	3
sustainable_development_goals[0].id	https://metadata.un.org/sdg/4
sustainable_development_goals[0].score	0.6299999952316284
sustainable_development_goals[0].display_name	Quality Education
citation_normalized_percentile.value	0.90459627
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False