Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
文献紹介:語彙の概念化と Wikipediaを用いた英字略語の意味推定方法
Search
Atsushi
July 26, 2018
160
0
Share
文献紹介:語彙の概念化と Wikipediaを用いた英字略語の意味推定方法
2018年7月26日 文献紹介
長岡技術科学大学
自然言語処理研究室
Atsushi
July 26, 2018
More Decks by Atsushi
See All by Atsushi
文献紹介:Automated Evaluation of Out-of-Context Errors
atsumikan
0
100
文献紹介:Correction of OCR Word Segmentation Errors in Articles from the ACL Collection through Neural Machine Translation Methods
atsumikan
0
170
文献紹介:Auxiliary Objectives for Neural Error Detection Models
atsumikan
0
97
文献紹介:Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection
atsumikan
0
130
文献紹介:Low-resource OCR error detection and correction in French Clinical Texts
atsumikan
0
130
文献紹介:CMMC-BDRC Solution to the NLP-TEA-2018 Chinese Grammatical Error Diagnosis Task
atsumikan
0
140
文献紹介 : Fluency Boost Learning and Inference for Neural Grammatical Error Correction
atsumikan
0
190
文献紹介:The Effect of Error Rate in Artificially Generated Data for Automatic Preposition and Determiner Correction
atsumikan
0
140
文献紹介: Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction
atsumikan
0
180
Featured
See All Featured
Building Applications with DynamoDB
mza
96
7k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
2.8k
A designer walks into a library…
pauljervisheath
211
24k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
21
1.4k
Heart Work Chapter 1 - Part 1
lfama
PRO
5
35k
Measuring Dark Social's Impact On Conversion and Attribution
stephenakadiri
1
180
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.2k
Max Prin - Stacking Signals: How International SEO Comes Together (And Falls Apart)
techseoconnect
PRO
0
140
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
37
6.3k
A Soul's Torment
seathinner
6
2.6k
Building Experiences: Design Systems, User Experience, and Full Site Editing
marktimemedia
0
480
Designing Experiences People Love
moore
143
24k
Transcript
ޠኮͷ֓೦Խͱ8JLJQFEJBΛ༻͍ͨ ӳࣈུޠͷҙຯਪఆํ๏ Ԭٕज़Պֶେֶࣗવݴޠॲཧݚڀࣨ ੁ३ࢤ จݙհ ݄ ࣗવݴޠॲཧ7PM/P ࣗવݴޠॲཧ 7PM/PQQ ޙ౻ਓ
࢘ ෦Ұ
֓ཁ w ӳࣈུޠͷଟٛੑΛղফͨ͠ҙຯਪఆ w ใͷܽΛ8JLJQFEJBͷใΛ༻͍ͯิ w ݅ͷ৽ฉهࣄʹର͠ ࠷ߴͰ͍ۙਖ਼Λࣔ͢
ఏҊख๏
֓೦ϕʔε w ෳͷిࢠԽࠃޠࣙॻͳͲͷݟग़͠ޠΛ֓೦ͱ͠ɺͦͷޠٛจʹ༻ ͞Ε͍ͯΔཱࣗޠΛ֓೦ͷҙຯಛΛද͢ଐੑͱఆٛͯ͠ߏங͞Εͨ େنͳσʔλϕʔε w ଐੑͰ͋Δ୯ޠ֓೦ͱͯ͠ඞͣఆٛ͞Ε͍ͯΔͱ͍͏ ಛΛ࣋ͭ
ະఆٛޠͷ֓೦Խ w 8FC্ͷݴޠใΛར༻͠ɼࣗಈతʹ֓೦Խ͢Δ ⁋ɼ෦ɼՏԬޙ౻ɼɼ෦ɼՏԬ w ཱࣗޠΛ֓೦ͱͯ͠நग़͢Δ w Ұ࣍ଐੑʹର͢ΔॏΈɺUGɾJEGͷԠ༻Ͱࢉग़͢Δ
8JLJQFEJBʹΑΔҙຯީิͷݕࡧ w ҙຯͷ֓೦Խॲཧʹ͓͚ΔϊΠζΛআڈ w ӳࣈུޠͰͳ͍ΞϧϑΝϕοτͷཏྻΛআ
࣮ݧ݅ w ೖྗจষ w શࠃࢴϲ݄ͷهࣄ͔Βҙຯͷ͋ΔӳࣈུޠΛؚΉهࣄΛແ࡞ҝʹ هࣄநग़ͨ͠ͷ w ਪఆͨ͠ҙຯ͕ਖ਼͍͔͠ͷஅਓखͰߦ͏ w ؔ࿈ੑධՁख๏
w ؔ࿈ܭࢉ w &BSUI.PWFS`T%JTUBODF &.% w ϕΫτϧۭؒϞσϧ 4BMUPOFUBM 74.
࣮ݧ݁Ռ
࣮ݧ݁Ռ
࣮ݧ݁Ռ
·ͱΊٴͼࠓޙͷల w ޠኮͷ֓೦Խํ๏ͱؔ࿈ੑධՁํ๏ٴͼ8JLJQFEJBΛࣙ ॻͱͯ͠༻͍Δ͜ͱͰӳࣈུޠͷଟٛੑΛղফ͠ɺຊདྷͷ ҙຯͷਪఆΛ࣮ݱͨ͠ w ࠓޙͷ՝ͱͯ͠ɺχϡʔϥϧωοτϫʔΫΛԠ༻ͨ͠ ϕΫτϧϞσϧΛద༻͢Δํ๏ͷݕ౼͕ߟ͑ΒΕΔ