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
520
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
140
Learning To Retrieve Prompts for In-Context Learning
ayaniwa
0
1.1k
UnNatural Language Inference
ayaniwa
0
410
Trends in Natural Language Processing at NeurIPS 2019.
ayaniwa
8
4.4k
Other Decks in Research
See All in Research
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations
satai
3
210
最適化と機械学習による問題解決
mickey_kubo
0
140
rtrec@dbem6
myui
6
860
Principled AI ~深層学習時代における課題解決の方法論~
taniai
3
1.2k
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
nk35jk
2
470
最適決定木を用いた処方的価格最適化
mickey_kubo
4
1.7k
3D Gaussian Splattingによる高効率な新規視点合成技術とその応用
muskie82
5
2.5k
A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis
satai
3
210
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
420
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
monochromegane
0
250
Ad-DS Paper Circle #1
ykaneko1992
0
5.5k
Streamlit 総合解説 ~ PythonistaのためのWebアプリ開発 ~
mickey_kubo
1
900
Featured
See All Featured
VelocityConf: Rendering Performance Case Studies
addyosmani
330
24k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
Site-Speed That Sticks
csswizardry
10
660
Scaling GitHub
holman
459
140k
Adopting Sorbet at Scale
ufuk
77
9.4k
RailsConf 2023
tenderlove
30
1.1k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
15
1.5k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
10
930
Facilitating Awesome Meetings
lara
54
6.4k
Designing Experiences People Love
moore
142
24k
Navigating Team Friction
lara
187
15k
A Modern Web Designer's Workflow
chriscoyier
693
190k
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