Benjamin Heinzerling

Latest

• Monotonic Representation of Numeric Attributes in Language Models
• ACORN: Aspect-wise Commonsense Reasoning Explanation Evaluation
• The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models
• Test-time Augmentation for Factual Probing
• Can LMs Store and Retrieve 1-to-N Relational Knowledge?
• Prompting for explanations improves Adversarial NLI. Is this true? Yes it is true because it weakens superficial cues
• BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
• Examining the effect of whitening on static and contextualized word embeddings
• Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction
• Tracing and Manipulating intermediate values in Neural Math Problem Solvers
• COPA-SSE: Semi-structured Explanations for Commonsense Reasoning
• Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries
• Learning to Learn to be Right for the Right Reasons
• NLP's Clever Hans Moment has Arrived
• On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages
• When Choosing Plausible Alternatives, Clever Hans can be Clever
• Fine-Grained Entity Typing in Hyperbolic Space
• NLP's Clever Hans Moment has Arrived
• Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation
• BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages
• Revisiting Selectional Preferences for Coreference Resolution
• Trust, but Verify! Better Entity Linking through Automatic Verification
• Visual Error Analysis for Entity Linking
• HITS at TAC KBP 2015: Entity discovery and linking, and event nugget detection
• HITS' Monolingual and Cross-lingual Entity Linking System at TAC 2014
• HITS' Monolingual and Cross-lingual Entity Linking System at TAC 2013