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
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
Search
onizuka laboratory
December 18, 2018
Research
0
48
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
弊研究室で行なったEMNLP2018読み会の発表資料です。
onizuka laboratory
December 18, 2018
Tweet
Share
More Decks by onizuka laboratory
See All by onizuka laboratory
Phrase-Based & Neural Unsupervised Machine Translation
onilab
0
110
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
onilab
0
65
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
onilab
0
31
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
onilab
0
98
Integrating Transformer and Paraphrase Rules for Sentence Simplification
onilab
0
56
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
onilab
0
98
Modeling Multi-turn Conversation with Deep Utterance Aggregation
onilab
0
91
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
onilab
0
110
SGM: Sequence Generation Model for Multi-Label Classification
onilab
0
67
Other Decks in Research
See All in Research
20240127_熊本から今いちど真面目に都市交通~めざせ「車1割削減、渋滞半減、公共交通2倍」~ 全国路面電車サミット2024宇都宮
trafficbrain
1
660
CSC590 Lecture 01
javiergs
PRO
0
130
クリック率を最大化しない推薦システム
joisino
42
14k
NeurIPS-23 参加報告 + DPO 解説
akifumi_wachi
4
1.5k
DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials
tsurubee
0
370
データで診て考える合志市の渋滞と公共交通 ~めざせ 車1割削減、渋滞半減、公共交通2倍~
trafficbrain
0
460
眠眠ガチャ:ガチャを活用した睡眠意欲向上アプリの開発 / EC71inui
yumulab
0
150
Trezor Safe 3 ファーストインプレッション
toshihr
0
190
LLMマルチエージェントを俯瞰する
masatoto
26
16k
株式会社リクルートホールディングス 企業分析
frandle256
0
130
Azure Arc-enabled Serversを利用した ハイブリッド・マルチクラウド環境の管理 / Managing Hybrid Multi-cloud Environments with Azure Arc-enabled Servers
nttcom
0
210
Discovering Universal Geometry in Embeddings with ICA
momoseoyama
1
350
Featured
See All Featured
The Straight Up "How To Draw Better" Workshop
denniskardys
227
130k
How GitHub (no longer) Works
holman
304
140k
Why You Should Never Use an ORM
jnunemaker
PRO
51
8.6k
Learning to Love Humans: Emotional Interface Design
aarron
267
39k
Become a Pro
speakerdeck
PRO
11
4.5k
A Philosophy of Restraint
colly
197
16k
What's in a price? How to price your products and services
michaelherold
237
11k
Optimising Largest Contentful Paint
csswizardry
8
2.4k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
60
14k
Into the Great Unknown - MozCon
thekraken
10
1k
Code Review Best Practice
trishagee
55
15k
jQuery: Nuts, Bolts and Bling
dougneiner
59
7.1k
Transcript
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in
Dialogue Generation 1 1
• ',"! %,(* + • $
Seq2Seq • ',& )# 2
!" # = − log ) * +
+; #) !. / = 1 2 2 ℎ − 4 !5 6 = − log ) * 7 7; 6) !8 #, /, 6 = − log )(7|+; #, /, 6) 3
Auto-Encoder Encoder !" # = − log ) *
+ +; #) !. / = 1 2 2 ℎ − 4 !5 6 = − log ) * 7 7; 6) !8 #, /, 6 = − log )(7|+; #, /, 6) 4
Mapping Module !" # = − log ) *
+ +; #) !. / = 1 2 2 ℎ − 4 !5 6 = − log ) * 7 7; 6) !8 #, /, 6 = − log )(7|+; #, /, 6) 5
Auto-Encoder Decoder !" # = − log ) *
+ +; #) !. / = 1 2 2 ℎ − 4 !5 6 = − log ) * 7 7; 6) !8 #, /, 6 = − log )(7|+; #, /, 6) 6
End-to-End train loss !" # = − log )
* + +; #) !. / = 1 2 2 ℎ − 4 !5 6 = − log ) * 7 7; 6) !8 #, /, 6 = − log )(7|+; #, /, 6) 7
• Daily Dialogue Corpus 36.3k pairs 11.1k
pairs 11.1k pairs • BLEU-(1, 2, 3, 4), Distinct-(1, 2, 3), Human evaluation • Seq2Seq, Seq2Seq + Attention 8
• • 9
10 • AEM •
10
• *.% # Seq2Seq& • Seq2Seq+ • ( $,!
• ( Fluency, Coherence ' " • Seq2Seq -) 11