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
Modeling Multi-turn Conversation with Deep Utterance Aggregation
Search
onizuka laboratory
October 23, 2018
Research
0
91
Modeling Multi-turn Conversation with Deep Utterance Aggregation
弊研究室で行なったCOLING2018読み会の発表資料です。
onizuka laboratory
October 23, 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
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
onilab
0
48
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
onilab
0
98
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
デフスポーツにおける支援技術 〜競技特性・ルールと技術との関係〜
slab
0
220
[Human-AI Decision Making勉強会] 説明の更新はユーザにどのような影響をもたらすか
okoso
1
200
Gmail の「メール送信者のガイドライン」強化から 1 ヵ月、今後予想されるメールセキュリティの変化とは
hirachan
1
250
説明可能AI:代表的手法と最近の動向
yuyay
1
610
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
音声処理ツールキットESPnetの現在と未来
kanbayashi1125
3
550
論文紹介 DSRNet: Single Image Reflection Separation via Component Synergy (ICCV 2023)
tattaka
0
180
CASCON 2023 Most Influential Paper Award Talk
tsantalis
0
130
クロスモーダル表現学習の研究動向: 音声関連を中心として
ryomasumura
3
610
精神疾患患者のアクティビティデータを利用したリハビリテーションのためのシステムに関する研究
comfortdesignlab
0
150
2024-01-23-az
sofievl
1
770
Featured
See All Featured
4 Signs Your Business is Dying
shpigford
176
21k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
13
8.3k
The Cult of Friendly URLs
andyhume
74
5.7k
Statistics for Hackers
jakevdp
790
220k
Raft: Consensus for Rubyists
vanstee
133
6.3k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
33
6k
Typedesign – Prime Four
hannesfritz
36
2.1k
How GitHub Uses GitHub to Build GitHub
holman
468
290k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
79
43k
Being A Developer After 40
akosma
66
580k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
6
1.3k
Fontdeck: Realign not Redesign
paulrobertlloyd
76
4.9k
Transcript
Modeling Multi-turn Conversation with Deep Utterance Aggregation M1 Koji Tanaka
1
,+! ' 2 %0#)-(0 (-:47".10*+ +/2%0 $ 38?5<?2
&;9>, AE-commerce Dialogue Corpus 2==@6B 2
3
Matching Attention Flow !" = $%& !"'( , *" ,
+" ,- " = ./ tanh 4 5 *- + 47 5 *" + 89 :; " = exp ,; " / @ -A( B exp(,- ") +" = @ ;A( B :; "*; 4
Ubuntu Dialogue Corpus (Ubuntu) Douban Conversation Corpus (Douban) E-commerce
Dialogue Corpus (ECD) TRAIN VALID TEST Ubuntu 1M 500K 500K Douban 1M 50K 10K ECD 1M 10K 10K [context-response pairs] 5
Rn@k Multi-turn
(Zhou et al, 2016) Sequential Matching Network (Wu et al, 2017) 6
7
EDC 8
1 U: How about
the packaging of skin care products. By the way, which delivery company will be responsible for shipping and how long can I receive the goods ? U:How about nuts ? S: Nuts is good. U: OK then, how about zongzi ? 9
!$*"'* &%) ,E-commerce Dialogue Corpus
((+#- EDC 10