diff --git a/authors/arianna_muti/avatar.jpeg b/authors/arianna_muti/avatar.jpeg new file mode 100644 index 00000000..d400039d Binary files /dev/null and b/authors/arianna_muti/avatar.jpeg differ diff --git a/authors/arianna_muti/avatar_hu830679e57224e317b7851355fbf45d95_30789_270x270_fill_q90_lanczos_center.jpeg b/authors/arianna_muti/avatar_hu830679e57224e317b7851355fbf45d95_30789_270x270_fill_q90_lanczos_center.jpeg new file mode 100644 index 00000000..1469508f Binary files /dev/null and b/authors/arianna_muti/avatar_hu830679e57224e317b7851355fbf45d95_30789_270x270_fill_q90_lanczos_center.jpeg differ diff --git a/authors/arianna_muti/index.html b/authors/arianna_muti/index.html index ee9b2a41..195a72f7 100644 --- a/authors/arianna_muti/index.html +++ b/authors/arianna_muti/index.html @@ -609,6 +609,9 @@

Search

+ + Arianna Muti +

Arianna Muti

diff --git a/index.html b/index.html index b7d3346c..fb09eb45 100644 --- a/index.html +++ b/index.html @@ -1035,6 +1035,12 @@

Assistant Professor

+ + + + + + Avatar
diff --git a/project/integrator/index.html b/project/integrator/index.html index 5c07ff37..ac7e7818 100644 --- a/project/integrator/index.html +++ b/project/integrator/index.html @@ -859,7 +859,7 @@

Related

  • Identifying Linguistic Areas for Geolocation
    • -
  • Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers
    • +
  • Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing
  • Dense Node Representation for Geolocation
    • diff --git a/project/mentalism/index.html b/project/mentalism/index.html index d2c3596f..d104cb84 100644 --- a/project/mentalism/index.html +++ b/project/mentalism/index.html @@ -859,14 +859,14 @@

    Related

  • INTEGRATOR
    • -
  • Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks
    • +
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
    • -
  • Pipelines for Social Bias Testing of Large Language Models
    • - -
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
    • +
  • Language Invariant Properties in Natural Language Processing
  • XLM-EMO: Multilingual Emotion Prediction in Social Media Text
    • +
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
    • +
    diff --git a/publication/2018-comparing-bayesian-models-annotation/index.html b/publication/2018-comparing-bayesian-models-annotation/index.html index ddf9dbaf..2bfcec9d 100644 --- a/publication/2018-comparing-bayesian-models-annotation/index.html +++ b/publication/2018-comparing-bayesian-models-annotation/index.html @@ -1115,13 +1115,13 @@

    Related

  • A Case for Soft Loss Functions
    • -
  • The Social and the Neural Network: How to Make Natural Language Processing about People again
    • -
  • Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting
  • Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning
    • -
  • Text Analysis in Python for Social Scientists – Discovery and Exploration
    • +
  • The Social and the Neural Network: How to Make Natural Language Processing about People again
    • + +
  • What the [MASK]? Making Sense of Language-Specific BERT Models
    • diff --git a/publication/2018-predicting-news-headline-popularity-syntactic-semantic-knowledge-multitask-learning/index.html b/publication/2018-predicting-news-headline-popularity-syntactic-semantic-knowledge-multitask-learning/index.html index c5595261..3e739c94 100644 --- a/publication/2018-predicting-news-headline-popularity-syntactic-semantic-knowledge-multitask-learning/index.html +++ b/publication/2018-predicting-news-headline-popularity-syntactic-semantic-knowledge-multitask-learning/index.html @@ -1031,12 +1031,12 @@

    Related

  • Geolocation with Attention-Based Multitask Learning Models
    • +
  • The Social and the Neural Network: How to Make Natural Language Processing about People again
    • +
  • Comparing Bayesian Models of Annotation
  • Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting
    • -
  • The Social and the Neural Network: How to Make Natural Language Processing about People again
    • -
  • Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success
    • diff --git a/publication/2018-social-neural-network/index.html b/publication/2018-social-neural-network/index.html index 4a7793fd..611cf8c9 100644 --- a/publication/2018-social-neural-network/index.html +++ b/publication/2018-social-neural-network/index.html @@ -983,7 +983,7 @@

    Related

  • Dense Node Representation for Geolocation
    • -
  • Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning
    • +
  • Comparing Bayesian Models of Annotation
    • diff --git a/publication/2019_m2v/index.html b/publication/2019_m2v/index.html index 260776c8..6d775f26 100644 --- a/publication/2019_m2v/index.html +++ b/publication/2019_m2v/index.html @@ -1001,10 +1001,10 @@

    Related

  • Geolocation with Attention-Based Multitask Learning Models
    • -
  • Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing
    • -
  • Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers
    • +
  • Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing
    • +
    diff --git a/publication/2019_siri/index.html b/publication/2019_siri/index.html index a11d2ed3..c2a24251 100644 --- a/publication/2019_siri/index.html +++ b/publication/2019_siri/index.html @@ -999,10 +999,10 @@

    Related

    diff --git a/publication/2020-bertlang-language-specific-bert/index.html b/publication/2020-bertlang-language-specific-bert/index.html index 840f0c2f..7738454b 100644 --- a/publication/2020-bertlang-language-specific-bert/index.html +++ b/publication/2020-bertlang-language-specific-bert/index.html @@ -1059,7 +1059,7 @@

    Related

  • Dense Node Representation for Geolocation
    • -
  • Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
    • +
  • Text Analysis in Python for Social Scientists – Discovery and Exploration
    • diff --git a/publication/2020_eutwitter/index.html b/publication/2020_eutwitter/index.html index 5951a19b..ce4a4276 100644 --- a/publication/2020_eutwitter/index.html +++ b/publication/2020_eutwitter/index.html @@ -1067,7 +1067,7 @@

    Related

  • Dense Node Representation for Geolocation
    • -
  • Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
    • +
  • Text Analysis in Python for Social Scientists – Discovery and Exploration
    • diff --git a/publication/2020_helpful/index.html b/publication/2020_helpful/index.html index fc30d1f4..7d103bd1 100644 --- a/publication/2020_helpful/index.html +++ b/publication/2020_helpful/index.html @@ -1087,15 +1087,15 @@

    Related

    diff --git a/publication/2020_lre/index.html b/publication/2020_lre/index.html index c09dfbdf..17cc6e06 100644 --- a/publication/2020_lre/index.html +++ b/publication/2020_lre/index.html @@ -1065,12 +1065,12 @@

    Related

  • Identifying Linguistic Areas for Geolocation
    • -
  • Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers
    • -
  • Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing
  • Dense Node Representation for Geolocation
    • +
  • Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers
    • + diff --git a/publication/2020_mt/index.html b/publication/2020_mt/index.html index 70417e0f..143a052c 100644 --- a/publication/2020_mt/index.html +++ b/publication/2020_mt/index.html @@ -1045,9 +1045,9 @@

    Related

  • Visualizing Regional Language Variation Across Europe on Twitter
    • -
  • What the [MASK]? Making Sense of Language-Specific BERT Models
    • +
  • Text Analysis in Python for Social Scientists – Discovery and Exploration
    • -
  • Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success
    • +
  • What the [MASK]? Making Sense of Language-Specific BERT Models
    • diff --git a/publication/2020_nlpss/index.html b/publication/2020_nlpss/index.html index 15ec5420..d232f0de 100644 --- a/publication/2020_nlpss/index.html +++ b/publication/2020_nlpss/index.html @@ -977,12 +977,12 @@

    Related

  • Peer networks and entrepreneurship: A Pan-African RCT
    • +
  • “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases
    • +
  • Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
  • Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success
    • -
  • Visualizing Regional Language Variation Across Europe on Twitter
    • - diff --git a/publication/2021-aclfindings-mimac/index.html b/publication/2021-aclfindings-mimac/index.html index 37c9012a..1b28728b 100644 --- a/publication/2021-aclfindings-mimac/index.html +++ b/publication/2021-aclfindings-mimac/index.html @@ -1121,12 +1121,12 @@

    Related

  • On the Gap between Adoption and Understanding in NLP
    • +
  • Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning
    • +
  • Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence
  • Five sources of bias in natural language processing
    • -
  • Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning
    • -
  • BERTective: Language Models and Contextual Information for Deception Detection
    • diff --git a/publication/2021-contextualized-improve-topic-models-coherence/index.html b/publication/2021-contextualized-improve-topic-models-coherence/index.html index 91180d01..71e81daa 100644 --- a/publication/2021-contextualized-improve-topic-models-coherence/index.html +++ b/publication/2021-contextualized-improve-topic-models-coherence/index.html @@ -1039,14 +1039,14 @@

    Related

  • Cross-lingual Contextualized Topic Models with Zero-shot Learning
    • -
  • Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning
    • -
  • 'We will Reduce Taxes' - Identifying Election Pledges with Language Models
  • On the Gap between Adoption and Understanding in NLP
  • Five sources of bias in natural language processing
    • +
  • Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning
    • + diff --git a/publication/2021-crosslingual-topic-model/index.html b/publication/2021-crosslingual-topic-model/index.html index 687bd839..8b0ab973 100644 --- a/publication/2021-crosslingual-topic-model/index.html +++ b/publication/2021-crosslingual-topic-model/index.html @@ -1121,14 +1121,14 @@

    Related

  • What the [MASK]? Making Sense of Language-Specific BERT Models
    • -
  • Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success
    • - -
  • The Social and the Neural Network: How to Make Natural Language Processing about People again
    • -
  • Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning
  • Text Analysis in Python for Social Scientists – Prediction and Classification
    • +
  • Comparing Bayesian Models of Annotation
    • + +
  • Text Analysis in Python for Social Scientists – Discovery and Exploration
    • + diff --git a/publication/2021-importance-modeling-social-factors-language/index.html b/publication/2021-importance-modeling-social-factors-language/index.html index 07bd6a05..4b1d96ee 100644 --- a/publication/2021-importance-modeling-social-factors-language/index.html +++ b/publication/2021-importance-modeling-social-factors-language/index.html @@ -1007,14 +1007,14 @@

    Related

  • Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
    • -
  • Five sources of bias in natural language processing
    • - -
  • On the Gap between Adoption and Understanding in NLP
    • -
  • 'We will Reduce Taxes' - Identifying Election Pledges with Language Models
    • +
  • Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence
    • +
  • Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning
    • +
  • On the Gap between Adoption and Understanding in NLP
    • + diff --git a/publication/2021-language-in-a-search-box/index.html b/publication/2021-language-in-a-search-box/index.html index 467bfe7f..e746cc48 100644 --- a/publication/2021-language-in-a-search-box/index.html +++ b/publication/2021-language-in-a-search-box/index.html @@ -1055,11 +1055,11 @@

    Related

  • What the [MASK]? Making Sense of Language-Specific BERT Models
    • -
  • Text Analysis in Python for Social Scientists – Prediction and Classification
    • -
  • Visualizing Regional Language Variation Across Europe on Twitter
    • -
  • Comparing Bayesian Models of Annotation
    • +
  • The Social and the Neural Network: How to Make Natural Language Processing about People again
    • + +
  • Text Analysis in Python for Social Scientists – Prediction and Classification
    • diff --git a/publication/2021-learning_from_disagreement_survey/index.html b/publication/2021-learning_from_disagreement_survey/index.html index 2f87e00d..417de59d 100644 --- a/publication/2021-learning_from_disagreement_survey/index.html +++ b/publication/2021-learning_from_disagreement_survey/index.html @@ -1117,11 +1117,11 @@

    Related

  • A Case for Soft Loss Functions
    • -
  • Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
    • -
  • The Importance of Modeling Social Factors of Language: Theory and Practice
    • -
  • Five sources of bias in natural language processing
    • +
  • Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
    • + +
  • 'We will Reduce Taxes' - Identifying Election Pledges with Language Models
    • diff --git a/publication/2021-naacl-softlabels/index.html b/publication/2021-naacl-softlabels/index.html index e99b8cb8..41783ade 100644 --- a/publication/2021-naacl-softlabels/index.html +++ b/publication/2021-naacl-softlabels/index.html @@ -1091,10 +1091,10 @@
    Related diff --git a/publication/2021-wassa-emotion-multitask/index.html b/publication/2021-wassa-emotion-multitask/index.html index e01d992c..a1ecea56 100644 --- a/publication/2021-wassa-emotion-multitask/index.html +++ b/publication/2021-wassa-emotion-multitask/index.html @@ -1047,7 +1047,7 @@

    Related

  • What the [MASK]? Making Sense of Language-Specific BERT Models
    • -
  • “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases
    • +
  • Text Analysis in Python for Social Scientists – Discovery and Exploration
    • diff --git a/publication/2021_eacl_decour/index.html b/publication/2021_eacl_decour/index.html index d63d90af..fadeeece 100644 --- a/publication/2021_eacl_decour/index.html +++ b/publication/2021_eacl_decour/index.html @@ -1079,10 +1079,10 @@

    Related

  • HONEST: Measuring Hurtful Sentence Completion in Language Models
    • -
  • Universal Joy A Data Set and Results for Classifying Emotions Across Languages
    • -
  • MilaNLP @ WASSA: Does BERT Feel Sad When You Cry?
    • +
  • Universal Joy A Data Set and Results for Classifying Emotions Across Languages
    • + diff --git a/publication/2022-acl-argumentation/index.html b/publication/2022-acl-argumentation/index.html index 256339dd..9945bf1a 100644 --- a/publication/2022-acl-argumentation/index.html +++ b/publication/2022-acl-argumentation/index.html @@ -963,10 +963,10 @@

    Related

  • DS-TOD: Efficient Domain Specialization for Task Oriented Dialog
    • -
  • SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems
    • -
  • Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
    • +
  • SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems
    • +
  • Text Analysis in Python for Social Scientists – Prediction and Classification
  • Learning from Disagreement: A Survey
    • diff --git a/publication/2022-acl-findings-dstod/index.html b/publication/2022-acl-findings-dstod/index.html index ca6d10a3..b2e57607 100644 --- a/publication/2022-acl-findings-dstod/index.html +++ b/publication/2022-acl-findings-dstod/index.html @@ -957,10 +957,10 @@

    Related

  • Fair and Argumentative Language Modeling for Computational Argumentation
    • -
  • Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
    • -
  • SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems
    • +
  • Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
    • +
  • Text Analysis in Python for Social Scientists – Prediction and Classification
  • Learning from Disagreement: A Survey
    • diff --git a/publication/2022-bridging_fairness_and_environmental_sustainability_in_natural_language_processing/index.html b/publication/2022-bridging_fairness_and_environmental_sustainability_in_natural_language_processing/index.html index a3443f61..fa60547e 100644 --- a/publication/2022-bridging_fairness_and_environmental_sustainability_in_natural_language_processing/index.html +++ b/publication/2022-bridging_fairness_and_environmental_sustainability_in_natural_language_processing/index.html @@ -1067,10 +1067,10 @@

    Related

  • Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design
    • -
  • It's Not Just Hate: A Multi-Dimensional Perspective on Detecting Harmful Speech Online
    • -
  • Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data
    • +
  • It's Not Just Hate: A Multi-Dimensional Perspective on Detecting Harmful Speech Online
    • +
  • SocioProbe: What, When, and Where Language Models Learn about Sociodemographics
    • diff --git a/publication/2022-guiding_release_safer_e2e_conversational_ai_through_value_sensitive_design/index.html b/publication/2022-guiding_release_safer_e2e_conversational_ai_through_value_sensitive_design/index.html index 4ec3a931..b80541da 100644 --- a/publication/2022-guiding_release_safer_e2e_conversational_ai_through_value_sensitive_design/index.html +++ b/publication/2022-guiding_release_safer_e2e_conversational_ai_through_value_sensitive_design/index.html @@ -1137,10 +1137,10 @@

    Related

  • SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems
    • -
  • “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases
    • -
  • Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
    • +
  • “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases
    • +
  • HATE-ITA: Hate Speech Detection in Italian Social Media Text
  • Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
    • diff --git a/publication/2022-hard_soft_evaluation_nlp_models_bootstrap_sampling-boostsa/index.html b/publication/2022-hard_soft_evaluation_nlp_models_bootstrap_sampling-boostsa/index.html index 7f2087f0..1be3356f 100644 --- a/publication/2022-hard_soft_evaluation_nlp_models_bootstrap_sampling-boostsa/index.html +++ b/publication/2022-hard_soft_evaluation_nlp_models_bootstrap_sampling-boostsa/index.html @@ -1073,13 +1073,13 @@

    Related

  • MENTALISM
    • -
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
    • +
  • Language Invariant Properties in Natural Language Processing
    • -
  • Pipelines for Social Bias Testing of Large Language Models
    • +
  • Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks
    • -
  • XLM-EMO: Multilingual Emotion Prediction in Social Media Text
    • +
  • Pipelines for Social Bias Testing of Large Language Models
    • -
  • Language Invariant Properties in Natural Language Processing
    • +
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
    • diff --git a/publication/2022-hate-speech-detection-italian-social-media/index.html b/publication/2022-hate-speech-detection-italian-social-media/index.html index 3e4340ba..c8d27432 100644 --- a/publication/2022-hate-speech-detection-italian-social-media/index.html +++ b/publication/2022-hate-speech-detection-italian-social-media/index.html @@ -1059,11 +1059,11 @@

    Related

  • Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
    • -
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
    • +
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
  • Pipelines for Social Bias Testing of Large Language Models
    • -
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
    • +
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
  • Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
    • diff --git a/publication/2022-honest-harmful-scandinavian-language-model/index.html b/publication/2022-honest-harmful-scandinavian-language-model/index.html index 2d2ddac1..f253f8e0 100644 --- a/publication/2022-honest-harmful-scandinavian-language-model/index.html +++ b/publication/2022-honest-harmful-scandinavian-language-model/index.html @@ -1009,11 +1009,11 @@

    Related

  • Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
    • -
  • HATE-ITA: Hate Speech Detection in Italian Social Media Text
    • -
  • Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
    • -
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
    • +
  • HATE-ITA: Hate Speech Detection in Italian Social Media Text
    • + +
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
    • diff --git a/publication/2022-interpretability-transformer-mysogyny-detection/index.html b/publication/2022-interpretability-transformer-mysogyny-detection/index.html index 5b30950a..0202a0a9 100644 --- a/publication/2022-interpretability-transformer-mysogyny-detection/index.html +++ b/publication/2022-interpretability-transformer-mysogyny-detection/index.html @@ -1079,10 +1079,10 @@

    Related

    diff --git a/publication/2022-limitation-diachronic-continuous-training/index.html b/publication/2022-limitation-diachronic-continuous-training/index.html index 26c5fe24..b817f063 100644 --- a/publication/2022-limitation-diachronic-continuous-training/index.html +++ b/publication/2022-limitation-diachronic-continuous-training/index.html @@ -1047,16 +1047,16 @@

    Related

    diff --git a/publication/2022-multilingual-hatecheck-hate-speech-functional-tests/index.html b/publication/2022-multilingual-hatecheck-hate-speech-functional-tests/index.html index 7d823864..6813cc68 100644 --- a/publication/2022-multilingual-hatecheck-hate-speech-functional-tests/index.html +++ b/publication/2022-multilingual-hatecheck-hate-speech-functional-tests/index.html @@ -1095,11 +1095,11 @@

    Related

  • HATE-ITA: Hate Speech Detection in Italian Social Media Text
    • -
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
    • +
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
  • Pipelines for Social Bias Testing of Large Language Models
    • -
  • Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
    • +
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
  • Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
    • diff --git a/publication/2022-safetykit-first-aid-measuring-safety-open-domain-conversational-systems/index.html b/publication/2022-safetykit-first-aid-measuring-safety-open-domain-conversational-systems/index.html index 2949b738..bdddf09e 100644 --- a/publication/2022-safetykit-first-aid-measuring-safety-open-domain-conversational-systems/index.html +++ b/publication/2022-safetykit-first-aid-measuring-safety-open-domain-conversational-systems/index.html @@ -1139,10 +1139,10 @@

    Related

  • Learning from Disagreement: A Survey
    • -
  • Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
    • -
  • The Importance of Modeling Social Factors of Language: Theory and Practice
    • +
  • Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
    • + diff --git a/publication/2022-strategies-hate-speech-detection-under-resourced-languages/index.html b/publication/2022-strategies-hate-speech-detection-under-resourced-languages/index.html index 54f81a97..2f979345 100644 --- a/publication/2022-strategies-hate-speech-detection-under-resourced-languages/index.html +++ b/publication/2022-strategies-hate-speech-detection-under-resourced-languages/index.html @@ -1063,16 +1063,16 @@

    Related

    diff --git a/publication/2022-twitter_demographer/index.html b/publication/2022-twitter_demographer/index.html index 84f4d503..6f2b997c 100644 --- a/publication/2022-twitter_demographer/index.html +++ b/publication/2022-twitter_demographer/index.html @@ -1049,10 +1049,10 @@

    Related

  • Measuring Harmful Representations in Scandinavian Language Models
    • -
  • XLM-EMO: Multilingual Emotion Prediction in Social Media Text
    • -
  • Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks
    • +
  • XLM-EMO: Multilingual Emotion Prediction in Social Media Text
    • +
  • BERTective: Language Models and Contextual Information for Deception Detection
    • diff --git a/publication/2022-two-contrasting-data-annotation-paradigms-subjective-nlp-tasks/index.html b/publication/2022-two-contrasting-data-annotation-paradigms-subjective-nlp-tasks/index.html index 1bfeb461..09c6af2a 100644 --- a/publication/2022-two-contrasting-data-annotation-paradigms-subjective-nlp-tasks/index.html +++ b/publication/2022-two-contrasting-data-annotation-paradigms-subjective-nlp-tasks/index.html @@ -1071,7 +1071,7 @@

    Related

  • Fake opinion detection: how similar are crowdsourced datasets to real data?
    • -
  • Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
    • +
  • Language Invariant Properties in Natural Language Processing
    • diff --git a/publication/2022-welcome_modern_world_pronouns_identity-inclusive_natural_language_processing_beyond_gender/index.html b/publication/2022-welcome_modern_world_pronouns_identity-inclusive_natural_language_processing_beyond_gender/index.html index acc8a656..8c80d288 100644 --- a/publication/2022-welcome_modern_world_pronouns_identity-inclusive_natural_language_processing_beyond_gender/index.html +++ b/publication/2022-welcome_modern_world_pronouns_identity-inclusive_natural_language_processing_beyond_gender/index.html @@ -1037,10 +1037,10 @@

    Related

  • Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design
    • -
  • “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases
    • -
  • Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
    • +
  • “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases
    • +
  • HATE-ITA: Hate Speech Detection in Italian Social Media Text
  • Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
    • diff --git a/publication/2022_nlpss2/index.html b/publication/2022_nlpss2/index.html index 0da505db..08e22a90 100644 --- a/publication/2022_nlpss2/index.html +++ b/publication/2022_nlpss2/index.html @@ -979,11 +979,11 @@

    Related

  • Peer networks and entrepreneurship: A Pan-African RCT
    • -
  • Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning
    • +
  • Comparing Bayesian Models of Annotation
  • Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success
    • -
  • Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting
    • +
  • What the [MASK]? Making Sense of Language-Specific BERT Models
    • diff --git a/publication/2023-alignmentparadigms/index.html b/publication/2023-alignmentparadigms/index.html index 024cc345..a41f144b 100644 --- a/publication/2023-alignmentparadigms/index.html +++ b/publication/2023-alignmentparadigms/index.html @@ -1073,11 +1073,11 @@

    Related

  • The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values
    • -
  • Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
    • +
  • SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety
    • -
  • Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
    • +
  • Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models
    • -
  • My Answer is C: First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
    • +
  • XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
    • diff --git a/publication/2023-cross-lingual-study-homotransphobia/index.html b/publication/2023-cross-lingual-study-homotransphobia/index.html index e46df112..3eaccedf 100644 --- a/publication/2023-cross-lingual-study-homotransphobia/index.html +++ b/publication/2023-cross-lingual-study-homotransphobia/index.html @@ -1039,10 +1039,10 @@

    Related

  • It's Not Just Hate: A Multi-Dimensional Perspective on Detecting Harmful Speech Online
    • -
  • HATE-ITA: Hate Speech Detection in Italian Social Media Text
    • -
  • Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
    • +
  • HATE-ITA: Hate Speech Detection in Italian Social Media Text
    • + diff --git a/publication/2023-human-feedback-learning-survey/index.html b/publication/2023-human-feedback-learning-survey/index.html index 191809ab..97529e43 100644 --- a/publication/2023-human-feedback-learning-survey/index.html +++ b/publication/2023-human-feedback-learning-survey/index.html @@ -1097,15 +1097,15 @@

    Related

    diff --git a/publication/2023-interpretability-for-fairer-machine-translation/index.html b/publication/2023-interpretability-for-fairer-machine-translation/index.html index d1fc0c29..b9986b42 100644 --- a/publication/2023-interpretability-for-fairer-machine-translation/index.html +++ b/publication/2023-interpretability-for-fairer-machine-translation/index.html @@ -1101,7 +1101,7 @@

    Related

  • Bridging Fairness and Environmental Sustainability in Natural Language Processing
    • -
  • Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
    • +
  • “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases
    • diff --git a/publication/2023-multidimensional-bias-vision-language-models/index.html b/publication/2023-multidimensional-bias-vision-language-models/index.html index a445d828..d625bc9b 100644 --- a/publication/2023-multidimensional-bias-vision-language-models/index.html +++ b/publication/2023-multidimensional-bias-vision-language-models/index.html @@ -1011,9 +1011,9 @@

    Related

  • The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond Sociodemographics
    • -
  • MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection
    • +
  • What about ''em''? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns
    • -
  • Respectful or Toxic? Using Zero-Shot Learning with Language Models to Detect Hate Speech
    • +
  • MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection
    • diff --git a/publication/2023-proceedings-c3nlp/index.html b/publication/2023-proceedings-c3nlp/index.html index 8e61cec4..e032df4f 100644 --- a/publication/2023-proceedings-c3nlp/index.html +++ b/publication/2023-proceedings-c3nlp/index.html @@ -1069,10 +1069,10 @@

    Related

  • Beyond Digital 'Echo Chambers': The Role of Viewpoint Diversity in Political Discussion
    • -
  • ferret: a Framework for Benchmarking Explainers on Transformers
    • -
  • Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers
    • +
  • ferret: a Framework for Benchmarking Explainers on Transformers
    • +
  • INDOMITA
  • Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?
    • diff --git a/publication/2023-simplesafetytests/index.html b/publication/2023-simplesafetytests/index.html index 55a5c0a2..2f1a1a00 100644 --- a/publication/2023-simplesafetytests/index.html +++ b/publication/2023-simplesafetytests/index.html @@ -1153,14 +1153,14 @@

    Related

    diff --git a/publication/2024-compromesso/index.html b/publication/2024-compromesso/index.html index 50e9fa47..8db865ca 100644 --- a/publication/2024-compromesso/index.html +++ b/publication/2024-compromesso/index.html @@ -1041,11 +1041,11 @@

    Related

    diff --git a/publication/2024-divine-llamas-emotion-bias/index.html b/publication/2024-divine-llamas-emotion-bias/index.html index e20dd559..0705563f 100644 --- a/publication/2024-divine-llamas-emotion-bias/index.html +++ b/publication/2024-divine-llamas-emotion-bias/index.html @@ -1097,10 +1097,10 @@

    Related

  • Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution
    • -
  • SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems
    • -
  • Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
    • +
  • SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems
    • + diff --git a/publication/2024-myanswerisc/index.html b/publication/2024-myanswerisc/index.html index 4b987512..922b7247 100644 --- a/publication/2024-myanswerisc/index.html +++ b/publication/2024-myanswerisc/index.html @@ -1181,16 +1181,16 @@

    Related

    diff --git a/publication/2024-politicalcompass/index.html b/publication/2024-politicalcompass/index.html index f65f3de6..d04d9df2 100644 --- a/publication/2024-politicalcompass/index.html +++ b/publication/2024-politicalcompass/index.html @@ -1147,15 +1147,15 @@

    Related

    diff --git a/publication/2024-safetyllamas/index.html b/publication/2024-safetyllamas/index.html index ec5f12b7..0988a351 100644 --- a/publication/2024-safetyllamas/index.html +++ b/publication/2024-safetyllamas/index.html @@ -1153,12 +1153,12 @@

    Related