default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDDirk Hovy
Person information
- affiliation: Bocconi University, Milan, Italy
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c102]Antonina Sinelnik, Dirk Hovy:
Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation Campaigns. ACL (Student Research Workshop) 2024: 225-237- [c101]Fabio Pernisi, Dirk Hovy, Paul Röttger:
Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language Models. ACL (Student Research Workshop) 2024: 339-345 - [c100]Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank:
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models. ACL (Findings) 2024: 7407-7416 - [c99]Flor Miriam Plaza del Arco, Amanda Cercas Curry, Alba Cercas Curry
, Gavin Abercrombie, Dirk Hovy:
Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution. ACL (1) 2024: 7682-7696 - [c98]Amanda Cercas Curry, Giuseppe Attanasio, Zeerak Talat, Dirk Hovy:
Classist Tools: Social Class Correlates with Performance in NLP. ACL (1) 2024: 12643-12655 - [c97]Paul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck, Hannah Kirk, Hinrich Schütze, Dirk Hovy:
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models. ACL (1) 2024: 15295-15311 - [c96]Donya Rooein, Paul Röttger, Anastassia Shaitarova, Dirk Hovy:
Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts. BEA 2024: 54-67 - [c95]Lorenzo Lupo, Paul Bose, Mahyar Habibi, Dirk Hovy, Carlo Schwarz:
DADIT: A Dataset for Demographic Classification of Italian Twitter Users and a Comparison of Prediction Methods. LREC/COLING 2024: 4322-4332 - [c94]Flor Miriam Plaza del Arco, Alba Curry, Amanda Cercas Curry, Dirk Hovy:
Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions. LREC/COLING 2024: 5696-5710 - [c93]Amanda Cercas Curry, Zeerak Talat, Dirk Hovy:
Impoverished Language Technology: The Lack of (Social) Class in NLP. LREC/COLING 2024: 8675-8682 - [c92]Eliana Pastor, Alkis Koudounas, Giuseppe Attanasio, Dirk Hovy, Elena Baralis:
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features. EACL (1) 2024: 2221-2238 - [c91]Flor Miriam Plaza del Arco, Amanda Cercas Curry, Susanna Paoli, Alba Cercas Curry, Dirk Hovy:
Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models. EMNLP (Findings) 2024: 4346-4366 - [c90]Giuseppe Attanasio, Beatrice Savoldi, Dennis Fucci, Dirk Hovy:
Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps. EMNLP 2024: 21318-21340 - [c89]Paul Röttger, Hannah Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy:
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models. NAACL-HLT 2024: 5377-5400 - [c88]Nikita Soni, Niranjan Balasubramanian, H. Andrew Schwartz, Dirk Hovy:
Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both? WASSA 2024: 316-328 - [i50]Nikita Soni, Niranjan Balasubramanian, H. Andrew Schwartz, Dirk Hovy:
Comparing Human-Centered Language Modeling: Is it Better to Model Groups, Individual Traits, or Both? CoRR abs/2401.12492 (2024) - [i49]Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank:
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models. CoRR abs/2402.14499 (2024) - [i48]Paul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck, Hannah Rose Kirk, Hinrich Schütze, Dirk Hovy:
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models. CoRR abs/2402.16786 (2024) - [i47]Giuseppe Attanasio, Beatrice Savoldi, Dennis Fucci, Dirk Hovy:
Multilingual Speech Models for Automatic Speech Recognition Exhibit Gender Performance Gaps. CoRR abs/2402.17954 (2024) - [i46]Flor Miriam Plaza del Arco, Alba Curry, Amanda Cercas Curry, Dirk Hovy:
Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions. CoRR abs/2403.01222 (2024) - [i45]Flor Miriam Plaza del Arco, Amanda Cercas Curry, Alba Curry, Gavin Abercrombie, Dirk Hovy:
Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution. CoRR abs/2403.03121 (2024) - [i44]Amanda Cercas Curry, Zeerak Talat, Dirk Hovy:
Impoverished Language Technology: The Lack of (Social) Class in NLP. CoRR abs/2403.03874 (2024) - [i43]Amanda Cercas Curry, Giuseppe Attanasio, Zeerak Talat, Dirk Hovy:
Classist Tools: Social Class Correlates with Performance in NLP. CoRR abs/2403.04445 (2024) - [i42]Lorenzo Lupo, Paul Bose, Mahyar Habibi, Dirk Hovy, Carlo Schwarz:
DADIT: A Dataset for Demographic Classification of Italian Twitter Users and a Comparison of Prediction Methods. CoRR abs/2403.05700 (2024) - [i41]Paul Röttger, Fabio Pernisi, Bertie Vidgen, Dirk Hovy:
SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety. CoRR abs/2404.05399 (2024) - [i40]Donya Rooein, Dirk Hovy:
Conversations as a Source for Teaching Scientific Concepts at Different Education Levels. CoRR abs/2404.10475 (2024) - [i39]Diyi Yang, Dirk Hovy, David Jurgens, Barbara Plank:
The Call for Socially Aware Language Technologies. CoRR abs/2405.02411 (2024) - [i38]Ilia Kuznetsov, Osama Mohammed Afzal, Koen Dercksen, Nils Dycke, Alexander Goldberg, Tom Hope, Dirk Hovy, Jonathan K. Kummerfeld, Anne Lauscher, Kevin Leyton-Brown, Sheng Lu, Mausam, Margot Mieskes, Aurélie Névéol, Danish Pruthi, Lizhen Qu, Roy Schwartz, Noah A. Smith, Thamar Solorio, Jingyan Wang, Xiaodan Zhu, Anna Rogers, Nihar B. Shah, Iryna Gurevych:
What Can Natural Language Processing Do for Peer Review? CoRR abs/2405.06563 (2024) - [i37]Donya Rooein, Paul Röttger, Anastassia Shaitarova, Dirk Hovy:
Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts. CoRR abs/2405.09482 (2024) - [i36]Flor Miriam Plaza del Arco, Amanda Cercas Curry, Susanna Paoli, Alba Curry, Dirk Hovy:
Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models. CoRR abs/2407.06908 (2024) - [i35]Fabio Pernisi, Dirk Hovy, Paul Röttger:
Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models. CoRR abs/2408.04522 (2024) - [i34]Antonina Sinelnik, Dirk Hovy:
Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation Campaigns. CoRR abs/2408.13651 (2024) - 2023
- [j4]Federico Bianchi, Amanda Cercas Curry, Dirk Hovy:
Viewpoint: Artificial Intelligence Accidents Waiting to Happen? J. Artif. Intell. Res. 76: 193-199 (2023) - [c87]Anne Lauscher, Debora Nozza, Ehm Miltersen, Archie Crowley, Dirk Hovy:
What about "em"? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns. ACL (1) 2023: 377-392 - [c86]Matthias Orlikowski, Paul Röttger, Philipp Cimiano, Dirk Hovy:
The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond Sociodemographics. ACL (2) 2023: 1017-1029 - [c85]Debora Nozza, Dirk Hovy:
The State of Profanity Obfuscation in Natural Language Processing Scientific Publications. ACL (Findings) 2023: 3897-3909 - [c84]Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavas:
Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers. EACL (Findings) 2023: 1520-1535 - [c83]Kilian Theil, Dirk Hovy, Heiner Stuckenschmidt:
Top-Down Influence? Predicting CEO Personality and Risk Impact from Speech Transcripts. ICWSM 2023: 832-841 - [c82]Amanda Cercas Curry, Giuseppe Attanasio, Debora Nozza, Dirk Hovy:
MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection. SemEval@ACL 2023: 2067-2074 - [c81]Rishav Hada, Amir Ebrahimi Fard, Sarah Shugars, Federico Bianchi, Patrícia G. C. Rossini, Dirk Hovy, Rebekah Tromble, Nava Tintarev:
Beyond Digital "Echo Chambers": The Role of Viewpoint Diversity in Political Discussion. WSDM 2023: 33-41 - [p1]Federico Bianchi, Tommaso Fornaciari, Dirk Hovy, Debora Nozza:
Gender and Age Bias in Commercial Machine Translation. Towards Responsible Machine Translation 2023: 159-184 - [i33]Gavin Abercrombie, Verena Rieser, Dirk Hovy:
Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreement. CoRR abs/2301.10684 (2023) - [i32]Tommaso Fornaciari, Luca Luceri, Emilio Ferrara, Dirk Hovy:
Leveraging Social Interactions to Detect Misinformation on Social Media. CoRR abs/2304.02983 (2023) - [i31]Anya Belz, Craig Thomson, Ehud Reiter, Gavin Abercrombie, Jose Maria Alonso-Moral, Mohammad Arvan, Jackie Chi Kit Cheung, Mark Cieliebak, Elizabeth Clark, Kees van Deemter, Tanvi Dinkar, Ondrej Dusek, Steffen Eger, Qixiang Fang, Albert Gatt, Dimitra Gkatzia, Javier González-Corbelle, Dirk Hovy, Manuela Hürlimann, Takumi Ito, John D. Kelleher, Filip Klubicka, Huiyuan Lai, Chris van der Lee, Emiel van Miltenburg, Yiru Li, Saad Mahamood, Margot Mieskes, Malvina Nissim, Natalie Parde, Ondrej Plátek, Verena Rieser, Pablo Mosteiro Romero, Joel R. Tetreault, Antonio Toral, Xiaojun Wan, Leo Wanner, Lewis Watson, Diyi Yang:
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP. CoRR abs/2305.01633 (2023) - [i30]Anne Lauscher, Debora Nozza, Archie Crowley, Ehm Miltersen, Dirk Hovy:
What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns. CoRR abs/2305.16051 (2023) - [i29]Matthias Orlikowski, Paul Röttger, Philipp Cimiano, Dirk Hovy:
The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics. CoRR abs/2306.11559 (2023) - [i28]Flor Miriam Plaza del Arco, Debora Nozza, Dirk Hovy:
Leveraging Label Variation in Large Language Models for Zero-Shot Text Classification. CoRR abs/2307.12973 (2023) - [i27]Paul Röttger, Hannah Rose Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy:
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models. CoRR abs/2308.01263 (2023) - [i26]Eliana Pastor, Alkis Koudounas, Giuseppe Attanasio, Dirk Hovy, Elena Baralis:
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features. CoRR abs/2309.07733 (2023) - [i25]Lorenzo Lupo, Oscar Magnusson, Dirk Hovy, Elin Naurin, Lena Wängnerud:
How to Use Large Language Models for Text Coding: The Case of Fatherhood Roles in Public Policy Documents. CoRR abs/2311.11844 (2023) - [i24]Donya Rooein, Amanda Cercas Curry, Dirk Hovy:
Know Your Audience: Do LLMs Adapt to Different Age and Education Levels? CoRR abs/2312.02065 (2023) - 2022
- [c80]Tommaso Fornaciari, Alexandra Uma, Massimo Poesio, Dirk Hovy:
Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa. ACL (demo) 2022: 127-134 - [c79]Giuseppe Attanasio, Debora Nozza, Dirk Hovy, Elena Baralis:
Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists. ACL (Findings) 2022: 1105-1119 - [c78]Emily Dinan, Gavin Abercrombie, A. Stevie Bergman, Shannon L. Spruit, Dirk Hovy, Y-Lan Boureau, Verena Rieser:
SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems. ACL (1) 2022: 4113-4133 - [c77]Anne Lauscher, Archie Crowley, Dirk Hovy:
Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender. COLING 2022: 1221-1232 - [c76]Federico Bianchi, Vincenzo Cutrona, Dirk Hovy:
Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data. EMNLP (Demos) 2022: 289-297 - [c75]Paul Röttger, Debora Nozza, Federico Bianchi, Dirk Hovy:
Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages. EMNLP 2022: 5674-5691 - [c74]Marius Hessenthaler, Emma Strubell, Dirk Hovy, Anne Lauscher:
Bridging Fairness and Environmental Sustainability in Natural Language Processing. EMNLP 2022: 7817-7836 - [c73]Anne Lauscher, Federico Bianchi, Samuel R. Bowman, Dirk Hovy:
SocioProbe: What, When, and Where Language Models Learn about Sociodemographics. EMNLP 2022: 7901-7918 - [c72]Federico Bianchi, Stefanie Anja Hills, Patrícia G. C. Rossini, Dirk Hovy, Rebekah Tromble, Nava Tintarev:
"It's Not Just Hate": A Multi-Dimensional Perspective on Detecting Harmful Speech Online. EMNLP 2022: 8093-8099 - [c71]Debora Nozza, Federico Bianchi, Anne Lauscher, Dirk Hovy:
Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals. LT-EDI 2022: 26-34 - [c70]Paul Röttger, Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert:
Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks. NAACL-HLT 2022: 175-190 - [c69]A. Stevie Bergman, Gavin Abercrombie, Shannon L. Spruit, Dirk Hovy, Emily Dinan, Y-Lan Boureau, Verena Rieser:
Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design. SIGDIAL 2022: 39-52 - [c68]Federico Bianchi, Debora Nozza, Dirk Hovy:
XLM-EMO: Multilingual Emotion Prediction in Social Media Text. WASSA@ACL 2022: 195-203 - [i23]Christoph Kilian Theil, Dirk Hovy, Heiner Stuckenschmidt:
Top-Down Influence? Predicting CEO Personality and Risk Impact from Speech Transcripts. CoRR abs/2201.07670 (2022) - [i22]Federico Bianchi, Vincenzo Cutrona, Dirk Hovy:
Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data. CoRR abs/2201.10986 (2022) - [i21]Anne Lauscher, Archie Crowley, Dirk Hovy:
Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender. CoRR abs/2202.11923 (2022) - [i20]Giuseppe Attanasio, Debora Nozza, Dirk Hovy, Elena Baralis:
Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists. CoRR abs/2203.09192 (2022) - [i19]Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavas:
On the Limitations of Sociodemographic Adaptation with Transformers. CoRR abs/2208.01029 (2022) - [i18]Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavas:
Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers. CoRR abs/2210.07362 (2022) - [i17]Giuseppe Attanasio, Debora Nozza, Federico Bianchi, Dirk Hovy:
Is It Worth the (Environmental) Cost? Limited Evidence for the Benefits of Diachronic Continuous Training. CoRR abs/2210.07365 (2022) - [i16]Debora Nozza, Dirk Hovy:
The State of Profanity Obfuscation in Natural Language Processing. CoRR abs/2210.07595 (2022) - [i15]Paul Röttger, Debora Nozza, Federico Bianchi, Dirk Hovy:
Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages. CoRR abs/2210.11359 (2022) - [i14]Tommaso Fornaciari, Dirk Hovy, Federico Bianchi:
ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds. CoRR abs/2210.14763 (2022) - [i13]Federico Bianchi, Stefanie Anja Hills, Patrícia G. C. Rossini, Dirk Hovy, Rebekah Tromble, Nava Tintarev:
"It's Not Just Hate": A Multi-Dimensional Perspective on Detecting Harmful Speech Online. CoRR abs/2210.15870 (2022) - [i12]Marius Hessenthaler, Emma Strubell, Dirk Hovy, Anne Lauscher:
Bridging Fairness and Environmental Sustainability in Natural Language Processing. CoRR abs/2211.04256 (2022) - [i11]Anne Lauscher, Federico Bianchi, Samuel R. Bowman, Dirk Hovy:
SocioProbe: What, When, and Where Language Models Learn about Sociodemographics. CoRR abs/2211.04281 (2022) - [i10]Rishav Hada, Amir Ebrahimi Fard, Sarah Shugars, Federico Bianchi, Patrícia G. C. Rossini, Dirk Hovy, Rebekah Tromble, Nava Tintarev:
Beyond Digital "Echo Chambers": The Role of Viewpoint Diversity in Political Discussion. CoRR abs/2212.09056 (2022) - 2021
- [j3]Alexandra Uma, Tommaso Fornaciari, Dirk Hovy, Silviu Paun, Barbara Plank, Massimo Poesio:
Learning from Disagreement: A Survey. J. Artif. Intell. Res. 72: 1385-1470 (2021) - [j2]Dirk Hovy, Shrimai Prabhumoye:
Five sources of bias in natural language processing. Lang. Linguistics Compass 15(8) (2021) - [c67]Federico Bianchi, Silvia Terragni, Dirk Hovy:
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence. ACL/IJCNLP (2) 2021: 759-766 - [c66]Tommaso Fornaciari, Dirk Hovy, Elin Naurin, Julia Runeson, Robert Thomson, Pankaj Adhikari:
"We will Reduce Taxes" - Identifying Election Pledges with Language Models. ACL/IJCNLP (Findings) 2021: 3406-3419 - [c65]Federico Bianchi, Dirk Hovy:
On the Gap between Adoption and Understanding in NLP. ACL/IJCNLP (Findings) 2021: 3895-3901 - [c64]Federico Bianchi, Silvia Terragni, Dirk Hovy, Debora Nozza, Elisabetta Fersini:
Cross-lingual Contextualized Topic Models with Zero-shot Learning. EACL 2021: 1676-1683 - [c63]Tommaso Fornaciari, Federico Bianchi, Massimo Poesio, Dirk Hovy:
BERTective: Language Models and Contextual Information for Deception Detection. EACL 2021: 2699-2708 - [c62]Dirk Hovy, Diyi Yang:
The Importance of Modeling Social Factors of Language: Theory and Practice. NAACL-HLT 2021: 588-602 - [c61]Debora Nozza, Federico Bianchi, Dirk Hovy:
HONEST: Measuring Hurtful Sentence Completion in Language Models. NAACL-HLT 2021: 2398-2406 - [c60]Tommaso Fornaciari, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, Massimo Poesio:
Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning. NAACL-HLT 2021: 2591-2597 - [c59]Sotiris Lamprinidis, Federico Bianchi, Daniel Hardt, Dirk Hovy:
Universal Joy A Data Set and Results for Classifying Emotions Across Languages. WASSA@EACL 2021: 62-75 - [c58]Federico Bianchi, Debora Nozza, Dirk Hovy:
FEEL-IT: Emotion and Sentiment Classification for the Italian Language. WASSA@EACL 2021: 76-83 - [c57]Tommaso Fornaciari, Federico Bianchi, Debora Nozza, Dirk Hovy:
MilaNLP @ WASSA: Does BERT Feel Sad When You Cry? WASSA@EACL 2021: 269-273 - [i9]Emily Dinan, Gavin Abercrombie, A. Stevie Bergman, Shannon L. Spruit, Dirk Hovy, Y-Lan Boureau, Verena Rieser:
Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling. CoRR abs/2107.03451 (2021) - [i8]Federico Bianchi, Debora Nozza, Dirk Hovy:
Language Invariant Properties in Natural Language Processing. CoRR abs/2109.13037 (2021) - [i7]Paul Röttger, Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert:
Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks. CoRR abs/2112.07475 (2021) - 2020
- [c56]Emily M. Bender, Dirk Hovy, Alexandra Schofield:
Integrating Ethics into the NLP Curriculum. ACL (tutorial) 2020: 6-9 - [c55]Dirk Hovy, Federico Bianchi, Tommaso Fornaciari:
"You Sound Just Like Your Father" Commercial Machine Translation Systems Include Stylistic Biases. ACL 2020: 1686-1690 - [c54]Deven Shah, H. Andrew Schwartz, Dirk Hovy:
Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview. ACL 2020: 5248-5264 - [c53]Farzana Rashid, Tommaso Fornaciari, Dirk Hovy, Eduardo Blanco, Fernando Vega-Redondo:
Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success. EMNLP (Findings) 2020: 2366-2371 - [c52]Alexandra Uma, Tommaso Fornaciari, Dirk Hovy, Silviu Paun, Barbara Plank, Massimo Poesio:
A Case for Soft Loss Functions. HCOMP 2020: 173-177 - [c51]Mihaela Gaman, Dirk Hovy, Radu Tudor Ionescu, Heidi Jauhiainen, Tommi Jauhiainen, Krister Lindén, Nikola Ljubesic, Niko Partanen, Christoph Purschke, Yves Scherrer, Marcos Zampieri:
A Report on the VarDial Evaluation Campaign 2020. VarDial@COLING 2020: 1-14 - [i6]Debora Nozza, Federico Bianchi, Dirk Hovy:
What the [MASK]? Making Sense of Language-Specific BERT Models. CoRR abs/2003.02912 (2020) - [i5]Federico Bianchi, Silvia Terragni, Dirk Hovy:
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence. CoRR abs/2004.03974 (2020) - [i4]Federico Bianchi, Silvia Terragni, Dirk Hovy, Debora Nozza, Elisabetta Fersini:
Cross-lingual Contextualized Topic Models with Zero-shot Learning. CoRR abs/2004.07737 (2020)
2010 – 2019
- 2019
- [c50]Hanh Nguyen, Dirk Hovy:
Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers. W-NUT@EMNLP 2019: 76-83 - [c49]Tommaso Fornaciari, Dirk Hovy:
Geolocation with Attention-Based Multitask Learning Models. W-NUT@EMNLP 2019: 217-223 - [c48]Tommaso Fornaciari, Dirk Hovy:
Dense Node Representation for Geolocation. W-NUT@EMNLP 2019: 224-230 - [c47]Tommaso Fornaciari, Dirk Hovy:
Identifying Linguistic Areas for Geolocation. W-NUT@EMNLP 2019: 231-236 - [c46]Dirk Hovy:
Recognizing and Reducing Bias in NLP Applications. CLiC-it 2019 - [i3]Deven Shah, H. Andrew Schwartz, Dirk Hovy:
Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview. CoRR abs/1912.11078 (2019) - 2018
- [j1]Silviu Paun, Bob Carpenter, Jon Chamberlain, Dirk Hovy, Udo Kruschwitz, Massimo Poesio:
Comparing Bayesian Models of Annotation. Trans. Assoc. Comput. Linguistics 6: 571-585 (2018) - [c45]Dirk Hovy:
The Social and the Neural Network: How to Make Natural Language Processing about People again. PEOPLES@NAACL-HTL 2018: 42-49 - [c44]Sotiris Lamprinidis, Daniel Hardt, Dirk Hovy:
Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning. EMNLP 2018: 659-664 - [c43]Dirk Hovy, Tommaso Fornaciari:
Improving Author Attribute Prediction by Retrofitting Linguistic Representations with Homophily. EMNLP 2018: 671-677 - [c42]Dirk Hovy, Christoph Purschke:
Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting. EMNLP 2018: 4383-4394 - [e5]Mark Alfano, Dirk Hovy, Margaret Mitchell, Michael Strube:
Proceedings of the Second ACL Workshop on Ethics in Natural Language Processing, EthNLP@NAACL-HLT 2018, New Orleans, Louisiana, USA, June 5, 2018. Association for Computational Linguistics 2018, ISBN 978-1-948087-14-8 [contents] - 2017
- [c41]Bahar Salehi, Dirk Hovy, Eduard H. Hovy, Anders Søgaard:
Huntsville, hospitals, and hockey teams: Names can reveal your location. NUT@EMNLP 2017: 116-121 - [c40]Adrian Benton, Margaret Mitchell, Dirk Hovy:
Multitask Learning for Mental Health Conditions with Limited Social Media Data. EACL (1) 2017: 152-162 - [c39]Rasmus Berg Palm, Dirk Hovy, Florian Laws, Ole Winther:
End-to-End Information Extraction without Token-Level Supervision. SCNLP@EMNLP 2017 2017: 48-52 - [e4]Zeerak Waseem, Wendy Hui Kyong Chung, Dirk Hovy, Joel R. Tetreault:
Proceedings of the First Workshop on Abusive Language Online, ALW@ACL 2017, Vancouver, BC, Canada, August 4, 2017. Association for Computational Linguistics 2017, ISBN 978-1-945626-66-1 [contents] - [e3]Dirk Hovy, Svitlana Volkova, David Bamman, David Jurgens, Brendan O'Connor, Oren Tsur, A. Seza Dogruöz:
Proceedings of the Second Workshop on NLP and Computational Social Science, NLP+CSS@ACL 2017, Vancouver, Canada, August 3, 2017. Association for Computational Linguistics 2017, ISBN 978-1-945626-65-4 [contents] - [e2]Dirk Hovy, Shannon L. Spruit, Margaret Mitchell, Emily M. Bender, Michael Strube, Hanna M. Wallach:
Proceedings of the First ACL Workshop on Ethics in Natural Language Processing, EthNLP@EACL, Valencia, Spain, April 4, 2017. Association for Computational Linguistics 2017, ISBN 978-1-945626-47-0 [contents] - [i2]Rasmus Berg Palm, Dirk Hovy, Florian Laws, Ole Winther:
End-to-End Information Extraction without Token-Level Supervision. CoRR abs/1707.04913 (2017) - [i1]Adrian Benton, Margaret Mitchell, Dirk Hovy:
Multi-Task Learning for Mental Health using Social Media Text. CoRR abs/1712.03538 (2017) - 2016
- [c38]Gavin Abercrombie, Dirk Hovy:
Putting Sarcasm Detection into Context: The Effects of Class Imbalance and Manual Labelling on Supervised Machine Classification of Twitter Conversations. ACL (Student Research Workshop) 2016: 107-113 - [c37]Dirk Hovy:
The Enemy in Your Own Camp: How Well Can We Detect Statistically-Generated Fake Reviews - An Adversarial Study. ACL (2) 2016 - [c36]Dirk Hovy, Shannon L. Spruit:
The Social Impact of Natural Language Processing. ACL (2) 2016 - [c35]Dirk Hovy, Anders Johannsen:
Exploring Language Variation Across Europe - A Web-based Tool for Computational Sociolinguistics. LREC 2016 - [c34]Zeerak Waseem, Dirk Hovy:
Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter. SRW@HLT-NAACL 2016: 88-93 - [c33]Anna Jørgensen, Dirk Hovy, Anders Søgaard:
Learning a POS tagger for AAVE-like language. HLT-NAACL 2016: 1115-1120 - [c32]Nathan Schneider, Dirk Hovy, Anders Johannsen, Marine Carpuat:
SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM). SemEval@NAACL-HLT 2016: 546-559 - [e1]David Bamman, A. Seza Dogruöz, Jacob Eisenstein, Dirk Hovy, David Jurgens, Brendan O'Connor, Alice Oh, Oren Tsur, Svitlana Volkova:
Proceedings of the First Workshop on NLP and Computational Social Science, NLP+CSS@EMNLP 2016, Austin, TX, USA, November 5, 2016. Association for Computational Linguistics 2016, ISBN 978-1-945626-26-5 [contents] - 2015
- [c31]Zeljko Agic, Dirk Hovy, Anders Søgaard:
If all you have is a bit of the Bible: Learning POS taggers for truly low-resource languages. ACL (2) 2015: 268-272 - [c30]Dirk Hovy, Anders Søgaard:
Tagging Performance Correlates with Author Age. ACL (2) 2015: 483-488 - [c29]Dirk Hovy:
Demographic Factors Improve Classification Performance. ACL (1) 2015: 752-762 - [c28]Anna Jørgensen, Dirk Hovy, Anders Søgaard:
Challenges of studying and processing dialects in social media. NUT@IJCNLP 2015: 9-18 - [c27]Anders Johannsen, Dirk Hovy, Anders Søgaard:
Cross-lingual syntactic variation over age and gender. CoNLL 2015: 103-112 - [c26]Lasse Borgholt, Peter Simonsen, Dirk Hovy:
The Rating Game: Sentiment Rating Reproducibility from Text. EMNLP 2015: 2527-2532 - [c25]Dirk Hovy, Barbara Plank, Héctor Martínez Alonso, Anders Søgaard:
Mining for unambiguous instances to adapt part-of-speech taggers to new domains. HLT-NAACL 2015: 1256-1261 - [c24]Barbara Plank, Dirk Hovy:
Personality Traits on Twitter - or - How to Get 1, 500 Personality Tests in a Week. WASSA@EMNLP 2015: 92-98 - [c23]Dirk Hovy, Anders Johannsen, Anders Søgaard:
User Review Sites as a Resource for Large-Scale Sociolinguistic Studies. WWW 2015: 452-461 - 2014
- [c22]Dirk Hovy, Barbara Plank, Anders Søgaard:
Experiments with crowdsourced re-annotation of a POS tagging data set. ACL (2) 2014: 377-382 - [c21]Dirk Hovy:
How Well can We Learn Interpretable Entity Types from Text? ACL (2) 2014: 482-487 - [c20]Barbara Plank, Dirk Hovy, Anders Søgaard:
Linguistically debatable or just plain wrong? ACL (2) 2014: 507-511 - [c19]Anders Søgaard, Barbara Plank, Dirk Hovy:
Selection Bias, Label Bias, and Bias in Ground Truth. COLING (Tutorials) 2014: 11-13 - [c18]Barbara Plank, Dirk Hovy, Ryan T. McDonald, Anders Søgaard:
Adapting taggers to Twitter with not-so-distant supervision. COLING 2014: 1783-1792 - [c17]Anders Søgaard, Anders Johannsen, Barbara Plank, Dirk Hovy, Héctor Martínez Alonso:
What's in a p-value in NLP? CoNLL 2014: 1-10 - [c16]Barbara Plank, Dirk Hovy, Anders Søgaard:
Learning part-of-speech taggers with inter-annotator agreement loss. EACL 2014: 742-751 - [c15]Hege Fromreide, Dirk Hovy, Anders Søgaard:
Crowdsourcing and annotating NER for Twitter #drift. LREC 2014: 2544-2547 - [c14]Yulia Tsvetkov, Nathan Schneider, Dirk Hovy, Archna Bhatia, Manaal Faruqui, Chris Dyer:
Augmenting English Adjective Senses with Supersenses. LREC 2014: 4359-4365 - [c13]Dirk Hovy, Barbara Plank, Anders Søgaard:
When POS data sets don't add up: Combatting sample bias. LREC 2014: 4472-4475 - [c12]Natalie Schluter, Anders Søgaard, Jakob Elming, Dirk Hovy, Barbara Plank, Héctor Martínez Alonso, Anders Johannsen, Sigrid Klerke:
Copenhagen-Malmö: Tree Approximations of Semantic Parsing Problems. SemEval@COLING 2014: 213-217 - [c11]Anders Johannsen, Dirk Hovy, Héctor Martínez Alonso, Barbara Plank, Anders Søgaard:
More or less supervised supersense tagging of Twitter. *SEM@COLING 2014: 1-11 - [c10]Jakob Elming, Barbara Plank, Dirk Hovy:
Robust Cross-Domain Sentiment Analysis for Low-Resource Languages. WASSA@ACL 2014: 2-7 - 2013
- [c9]Shashank Srivastava, Dirk Hovy, Eduard H. Hovy:
A Walk-Based Semantically Enriched Tree Kernel Over Distributed Word Representations. EMNLP 2013: 1411-1416 - [c8]Dirk Hovy, Gopala Krishna Anumanchipalli, Alok Parlikar, Caroline Vaughn, Adam C. Lammert, Eduard H. Hovy, Alan W. Black:
Analysis and modeling of "focus" in context. INTERSPEECH 2013: 402-406 - [c7]Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, Eduard H. Hovy:
Learning Whom to Trust with MACE. HLT-NAACL 2013: 1120-1130 - [c6]Mrinmaya Sachan, Dirk Hovy, Eduard H. Hovy:
Solving electrical networks to incorporate supervision in random walks. WWW (Companion Volume) 2013: 109-110 - 2012
- [c5]Dirk Hovy, James Fan, Alfio Massimiliano Gliozzo, Siddharth Patwardhan, Christopher A. Welty:
When Did that Happen? - Linking Events and Relations to Timestamps. EACL 2012: 185-193 - 2011
- [c4]Dirk Hovy, Ashish Vaswani, Stephen Tratz, David Chiang, Eduard H. Hovy:
Models and Training for Unsupervised Preposition Sense Disambiguation. ACL (2) 2011: 323-328 - [c3]Dirk Hovy, Chunliang Zhang, Eduard H. Hovy, Anselmo Peñas:
Unsupervised Discovery of Domain-Specific Knowledge from Text. ACL 2011: 1466-1475 - 2010
- [c2]Dirk Hovy, Stephen Tratz, Eduard H. Hovy:
What's in a Preposition? Dimensions of Sense Disambiguation for an Interesting Word Class. COLING (Posters) 2010: 454-462
2000 – 2009
- 2009
- [c1]Stephen Tratz, Dirk Hovy:
Disambiguation of Preposition Sense Using Linguistically Motivated Features. HLT-NAACL (Student Research Workshop and Doctoral Consortium) 2009: 96-100
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-19 21:41 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
