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
SNLP2019
Search
Ayana Niwa
September 25, 2019
Research
1
380
SNLP2019
第11回最先端NLP勉強会 発表資料
Ayana Niwa
September 25, 2019
Tweet
Share
More Decks by Ayana Niwa
See All by Ayana Niwa
Learning To Retrieve Prompts for In-Context Learning
ayaniwa
0
890
UnNatural Language Inference
ayaniwa
0
350
Trends in Natural Language Processing at NeurIPS 2019.
ayaniwa
9
4.1k
Other Decks in Research
See All in Research
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
590
LLMマルチエージェントを俯瞰する
masatoto
26
16k
研究効率化Tips_2024 / Research Efficiency Tips 2024
ryo_nakamura
5
2.7k
CSC590 Lecture 01
javiergs
PRO
0
130
SSII2023 医療支援における画像処理研究の動向と展望
moda0
0
110
第12回全日本コンピュータビジョン勉強会:画像の自己教師あり学習における大規模データセット
naok615
0
520
MegaParticles: GPUを利用したStein Particle Filterによる点群6自由度姿勢推定
koide3
1
510
Alternative Photographic Processes Reimagined: The Role of Digital Technology in Revitalizing Classic Printing Techniques【SIGGRAPH Asia 2023】
toremolo72
0
430
SANER 2019 Most Influential Paper Talk
tsantalis
0
120
Trezor Safe 3 ファーストインプレッション
toshihr
0
190
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
[ICLR'24] Towards Assessing and Benchmarking Risk-Return Tradeoff of OPE
harukakiyohara_
0
200
Featured
See All Featured
Fantastic passwords and where to find them - at NoRuKo
philnash
37
2.5k
Building a Scalable Design System with Sketch
lauravandoore
456
32k
Happy Clients
brianwarren
92
6.4k
GraphQLの誤解/rethinking-graphql
sonatard
50
9.2k
KATA
mclloyd
15
12k
Visualization
eitanlees
136
14k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
116
18k
Why Our Code Smells
bkeepers
PRO
331
56k
Optimising Largest Contentful Paint
csswizardry
8
2.4k
Art, The Web, and Tiny UX
lynnandtonic
289
19k
Why You Should Never Use an ORM
jnunemaker
PRO
51
8.6k
Side Projects
sachag
451
41k
Transcript
Probing for Semantic Classes: Diagnosing the Meaning Content of Word
Embeddings Yadollah Yaghoobzadeh, Katharina Kann, Timothy J. Hazen, Eneko Agirre, Hinrich Schutze ACL2019 11 NLP 2019/09/28 <
[email protected]
>
Outline 2 H9P=O8 O8 "!PC
$@K !.S%,'3 F5T&*'$:I P=O8$.S%,'PV ! R<72$PC H/+%)- >#"!.S O8! H9E69NR<72;BJ?Q1L >#".S(rare senses)P=O8APM0 " 4D('% UG
Background 3 # " !Word2VecGrove #"NLPIR* - ELMoBERT
$'+ ) %" full-space , % & L "$( " # &!
Background 4 # "@!Semantic class>*( S-class , "@=6:-&C?4=6
B $8 SEMCAT, HyperLex… =1;+=62%A → 0# .9/ - WIKI-PSE(WIKIpedia-based resource for Probing Semantics in word Embeddings) - "@=1;+sense embedding'7) “Lamb” Food3< Living-thing5< "@ !
Background 5 # Apple Apple Apple
+ Word embeddingsense embedding Arora et al. (2018) Arora et al. (2018) Word embedding sparse coding WIKI-PSEsense embedding Word embedding Sense embedding Sense embedding
WIKI-PSE Resource 6 Wikipedia .!2,$# .! ()
S-class 113 FIGER types%+134"10 person/authorperson/politician… à person -S-class *'.!/.! & - S-class0
WIKI-PSE Resource 7 "$% %2& +:! 343,000-6.-S-class#5'5000;-!% 75,.6,.83
+*1! /4 44,250- -S-class - S-class )0organization (9food @apple@ – food @apple@ – organization
8 Word embedding (word) @apple@ WIKI-PSE
word embedding Sense embedding @apple@ @apple@ - food @apple@ - organization @ word/S-class Uniform sum (unifΣ) !" Weighted sum (wghtΣ) !" # = % " !" #&" # Aggregated word embedding #&" Sense (word/S-class) embeddings word, unifΣ, wghtΣ
Experiments 9 Problem settings SkipGram Structured SkipGram
WIKI-PSE (LR) # (MLP k*)KNN) 1. word % word embedding 2. unifΣ sense embedding " 3. wghtΣ sense embedding ! $'& (" Word embedding
Experiments 10 Probing Task 1S-class Prediction S-class
@apple@ +food ∩ +organization ∩ -event S-class
Experiments 11 MLP > LRKNN 8&!S-class ."7;5
KNN )#, *:3, <(3-/ unifΣ > word > wghtΣ 'rare sense 0$ 97< à Rare sense42%+6 unifΣ Probing Task 1S-class Prediction F11 4
Experiments 12 Probing Task 1S-class Prediction
unifΣ $ #rare sense (13,000) F1! "
Experiments 13 Probing Task 1S-class Prediction * #4(! Recall
) S-class& sense embedding+%3 Rare S-class/"12 %"0, .$- Recall Dominance S-class' Recall
Experiments 14 Probing Task 1S-class Prediction /&)5. !"$' ,(20-
3+1(#41( Personlocation,(20* S-class !"6 20% Recall Recall #4 ,(20 Typicality Recall
Experiments 15 " Probing Task 2Ambiguity
Prediction ! L2 SSKIP$" LR / KNN / MLP ! ! unifΣ > word > wghtΣ KNN à % FREQUENCY(Baseline) # &LR
NLP Application Experiments 16 wghtΣ > word >(=) unifΣ <--
Probing task #!! -the U.S. Attorney’s Office announced Friday → location Common S-classtime Rare S-class location Friday mountain unifΣ ( !+ entity mention MC ), CRMR $)& SUBJ %*' MRPC " S-class
Summary & Conclusion 17 * $2"(3 WIKI-PSE'. 1)/& 0+$2/&
1, 1)/&% # 0+$2- a a e Rare sense e harder NLP Rare sense !# e