Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Learning Word Meta-Embeddings by Autoencoding

Avatar for onizuka laboratory onizuka laboratory
October 17, 2018
Research
0
44

Learning Word Meta-Embeddings by Autoencoding

弊研究室で行なったCOLING2018読み会の発表資料です。

Avatar for onizuka laboratory

onizuka laboratory

October 17, 2018
Tweet

More Decks by onizuka laboratory

See All by onizuka laboratory
Phrase-Based & Neural Unsupervised Machine Translation
Avatar for onizuka laboratory onilab
0
110
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
Avatar for onizuka laboratory onilab
0
71
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
Avatar for onizuka laboratory onilab
0
33
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
Avatar for onizuka laboratory onilab
0
120
Integrating Transformer and Paraphrase Rules for Sentence Simplification
Avatar for onizuka laboratory onilab
0
59
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
Avatar for onizuka laboratory onilab
0
55
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
Avatar for onizuka laboratory onilab
0
100
Modeling Multi-turn Conversation with Deep Utterance Aggregation
Avatar for onizuka laboratory onilab
0
95
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
Avatar for onizuka laboratory onilab
0
120

Other Decks in Research

See All in Research
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Avatar for Naoki Kato nk35jk
2
980
機械学習と数理最適化の融合 (MOAI) による革新
Avatar for MIKIO KUBO mickey_kubo
0
310
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
Avatar for monochromegane monochromegane
0
2.8k
Mechanistic Interpretability：解釈可能性研究の新たな潮流
Avatar for Koshiro Aoki koshiro_aoki
1
410
When Submarine Cables Go Dark: Examining the Web Services Resilience Amid Global Internet Disruptions
Avatar for Irvin Chen irvin
0
300
AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
Avatar for SatAI.challenge satai
1
200
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
Avatar for MasaKat0 masakat0
0
110
数理最適化に基づく制御
Avatar for MIKIO KUBO mickey_kubo
6
730
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
Avatar for Traffic Brain trafficbrain
0
770
データｘデジタルマップで拓く
ミラノ発・地域共創最前線
Avatar for mapconcierge mapconcierge4agu
0
210
最適化と機械学習による問題解決
Avatar for MIKIO KUBO mickey_kubo
0
170
Delta Airlines® Customer Care in the U.S.: How to Reach Them Now
Avatar for booking.comcustomerservice bookingcomcustomersupportusa
0
110

Featured

See All Featured
Building Adaptive Systems
Avatar for Chris Keathley keathley
43
2.7k
The World Runs on Bad Software
Avatar for Brandon Keepers bkeepers
PRO
70
11k
Imperfection Machines: The Place of Print at Facebook
Avatar for Scott Boms scottboms
268
13k
Designing for humans not robots
Avatar for Tammie Lister tammielis
253
25k
Gamification - CAS2011
Avatar for David Bonilla davidbonilla
81
5.4k
Java REST API Framework Comparison - PWX 2021
Avatar for Matt Raible mraible
33
8.8k
How GitHub (no longer) Works
Avatar for Zach Holman holman
315
140k
Faster Mobile Websites
Avatar for Dean Hume deanohume
309
31k
Scaling GitHub
Avatar for Zach Holman holman
463
140k
GraphQLの誤解/rethinking-graphql
Avatar for sonatard sonatard
72
11k
Rails Girls Zürich Keynote
Avatar for Gregor Martynus gr2m
95
14k
Reflections from 52 weeks, 52 projects
Avatar for Jefferson Lam jeffersonlam
352
21k

Transcript

  1. 

  2. DC BA - -- - - 1

  3. • 2 – 2 – • 2

  4. • ) ) ( - • ) ) ( -

    • ) ( - 3

  5. 2 2 1 2 1- • , ,2 4

  6. - - - • 5

  7. - 6

  8. G • 0 6 , – 74: 2 51 –

    • G 7 Method Bs Lr Epoch !" !# !$ Hidden neurons DAEME 128 0.001 500 1.0 1.0 5.0 600 CAEME 128 0.001 500 1.0 1.0 / 600 AAEME 128 0.001 500 1.0 1.0 / 600

  9. DR • M • • M • E – ,

    • B J – M B J 8

  10. • 2 2 • 2 9    

    

  11.   • 0 #&/% "1(* +!"1(*$) •  "1(*,.

    • -' ,. 10