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
Open-Retrieval Conversational Question Answering
Search
Scatter Lab Inc.
July 24, 2020
Research
0
2.1k
Open-Retrieval Conversational Question Answering
Scatter Lab Inc.
July 24, 2020
Tweet
Share
More Decks by Scatter Lab Inc.
See All by Scatter Lab Inc.
SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
scatterlab
0
3.1k
Adversarial Filters of Dataset Biases
scatterlab
0
2.1k
Sparse, Dense, and Attentional Representations for Text Retrieval
scatterlab
0
2.1k
Weight Poisoning Attacks on Pre-trained Models
scatterlab
0
2k
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
scatterlab
0
2.2k
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
scatterlab
0
2.1k
What Can Neural Networks Reason About?
scatterlab
0
2.1k
Exploring the Limits of Transfer Learning with Unified Text-to-Text Transformer
scatterlab
0
2k
Pruning Basics on Multi Head Attention-based Models
scatterlab
0
2k
Other Decks in Research
See All in Research
The Theory behind Vector DB
matsui_528
0
1.6k
クリック率を最大化しない推薦システム
joisino
41
14k
SANER 2019 Most Influential Paper Talk
tsantalis
0
120
自己教師あり学習による事前学習(CVIMチュートリアル)
naok615
2
1.4k
リサーチに組織を巻き込むための「準備8割」の話
terasho
0
470
Ground Metric Learning with applications in genomics
gpeyre
0
360
株式会社リクルートホールディングス 企業分析
frandle256
0
130
AIを前提とした体験の実現に向けて/toward_ai_based_experiences
monochromegane
1
240
ゼロからわかるリザバーコンピューティング
kurotaky
1
290
センサデータを活用した 肌質改善への支援システムに関する研究
comfortdesignlab
0
150
訓練データ作成のためのCloudCompareを利用した点群の手動ラベリング
kentaitakura
0
530
F0に基づいて伸縮された画像文字からの音声合成 [ASJ2024春]
nehi0615
0
120
Featured
See All Featured
Code Reviewing Like a Champion
maltzj
514
39k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
274
13k
Writing Fast Ruby
sferik
621
60k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
357
22k
VelocityConf: Rendering Performance Case Studies
addyosmani
320
23k
A designer walks into a library…
pauljervisheath
200
23k
Raft: Consensus for Rubyists
vanstee
132
6.3k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
659
120k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
501
140k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
17
1.4k
Building Applications with DynamoDB
mza
88
5.6k
Side Projects
sachag
451
41k
Transcript
Open-Retrieval Conversational Question Answering ࢲ࢚ (ܻࢲ ࢎ౭झ, ೝಯ)
ѐਃ Open-Retrieval Conversational Question Answering
ѐਃ ѐਃ • SIGIR 20 • Chen Qu, Liu Yang,
Cen Chen, Minghui Qiu, W. Bruce Croft, Mohit Iyyer • University of Massachusetts Amherst, Ant Financial, Alibaba Group • Conversational searchਸ ਤ೧ ConvQAܳ open retrieval settingਵ۽ ഛೞח Ѫ ਃ োҳ ਃ
ѐਃ ѐਃ • Conversational search information retrieval Ҿӓੋ ݾী ೞա
• ୭Ӕ োҳٜ conversational searchܳ response rankingҗ conversational question answering۽ ೧Ѿ • ױࣽ ߸ਸ য candidate setীࢲ ҊܰѢա য passageীࢲ spanਸ ࢶఖ • ח conversational searchীࢲ retrieval ӝୡੋ ഝਸ ޖदೞח ߑध • ࠄ ֤ޙ open-retrieval conversational question answering(ORConvQA) settingਸ ઁউೞৈ ޙઁܳ ೧Ѿ
ѐਃ ѐਃ • ORConvQAী ೠ োҳܳ ਤ೧ OR-QuAC ؘఠ ࣇਸ
ٜ݅ਵݴ ORConvQAܳ ਤೠ end-to-end दझమਸ ҳ୷ೞݴ ےझನݠ ӝ߈ retriever, reranker ৬ reader ١ਸ ನೣ • OR-QuACܳ ࢚ਵ۽ ೠ ֤ޙ प learnable retriever ਃࢿਸ ૐݺ • ژೠ ݽٚ दझమ ҳࢿ ਃࣗ(retriever, reranker ৬ reader)ীࢲ history modelingਸ ࢎਊೞݶ दझమ ѱ ѐࢶ ؼ ࣻ ਸ ࠁ
Dataset Open-Retrieval Conversational Question Answering
ORConvQA? Dataset • conversational search systemsਸ ҳ୷ೞӝ ਤೠ ୶о ױ҅۽ࢲ
߸ਸ Ҋܰ ӝ ী retrieve evidenceܳ large collection۽ ࠗఠ Ѩ࢝ 1. ࠁܳ ҳೞח ചܳ ઁҕ(information seeker৬ information provider)৬ ೞח QuAC dataset 2. QuAC ޙਸ context-independentೞѱ द ࢿೠ CANARD dataset 3. Wikipedia passage
Dataset
CANARD? Dataset • QuAC dialogsח self-containedೞ ঋח ড חؘ ח
ࠛ৮ೠ ୡӝ ޙਵ۽ ੋ೧ ߊࢤ • ܳ ٜয seekerীѱ a Chinese polymathic scientistੋ Zhang Hengী ೧ ߓۄҊ ೮חؘ ޙ "җҗ ӝࣿҗ যڃ ҙ ҅о णפө?” • ۞ೠ ࠛౠೞҊ ݽഐೠ ୡӝ ޙ ചܳ ೧ࢳೞӝ য۵ѱ ೞӝ ٸޙী ҕѐ Ѩ࢝ ജ҃ীࢲ ޙઁܳ ঠӝ • CANARD ؘఠ ࣁীࢲ ઁҕೞח context-independent rewritesਵ۽ ೞৈ ޙઁܳ ೧Ѿ, Ӓۢ "Zhang Heng җ ӝ ࣿҗ যڃ ҙ҅о णפө?"۽ ޙ
CANARD? Dataset • ߣ૩ ޙী ೧ࢲ݅ Үܳ ࣻ೯ೞݶ ച
ղীࢲ history dependenciesਸ Ӓ۽ ਬೞݶࢲ ചо self-contained • QuAC test set ҕѐغয ঋӝ ٸޙী QuAC dev setਸ ਊೞৈ CANARD test setਸ ݅ٞ • ژೠ QuAC train set 10%ܳ dev۽ ഝਊ. • CANARDী হח QuAC ޙ ತӝ೮ਵݴ ܳ ਊೠ ࢤ ؘఠ ੋ OR-QuAC ؘఠ ా҅ח җ э.
Model Open-Retrieval Conversational Question Answering
ݽ؛ Retriever, Reranker, Reader۽ ա Model
ݽ؛ Retriever, Reranker, Reader۽ ա Model
Passage Retriever Dataset • Passage Encoder • Question Encoder •
Retrieval Score
Retrieval score ӝળਵ۽ ࢚ਤ top-Kѐ ޙࢲܳ rerank৬ reader۽ ׳ Model
ݽ؛ Retriever, Reranker, Reader۽ ա Model
Reranker& Reader Encoding Dataset • Input • Contextualized Representations •
sequence representation
Reranker& Reader Dataset • Sequence Representation • Reranker (W_rr is
vector) • Reader (span prediction)
Training Open-Retrieval Conversational Question Answering
Retriever pretraining Training • retrieval scores for the batch •
to maximize the probability of the gold passage for each question • Pretraining loss Pretraning റী passage encoderח offlineਵ۽ ك. Faissܳ ࢎਊ೧ࢲ Ѿҗܳ ࡳই১.
Concurrent Learning Training • Retriever loss • Reranker loss •
Reader loss
Inference Training • Retrieval Ѿҗ Top-K ޙࢲܳ ݽف ੋಌ۠झ ೞৈ
п ޙࢲ߹ spanਸ ஏ • Retriever loss + Reranker loss + Reader lossо ઁੌ ޙࢲ spanਸ ୭ઙ ਵ۽ ஏ
RESULTS Open-Retrieval Conversational Question Answering
Competing Method RESULTS • DrQA : TF-IDF + RNN based
reader • BERTserini : BM25 + BERT reader • ORConvQA without history : our method + window size 0 • ORConvQA : our method • Evaluation Metric : word level F1, human equivalence score (HEQ), Mean Reciprocal Rank(MRR), Recall
DrQA < BERTserini < Ours w/o hist < Ours RESULTS
Ablation study RESULTS
History windows size ઑ RESULTS
хࢎפ✌ ୶о ޙ ژח ҾӘೠ ݶ ઁٚ ইې োۅ۽
োۅ ࣁਃ! ࢲ࢚ (ܻࢲ ࢎ౭झ, ೝಯ)
[email protected]
Linked in. @pingpong