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
500
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
A Quick Overview to Unlock the Potential of LLMs through Prompt Engineering
ayaniwa
0
130
Learning To Retrieve Prompts for In-Context Learning
ayaniwa
0
1k
UnNatural Language Inference
ayaniwa
0
390
Trends in Natural Language Processing at NeurIPS 2019.
ayaniwa
8
4.3k
Other Decks in Research
See All in Research
Weekly AI Agents News! 1月号 アーカイブ
masatoto
1
190
論文紹介: COSMO: A Large-Scale E-commerce Common Sense Knowledge Generation and Serving System at Amazon (SIGMOD 2024)
ynakano
1
410
PostgreSQLにおける分散トレーシングの現在 - 第50回PostgreSQLアンカンファレンス
seinoyu
0
250
Large Vision Language Model (LVLM) に関する最新知見まとめ (Part 1)
onely7
24
6k
Optimal and Diffusion Transports in Machine Learning
gpeyre
0
1.3k
LLM 시대의 Compliance: Safety & Security
huffon
0
610
ラムダ計算の拡張に基づく 音楽プログラミング言語mimium とそのVMの実装
tomoyanonymous
0
410
「熊本県内バス・電車無料デー」の振り返りとその後の展開@土木計画学SS:成功失敗事例に学ぶ公共交通運賃設定
trafficbrain
0
230
サーブレシーブ成功率は勝敗に影響するか?
vball_panda
0
550
Tiaccoon: コンテナネットワークにおいて複数トランスポート方式で統一的なアクセス制御
hiroyaonoe
0
450
eAI (Engineerable AI) プロジェクトの全体像 / Overview of eAI Project
ishikawafyu
0
390
医療支援AI開発における臨床と情報学の連携を円滑に進めるために
moda0
0
150
Featured
See All Featured
Music & Morning Musume
bryan
46
6.4k
Measuring & Analyzing Core Web Vitals
bluesmoon
6
260
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
193
16k
Fashionably flexible responsive web design (full day workshop)
malarkey
406
66k
4 Signs Your Business is Dying
shpigford
183
22k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
27
1.9k
A Modern Web Designer's Workflow
chriscoyier
693
190k
The Power of CSS Pseudo Elements
geoffreycrofte
75
5.5k
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 <ayana.niwa@nlp.c.titech.ac.jp>
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