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
470
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
100
Learning To Retrieve Prompts for In-Context Learning
ayaniwa
0
980
UnNatural Language Inference
ayaniwa
0
380
Trends in Natural Language Processing at NeurIPS 2019.
ayaniwa
8
4.3k
Other Decks in Research
See All in Research
Leveraging LLMs for Unsupervised Dense Retriever Ranking (SIGIR 2024)
kampersanda
2
200
ECCV2024読み会: Minimalist Vision with Freeform Pixels
hsmtta
1
150
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
110
snlp2024_multiheadMoE
takase
0
430
marukotenant01/tenant-20240826
marketing2024
0
510
尺度開発における質的研究アプローチ(自主企画シンポジウム7:認知行動療法における尺度開発のこれから)
litalicolab
0
350
大規模言語モデルを用いた日本語視覚言語モデルの評価方法とベースラインモデルの提案 【MIRU 2024】
kentosasaki
2
520
129 2 th
0325
0
240
LiDARとカメラのセンサーフュージョンによる点群からのノイズ除去
kentaitakura
0
130
Zipf 白色化:タイプとトークンの区別がもたらす良質な埋め込み空間と損失関数
eumesy
PRO
6
700
さんかくのテスト.pdf
sankaku0724
0
350
Whoisの闇
hirachan
3
140
Featured
See All Featured
GraphQLの誤解/rethinking-graphql
sonatard
67
10k
Gamification - CAS2011
davidbonilla
80
5k
The Invisible Side of Design
smashingmag
298
50k
How GitHub (no longer) Works
holman
310
140k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
4
370
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
169
50k
Code Review Best Practice
trishagee
64
17k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
665
120k
How To Stay Up To Date on Web Technology
chriscoyier
788
250k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
38
1.8k
GraphQLとの向き合い方2022年版
quramy
43
13k
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.5k
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 <
[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