$30 off During Our Annual Pro Sale. View Details »

文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing

Yumeto Inaoka
August 08, 2019
Research
0
240

文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing

2019/08/08の文献紹介で発表

Yumeto Inaoka

August 08, 2019
Tweet

More Decks by Yumeto Inaoka

See All by Yumeto Inaoka
文献紹介: Quantity doesn’t buy quality syntax with neural language models
yumeto
1
100
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
130
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
110
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
110
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
76
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
190
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
170
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
160
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
140

Other Decks in Research

See All in Research
LLMとプランニングの未来
smatsumori
1
290
大規模言語モデル入門 / LLM introduction (SES2023)
kyoun
8
2.8k
Hand Rehabilitation Lab Research Projects
ahspragu
0
510
レガシーなサービス・組織でリサーチの土壌を耕す
uepon73
3
1.1k
V&V of Systems Engineering Models and Modeling Languages
ftsrg
0
180
信頼できるLLMは何を満たすべきか（Trustworthy LLMs）
masatoto
0
540
企業で"も"活躍できる人材像: 企業が院卒者のためにできること、教育機関としての大学に望むこと
mhangyo
1
390
A Theory of Emergent In-Context Learning as Implicit Structure Induction
eumesy
PRO
4
620
数理最適化と機械学習の 融合アプローチ -分類と新しい枠組みと応用-
mickey_kubo
4
870
Why AI Security is a field of Security?
speed1313
1
340
IRではデータ収集がどのように実施・認識されてきたのか
gmoriki
0
170
Google Cloud Next’23「Title：出店ブースで10社以上におすすめ機能を質問してきた」
yasumuusan
0
390

Featured

See All Featured
How to train your dragon (web standard)
notwaldorf
71
4.8k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
318
20k
Ruby is Unlike a Banana
tanoku
93
10k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
239
1.2M
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
15
1.7k
How to name files
jennybc
59
87k
What the flash - Photography Introduction
edds
64
11k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
225
51k
Debugging Ruby Performance
tmm1
68
11k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
226
16k
GraphQLとの向き合い方2022年版
quramy
26
12k
4 Signs Your Business is Dying
shpigford
172
21k

Transcript

  1. View Slide

  2. View Slide

  3. •
    •
    •
    •

    View Slide

  4. •
    •

    View Slide

  5. View Slide

  6. View Slide

  7. •
    •
    •1:−1
    •1:−1
    •

    View Slide

  8. •
    • enc
    = 1
    , … ,
    enc = ℎ1
    enc, … , ℎ
    enc
    • = 1
    , … ,
    •ℎ
    enc = LSTMenc 1

    , 2

    1
    ∙ , 2
    ∙

    View Slide

  9. •
    •h
    enc
    •ℎ
    edit 1:−1
    •
    •ℎ
    edit = LSTMedit ℎ
    enc,
    , ℎ−1
    edit, ℎ−1
    int
    •
    = σ
    =1
    ||
    ℎ

    = softmax ℎ
    , ℎ

    View Slide

  10. •
    •

    View Slide

  11. •

    •ℎ
    int = LSTMint ℎ−1
    int , −1

    View Slide

  12. •
    •

    View Slide

  13. •
    •

    View Slide

  14. •

    View Slide

  15. •
    •
    •

    View Slide

  16. •
    •
    •
    •

    View Slide

  17. •
    •
    •
    •
    •

    View Slide

  18. •
    •

    View Slide

  19. •
    •

    View Slide

  20. •
    •

    View Slide

  21. •

    View Slide

  22. •
    •
    •
    •

    View Slide