Efficient Methods for Natural Language Processing: A Survey

被引：0

作者：

Treviso, Marcos ^{[1
]}

Lee, Ji-Ung ^{[2
]}

Ji, Tianchu ^{[3
]}

van Aken, Betty ^{[4
]}

Cao, Qingqing ^{[5
]}

Ciosici, Manuel R. ^{[6
]}

Hassid, Michael ^{[7
]}

Heafield, Kenneth ^{[8
]}

Hooker, Sara ^{[9
]}

Raffel, Colin ^{[10
]}

Martins, Pedro H. ^{[1
,11
]}

Martins, Andre F. T. ^{[1
,11
]}

Forde, Jessica Zosa ^{[12
]}

Milder, Peter ^{[16
]}

Simpson, Edwin ^{[13
]}

Slonim, Noam ^{[14
]}

Dodge, Jesse ^{[15
]}

Strubell, Emma ^{[15
,16
]}

Balasubramanian, Niranjan ^{[3
]}

Derczynski, Leon ^{[5
,17
]}

Gurevych, Iryna ^{[2
]}

Schwartz, Roy ^{[7
]}

机构：

[1] IST U Lisbon & Inst Telecomunicacoes, Lisbon, Portugal

[2] Tech Univ Darmstadt, Darmstadt, Germany

[3] SUNY Stony Brook, Stony Brook, NY USA

[4] Berliner Hsch Tech, Berlin, Germany

[5] Univ Washington, Washington, DC USA

[6] Univ Southern Calif, Los Angeles, CA USA

[7] Hebrew Univ Jerusalem, Jerusalem, Israel

[8] Univ Edinburgh, Edinburgh, Scotland

[9] Cohere AI, San Francisco, CA USA

[10] Univ North Carolina Chapel Hill, Chapel Hill, NC USA

[11] Unbabel, Lisbon, Portugal

[12] Brown Univ, Providence, RI USA

[13] Univ Bristol, Bristol, England

[14] IBM Res, Haifa, Israel

[15] Allen Inst AI, Seattle, WA USA

[16] Carnegie Mellon Univ, Pittsburgh, PA USA

[17] IT Univ Copenhagen, Copenhagen, Denmark

来源：

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS | 2023年 / 11卷

基金：

欧洲研究理事会;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows. Such resources include data, time, storage, or energy, all of which are naturally limited and unevenly distributed. This motivates research into efficient methods that require fewer resources to achieve similar results. This survey synthesizes and relates current methods and findings in efficient NLP. We aim to provide both guidance for conducting NLP under limited resources, and point towards promising research directions for developing more efficient methods.

引用

页码：826 / 860

页数：35

共 50 条

[1] Efficient Methods for Natural Language Processing: A Survey
Treviso, Marcos
Ji, Tianchu
Lee, Ji-Ung
van Aken, Betty
Cao, Qingqing
R. Ciosici, Manuel
Hassid, Michael
Heafield, Kenneth
Hooker, Sara
H. Martins, Pedro
F. T. Martins, Andre
Milder, Peter
Raffel, Colin
Simpson, Edwin
Slonim, Noam
Dodge, Jesse
Strubell, Emma
Balasubramanian, Niranjan
Derczynski, Leon
Gurevych, Iryna
Schwartz, Roy
[J]. TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2023, 11 (826-860) : 826 - 860
[2] A survey of graphs in natural language processing
Nastase, Vivi
Mihalcea, Rada
Radev, Dragomir R.
[J]. NATURAL LANGUAGE ENGINEERING, 2015, 21 (05) : 665 - 698
[3] Natural language processing in finance: A survey
Du, Kelvin
Zhao, Yazhi
Mao, Rui
Xing, Frank
Cambria, Erik
[J]. Information Fusion, 2025, 115
[4] Quantum Natural Language Processing: A Comprehensive Survey
Varmantchaonala, Charles M.
Fendji, Jean Louis K. E.
Schoning, Julius
Atemkeng, Marcellin
[J]. IEEE ACCESS, 2024, 12 : 99578 - 99598
[5] Perspectivist approaches to natural language processing: a survey
Frenda, Simona
Abercrombie, Gavin
Basile, Valerio
Pedrani, Alessandro
Panizzon, Raffaella
Cignarella, Alessandra Teresa
Marco, Cristina
Bernardi, Davide
[J]. LANGUAGE RESOURCES AND EVALUATION, 2024,
[6] Survey of Natural Language Processing Techniques in Bioinformatics
Zeng, Zhiqiang
Shi, Hua
Wu, Yun
Hong, Zhiling
[J]. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2015, 2015
[7] Deep Learning for Natural Language Processing: A Survey
Arkhangelskaya E.O.
Nikolenko S.I.
[J]. Journal of Mathematical Sciences, 2023, 273 (4) : 533 - 582
[8] Meta Learning for Natural Language Processing: A Survey
Lee, Hung-yi
Li, Shang-Wen
Vu, Ngoc Thang
[J]. NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 666 - 684
[9] Synergizing machine learning & symbolic methods: A survey on hybrid approaches to natural language processing
Panchendrarajan, Rrubaa
Zubiaga, Arkaitz
[J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 251
[10] Graph-Based Methods for Natural Language Processing and Understanding-A Survey and Analysis
Mills, Michael T.
Bourbakis, Nikolaos G.
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2014, 44 (01): : 59 - 71

← 1 2 3 4 5 →