Nome |
# |
Pipelines for social bias testing of large language models, file f7980a13-e6ba-4f66-8311-4f3f1a3626bc
|
1.354
|
The importance of modeling social factors of language: theory and practice, file e31e10d4-7912-31fb-e053-1705fe0a5b99
|
1.104
|
Measuring harmful sentence completion in language models for LGBTQIA+ individuals, file 442bf186-670e-40a4-93dd-71f79640d8f0
|
903
|
HONEST: measuring hurtful sentence completion in language models, file e31e10d4-7910-31fb-e053-1705fe0a5b99
|
785
|
SafetyKit: first aid for measuring safety in open-domain conversational systems, file 9ee7908c-a74f-4bca-9ece-a2e00db5f1b6
|
751
|
Beyond black & white: leveraging annotator disagreement via soft-label multi-task learning, file e31e10d4-6f0e-31fb-e053-1705fe0a5b99
|
695
|
FEEL-IT: emotion and sentiment classification for the Italian language, file e31e10d4-7b51-31fb-e053-1705fe0a5b99
|
619
|
Multitask learning for mental health conditions with limited social media data, file e31e10d4-aad6-31fb-e053-1705fe0a5b99
|
522
|
Five sources of bias in natural language processing, file e31e10d4-7639-31fb-e053-1705fe0a5b99
|
440
|
BERTective: language models and contextual information for deception detection, file e31e10d4-72fc-31fb-e053-1705fe0a5b99
|
397
|
Benchmarking post-hoc interpretability approaches for transformer-based misogyny detection, file dd2e13b2-7991-45ef-93ce-3a0e94a7d859
|
382
|
Guiding the release of safer E2E conversational AI through value sensitive design, file dc4c9d96-9359-4ff5-bf49-00e445022e9e
|
354
|
Respectful or toxic? Using zero-shot learning with language models to detect hate speech, file 4a8fb2c4-30d6-487c-acd5-2e075034cea1
|
268
|
Learning a POS tagger for AAVE-like language, file e31e10d4-a9dd-31fb-e053-1705fe0a5b99
|
255
|
Universal joy: a data set and results for classifying emotions across languages, file e31e10d4-7e5b-31fb-e053-1705fe0a5b99
|
180
|
Hey Siri. Ok Google. Alexa: a topic modeling of user reviews for smart speakers, file e31e10d3-c1e5-31fb-e053-1705fe0a5b99
|
149
|
Geolocation with attention-based multitask learning models, file e31e10d3-c1eb-31fb-e053-1705fe0a5b99
|
143
|
Pre-training is a hot topic: contextualized document embeddings improve topic coherence, file e31e10d4-790e-31fb-e053-1705fe0a5b99
|
123
|
“We will reduce taxes” - Identifying election pledges with language models, file e31e10d4-72ff-31fb-e053-1705fe0a5b99
|
117
|
The state of profanity obfuscation in Natural Language Processing scientific publications, file c5e8ed0f-cc25-4607-bc74-a66a5c9ed0bb
|
112
|
Identifying linguistic areas for geolocation, file e31e10d3-c1e9-31fb-e053-1705fe0a5b99
|
96
|
Predicting news headline popularity with syntactic and semantic knowledge using multi-task learning, file e31e10d3-87bf-31fb-e053-1705fe0a5b99
|
94
|
MilaNLP @ WASSA: does BERT feel sad when you cry?, file e31e10d4-72fd-31fb-e053-1705fe0a5b99
|
82
|
Hard and soft evaluation of NLP models with BOOtSTrap SAmpling - BooStSa, file 930704e4-734f-4c98-b1f6-cb82f9429863
|
73
|
Dense node representation for geolocation, file e31e10d3-c1ee-31fb-e053-1705fe0a5b99
|
68
|
Can demographic factors improve text classification? Revisiting demographic adaptation in the age of transformers, file b7eafdbf-df44-43a5-8e02-628518046121
|
67
|
Increasing in-class similarity by retrofitting embeddings with demographic information, file e31e10d3-c57f-31fb-e053-1705fe0a5b99
|
64
|
Comparing Bayesian models of annotation, file e31e10d3-c63a-31fb-e053-1705fe0a5b99
|
64
|
Helpful or hierarchical? Predicting the communicative strategies of chat participants, and their impact on success, file e31e10d4-27ef-31fb-e053-1705fe0a5b99
|
64
|
Women’s syntactic resilience and men’s grammatical luck: gender-bias in part-of-speech tagging and dependency parsing, file e31e10d3-c570-31fb-e053-1705fe0a5b99
|
60
|
The social and the neural network: how to make natural language processing about people again, file e31e10d3-c650-31fb-e053-1705fe0a5b99
|
55
|
A case for soft loss functions, file e31e10d4-2923-31fb-e053-1705fe0a5b99
|
54
|
Predictive biases in natural language processing models: a conceptual framework and overview, file e31e10d4-2815-31fb-e053-1705fe0a5b99
|
52
|
“You sound just like your father”. Commercial machine translation systems include stylistic biases, file e31e10d4-2817-31fb-e053-1705fe0a5b99
|
44
|
Capturing regional variation with distributed place representations and geographic retrofitting, file e31e10d3-87be-31fb-e053-1705fe0a5b99
|
43
|
Welcome to the modern world of pronouns: identity-inclusive Natural Language Processing beyond gender, file 5caed632-82d4-4df3-be1b-b2f847723b5f
|
42
|
We need to consider disagreement in evaluation, file e31e10d4-725c-31fb-e053-1705fe0a5b99
|
30
|
On the gap between adoption and understanding in NLP, file e31e10d4-7658-31fb-e053-1705fe0a5b99
|
29
|
Viewpoint: Artificial Intelligence accidents waiting to happen?, file c8c718f4-1002-4b8b-bd8e-864a53691737
|
28
|
Learning from disagreement: a survey, file ac01011f-c459-4daf-8aeb-5793b0bcade5
|
27
|
Entropy-based attention regularization frees unintended bias mitigation from lists, file f9bd81ff-903a-4b7e-9143-5b7c5089b7a0
|
27
|
Cross-lingual contextualized topic models with zero-shot learning, file e31e10d4-7656-31fb-e053-1705fe0a5b99
|
26
|
Two contrasting data annotation paradigms for subjective NLP tasks, file 0600cf7e-52fb-406f-8b62-e7a616b017cf
|
22
|
MilaNLP at SemEval-2023 Task 10: ensembling domain-adapted and regularized pretrained language models for robust sexism detection, file 00d41fe7-67a1-435b-8dee-1f44c7bb4b17
|
21
|
Language invariant properties in Natural Language Processing, file 6d2bf7d9-300a-43e6-84de-cd025b325581
|
20
|
"It's not just hate": a multi-dimensional perspective on detecting harmful speech online, file d1b46c69-10c2-4990-9a44-f38dc13ab2e7
|
19
|
XLM-EMO: multilingual emotion prediction in social media text, file dc06b5ac-3cac-4f2d-a7c3-10282ba182f3
|
18
|
SocioProbe: what, when, and where language models learn about sociodemographics, file 92414e9d-a58b-4254-8877-9c6387b8a215
|
14
|
The ecological fallacy in annotation: modeling human label variation goes beyond sociodemographics, file fec1c2c6-8690-4f74-85ac-ffffbe380572
|
14
|
Data-efficient strategies for expanding hate speech detection into under-resourced languages, file 3dde6ad8-fcac-4b61-a106-7f4147585a50
|
11
|
Bridging fairness and environmental sustainability in natural language processing, file dd6626f8-6544-458a-af48-9c5d4afbc429
|
11
|
Twitter-demographer: a flow-based tool to enrich Twitter data, file 1db52899-8354-4385-9c10-db459eb32546
|
10
|
Hateful symbols or hateful people? Predictive features for hate speech detection on Twitter, file ed4adf69-baec-46a2-b738-59d4947df732
|
8
|
What about em? How commercial Machine Translation fails to handle (neo-)pronouns, file 07523bb3-8226-4d9d-b9cf-0e63ea43546e
|
7
|
What’s in a p-value in NLP?, file e31e10d3-1ce1-31fb-e053-1705fe0a5b99
|
2
|
Lörres, Möppes, and the Swiss. (Re)Discovering regional patterns in anonymous social media data, file e31e10d3-c1e1-31fb-e053-1705fe0a5b99
|
2
|
Beyond digital "echo chambers": the role of viewpoint diversity in political discussion, file 22f71c78-d9b4-47fd-bcb9-df853af42e20
|
1
|
Demographic factors improve classification performance, file bc37e30f-a50f-4a93-bcd4-5477aa4f95d1
|
1
|
A Walk-Based Semantically Enriched Tree Kernel Over Distributed Word Representations, file e31e10d3-2185-31fb-e053-1705fe0a5b99
|
1
|
Learning whom to trust with MACE, file e31e10d3-2187-31fb-e053-1705fe0a5b99
|
1
|
Augmenting English adjective senses with supersenses, file e31e10d3-225c-31fb-e053-1705fe0a5b99
|
1
|
Text analysis in Python for social scientists: discovery and exploration, file e31e10d4-27ec-31fb-e053-1705fe0a5b99
|
1
|
Wordify: a tool for discovering and differentiating consumer vocabularies, file e31e10d4-7ab9-31fb-e053-1705fe0a5b99
|
1
|
Text analysis in Python for social scientists : prediction and classification, file e31e10d4-a6bc-31fb-e053-1705fe0a5b99
|
1
|
Totale |
11.029 |