RT @math_rachel: Word embeddings quantify 100 years of gender and ethnic stereotypes paper: https://t.co/1Wk7kSINpg code: https://t.co/nBi4…
Word embeddings quantify 100 years of gender and ethnic stereotypes paper: https://t.co/1Wk7kSINpg code: https://t.co/nBi4WkmG4p
RT @ani_nenkova: The gender associations in embeddings closely track the proportion of that gender in the profession https://t.co/DuCW5eYdt…
RT @ani_nenkova: The gender associations in embeddings closely track the proportion of that gender in the profession https://t.co/DuCW5eYdt…
RT @ani_nenkova: The gender associations in embeddings closely track the proportion of that gender in the profession https://t.co/DuCW5eYdt…
I'm not familiar with that literature, but would love to see more details on how implicit bias reproduced in word representations predicts human behavior. The discussion section of the paper below overviews some studies that paint a more complex picture h
RT @ani_nenkova: The gender associations in embeddings closely track the proportion of that gender in the profession https://t.co/DuCW5eYdt…
RT @ani_nenkova: The gender associations in embeddings closely track the proportion of that gender in the profession https://t.co/DuCW5eYdt…
The gender associations in embeddings closely track the proportion of that gender in the profession https://t.co/DuCW5eYdt4 @jurafsky So an effective way to change word representations would be to change society.
For instance, word embeddings have been used to quantify gender and ethnic stereotypes: Garg et al. (https://t.co/POes3oRvlg). Some really interesting work envisions causal inference with *texts*: Egami et al. (https://t.co/vCF1OiGh9K). 11/
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/Lu2Woeik6W #ai #machinelearning #artificialintelligence via @gwern
RT @gwern: @TomerUllman And people say language models don't learn anything about the real world! But word2vec's already been shown to accu…
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/Mji8ZQH8bB
Machine learning tracks 100 years of gender and ethnic stereotypes https://t.co/boIv1jWXgE
@data_stephanie Another, more recent paper: https://t.co/YtrIEeyE3T https://t.co/vWcSGh99iO There's no implicit dataset, but it does have associations of gender word pairs with different adjectives!
타임라인에 딥러닝 알고리즘을 통해 드러난 혹은 재확인된 인간의 차별행동/패턴에 대한 글들이 보이길래, 제 전공과도 관련이 있다보니, 관련 연구 페이퍼들 링크를 좀 남겨봅니다. 1. https://t.co/3cp4kYrv3G 2. https://t.co/KyaHZ4Kpff 3. https://t.co/U2uriv0Gne
@Russwarne @JonathanLWai @PsychRabble See this cool paper. Method is generally applicable to text to infer popular stereotypes over time. https://t.co/kR2w3uooWr
Word embeddings can be used as a powerful tool to quantify historical trends and social change. https://t.co/0QlTD0hcG9 via @GenderStanford
'Word embeddings quantify 100 years of gender and ethnic stereotypes' @PNASNews https://t.co/tLVel4DUhW
RT @kanarinka: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/6fxhN1Vz3Q
RT @kanarinka: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/6fxhN1Vz3Q
RT @kanarinka: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/6fxhN1Vz3Q
RT @kanarinka: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/6fxhN1Vz3Q
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/6fxhN1Vz3Q
An important recent usage of word embeddings for a social science problem: studying gender and ethnic stereotypes. See Garg et al. https://t.co/imWZIqeiHy
@zakkohane Agree. Transfer learning through embedded representations is promising yet rife with challenges (bias https://t.co/mGjaOgkg4g, staleness/concept drift, reidentification). Transfer learning suggests need for pairing with go-live teams for all use
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @DanBischof: Extremely nice paper in @PNASNews via @fgilardi: "The embedding captures societal shifts [...] and also illuminates how sp…
Extremely nice paper in @PNASNews via @fgilardi: "The embedding captures societal shifts [...] and also illuminates how specific adjectives and occupations became more closely associated with certain populations over time." https://t.co/X3m6Ub7Iuq https:/
"we develop metrics based on word embeddings to characterize how gender stereotypes and attitudes toward ethnic minorities in the United States evolved during the 20th and 21st centuries starting from 1910" https://t.co/3dI18pZomP
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/5iqgdAdNGj https://t.co/JPU5zNzhVb
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
#stanfordnlp RT affectScience: Super cool new paper by jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender and ethnic groups is detailed in our language: https://t.co/FXsSwFl7Wb #2018SAS
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
RT @affectScience: Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender an…
Super cool new paper by @jurafsky and colleagues demonstrating that the evolution of linguistic biases towards gender and ethnic groups is detailed in our language: https://t.co/COwKz81EWv #2018SAS
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/0Pr8J7nQV9 #science
Very cool stereotype accuracy study! h/t gwern https://t.co/kR2w3uooWr (no data for blacks because their names weren't distinct enough) https://t.co/PqWsRsEyHp
RT @paul_dimaggio: Fascinating new piece in PNAS uses word embeddings to track gender & ethnic stereotypes > 100 yrs. (Compared to co-occu…
RT @paul_dimaggio: Fascinating new piece in PNAS uses word embeddings to track gender & ethnic stereotypes > 100 yrs. (Compared to co-occu…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @cdcrabtree: This is a must read. https://t.co/s9iRLeYIOC
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
This is a must read. https://t.co/s9iRLeYIOC
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
RT @MattGrossmann: Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings q…
Using word proximity in Google Books and news articles to study changing gender & racial stereotypes. Word embeddings quantify 100 years of gender and ethnic stereotypes: https://t.co/ZTkBuI4xei Here are changing gender & asian stereotypes over ti
RT @NKC_CZ: A fruitful intersection between machine learning and quantitative social science https://t.co/0QlTD0hcG9 #gender #ethnicity #bi…
A fruitful intersection between machine learning and quantitative social science https://t.co/0QlTD0hcG9 #gender #ethnicity #bias via @GenderStanford
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/Y2SQguv9Sv
Artificial intelligence reveals how U.S. stereotypes about women and minorities have changed in the past 100 years https://t.co/oHLsgQxEtp https://t.co/0yctqon493 ($) #ai #gender #discrimination #ethics https://t.co/WPPGgKbyhZ
BIG DATA MEME WATCH: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/BCa0AiGgLf
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/Bj3nBMU08A
One of the positive outcomes of #AI: How gender and ethnic #stereotypes have changed over the last #100Years https://t.co/FJgbHKtwby #MachineLearning #NeuralNetworks #SiliconValley #Discrimination #IISc #BBCNews
RT @LussierY: 100 years of #gender and #Ethnic #stereotypes quantified by #MachineLearning and #NLP: "resourceful"and "clever" progressivel…
100 years of #gender and #Ethnic #stereotypes quantified by #MachineLearning and #NLP: "resourceful"and "clever" progressively becoming gender neutral https://t.co/4hLXLnkfup @PNASNews @NYTScience
#WordEmbeddings quantify 100 years of #gender and #ethnic #stereotypes https://t.co/5qZ2v7YcWZ
RT @vedransekara: Really cool paper. Do stereotypes change over time, yes the do. Are these changes reflected in word embeddings, yes they…
RT @vedransekara: Really cool paper. Do stereotypes change over time, yes the do. Are these changes reflected in word embeddings, yes they…
RT @vedransekara: Really cool paper. Do stereotypes change over time, yes the do. Are these changes reflected in word embeddings, yes they…
RT @vedransekara: Really cool paper. Do stereotypes change over time, yes the do. Are these changes reflected in word embeddings, yes they…
You are what You say. #MachineLearning #VectorSrmanticsModel https://t.co/Z5K2l4GVYt
Really cool paper. Do stereotypes change over time, yes the do. Are these changes reflected in word embeddings, yes they are! https://t.co/XBgzalwwXV
RT @ChrisDanforth: "Word embeddings quantify 100 years of gender & ethnic stereotypes" via @_SalvorHardin https://t.co/C8z50rVb6a https://t…
When machine learning and quantitative social science meet up :) https://t.co/M2mH8fQdlL https://t.co/7U6kXPAABc
RT @ChrisDanforth: "Word embeddings quantify 100 years of gender & ethnic stereotypes" via @_SalvorHardin https://t.co/C8z50rVb6a https://t…
A paper outlining how with machine learning, word embeddings can be use to quantify social and historical trends and changes. The paper - https://t.co/aw4CQPs2WR Data and code - https://t.co/iN4pK3p6VD #wordembeddings #machinelearning
Word embeddings quantify 100 years of gender and ethnic stereotypes | PNAS https://t.co/mExLZFM4hT https://t.co/S8VXlHcNCO
Neat paper from Garg et al. about the analysis of temporal word embeddings to track gender and ethnic stereotypes over time https://t.co/kgB4fEfHdV
RT @ChrisDanforth: "Word embeddings quantify 100 years of gender & ethnic stereotypes" via @_SalvorHardin https://t.co/C8z50rVb6a https://t…
RT @ChrisDanforth: "Word embeddings quantify 100 years of gender & ethnic stereotypes" via @_SalvorHardin https://t.co/C8z50rVb6a https://t…
RT @ChrisDanforth: "Word embeddings quantify 100 years of gender & ethnic stereotypes" via @_SalvorHardin https://t.co/C8z50rVb6a https://t…
"Word embeddings quantify 100 years of gender & ethnic stereotypes" via @_SalvorHardin https://t.co/C8z50rVb6a https://t.co/4mqCkU0Rvm
Word embeddings quantify 100 years of gender and ethnic stereotypes | PNAS https://t.co/Y1NFeD4mOX [arxived pdf] https://t.co/ttXbEBH3kh cool findings!
Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/653nSv3jRL
Interesting article on how word embeddings reveal the historical trend and social changes on gender and ethnic stereotypes: https://t.co/8G6642TvDn https://t.co/EBpUMfK8NL
RT @ndiakopoulos: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/lh61Eg8mT9
Temporal analysis of word embedding reveals relationships with social change. https://t.co/4FAGEtOMcA
RT @ndiakopoulos: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/lh61Eg8mT9
RT @ndiakopoulos: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/lh61Eg8mT9
RT @ndiakopoulos: Word embeddings quantify 100 years of gender and ethnic stereotypes https://t.co/lh61Eg8mT9