📰 BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022 — accepted papers

BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022 is the 2022 edition of the BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, held in Abu Dhabi, United Arab Emirates (Hybrid), December 2022 (publisher: Association for Computational Linguistics). The ACL Anthology lists 37 papers of it; our library holds 1 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image ModelsRoyi Rassin, Shauli Ravfogel, Yoav Goldberg39 citations
2. Probing Pretrained Models of Source CodesSergey Troshin, Nadezhda Chirkova21 citations
3. Probing GPT-3's Linguistic Knowledge on Semantic TasksLining Zhang, Mengchen Wang, Liben Chen et al.11 citations
4. On the Compositional Generalization Gap of In-Context LearningArian Hosseini, Ankit Vani, Dzmitry Bahdanau et al.10 citations
5. It Is Not Easy To Detect Paraphrases: Analysing Semantic Similarity With Antonyms and Negation Using the New SemAntoNeg BenchmarkTeemu Vahtola, Mathias Creutz, Jörg Tiedemann9 citations
6. Explaining Translationese: why are Neural Classifiers Better and what do they Learn?Kwabena Amponsah-Kaakyire, Daria Pylypenko, Josef Genabith et al.7 citations
7. Are Multilingual Sentiment Models Equally Right for the Right Reasons?Rasmus Jørgensen, Fiammetta Caccavale, Christian Igel et al.6 citations
8. Sparse Interventions in Language Models with Differentiable MaskingNicola De Cao, Leon Schmid, Dieuwke Hupkes et al.6 citations
9. Decomposing Natural Logic Inferences for Neural NLIJulia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan et al.5 citations · our summary
10. Investigating the Characteristics of a Transformer in a Few-Shot Setup: Does Freezing Layers in RoBERTa Help?Digvijay Ingle, Rishabh Tripathi, Ayush Kumar et al.5 citations

All accepted papers (37)

The most cited first; 1 with our summary link to their page here, the others to the original.

1. DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image ModelsRoyi Rassin, Shauli Ravfogel, Yoav Goldberg39 citations
2. Probing Pretrained Models of Source CodesSergey Troshin, Nadezhda Chirkova21 citations
3. Probing GPT-3's Linguistic Knowledge on Semantic TasksLining Zhang, Mengchen Wang, Liben Chen et al.11 citations
4. On the Compositional Generalization Gap of In-Context LearningArian Hosseini, Ankit Vani, Dzmitry Bahdanau et al.10 citations
5. It Is Not Easy To Detect Paraphrases: Analysing Semantic Similarity With Antonyms and Negation Using the New SemAntoNeg BenchmarkTeemu Vahtola, Mathias Creutz, Jörg Tiedemann9 citations
6. Explaining Translationese: why are Neural Classifiers Better and what do they Learn?Kwabena Amponsah-Kaakyire, Daria Pylypenko, Josef Genabith et al.7 citations
7. Are Multilingual Sentiment Models Equally Right for the Right Reasons?Rasmus Jørgensen, Fiammetta Caccavale, Christian Igel et al.6 citations
8. Sparse Interventions in Language Models with Differentiable MaskingNicola De Cao, Leon Schmid, Dieuwke Hupkes et al.6 citations
9. Decomposing Natural Logic Inferences for Neural NLIJulia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan et al.5 citations · our summary
10. Investigating the Characteristics of a Transformer in a Few-Shot Setup: Does Freezing Layers in RoBERTa Help?Digvijay Ingle, Rishabh Tripathi, Ayush Kumar et al.5 citations
11. Garden Path Traversal in GPT-2William Jurayj, William Rudman, Carsten Eickhoff4 citations
12. Practical Benefits of Feature Feedback Under Distribution ShiftAnurag Katakkar, Clay H. Yoo, Weiqin Wang et al.4 citations
13. Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment InformationIsar Nejadgholi, Esma Balkir, Kathleen Fraser et al.4 citations
14. Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model PredictionsJenny Kunz, Martin Jirenius, Oskar Holmström et al.3 citations
15. Probing with Noise: Unpicking the Warp and Weft of EmbeddingsFilip Klubicka, John Kelleher3 citations
16. Understanding Domain Learning in Language Models Through Subpopulation AnalysisZheng Zhao, Yftah Ziser, Shay B. Cohen3 citations
17. Look to the Right: Mitigating Relative Position Bias in Extractive Question AnsweringKazutoshi Shinoda, Saku Sugawara, Akiko Aizawa2 citations
18. Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting MachinesKiron Deb, Xuan Zhang, Kevin Duh2 citations
19. Post-hoc analysis of Arabic transformer modelsAhmed Abdelali, Nadir Durrani, Fahim Dalvi et al.2 citations
20. Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language ModelsDavid Yi, James Bruno, Jiayu Han et al.2 citations
21. Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation AnalysisPangbo Ban, Yifan Jiang, Tianran Liu et al.2 citations
22. A Continuum of Generation Tasks for Investigating Length Bias and Degenerate RepetitionDarcey Riley, David Chiang1 citation
23. A Minimal Model for Compositional Generalization on gSCANAlice Hein, Klaus Diepold1 citation
24. Analyzing Gender Translation Errors to Identify Information Flows between the Encoder and Decoder of a NMT SystemGuillaume Wisniewski, Lichao Zhu, Nicolas Ballier et al.1 citation
25. Analyzing the Representational Geometry of Acoustic Word EmbeddingsBadr Abdullah, Dietrich Klakow1 citation

See all 37 papers in BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022 — accepted papers →

📄 Papers with our summary in our library (1)

The most cited first (OpenAlex citations plus our library's).

1. Decomposing Natural Logic Inferences for Neural NLIBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLPJulia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, et al.2022 · 8 citations

🧭 Top topics

Topics of its works in our library, with the number of works on each.

🧮Reasoning (1)

📚 Fields

🎭Arts and Humanities (1)🖥️Computer Science (1)

🧑‍🔬 Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

🏛️ Top institutions

Institutions on the bylines of its works here, by the number of works.

🎓University of ManchesterManchester · United Kingdom1 work here🔬Idiap Research InstituteMartigny-Combe · Switzerland1 work here

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/blackboxnlp/2022/