Papers by Roger Wattenhofer
Text Compression for Efficient Language Generation (2025.naacl-srw)
Copied to clipboard
| Challenge: | Existing models rely on sub-word tokens for text generation, but there is no evidence for a more efficient way to generate text. |
| Approach: | They propose a hierarchical transformer language model capable of text generation by compressing text into sentence embeddings and employing a sentence attention mechanism. |
| Outcome: | The proposed model achieves an up to an order of magnitude improvement in FLOPs efficiency and a threefold increase in runtime speed compared to equally-sized models in the low-size regime. |
ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting (2025.acl-long)
Copied to clipboard
Steven H Wang, Maksim Zubkov, Kexin Fan, Sarah Harrell, Yuyang Sun, Wei Chen, Andreas Plesner, Roger Wattenhofer
| Challenge: | Contract clause retrieval is critical to contract drafting because of its high quality and complexity. |
| Approach: | They propose the first expert-annotated benchmark specifically designed for contract clause retrieval . ACORD focuses on complex contract clauses such as Limitation of Liability, Indemnification, Change of Control . |
| Outcome: | The atticus clause retrieval dataset shows promising results but needs improvement . the benchmark can be used as an IR benchmark for the NLP community . |
A Plug-and-Play Method for Controlled Text Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for controlling language generation are not able to produce fluent text . current methods require additional models or fine-tuning to ensure specific words are included . |
| Approach: | They propose a plug-and-play decoding method that allows for controlled language generation . they add a shift in the probability distribution over our vocabulary towards semantically similar words . |
| Outcome: | The proposed method outperforms competing methods in human evaluations and does not impact fluency. |
Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to improve model robustness against word substitution-based adversarial attacks are too slow to generate adversarials on the fly. |
| Approach: | They propose an approach to improve the robustness of BERT models against word substitution-based adversarial attacks by leveraging adversarials for self-supervised contrastive learning. |
| Outcome: | The proposed method improves robustness of BERT models against word substitution-based adversarial attacks without using any labeled data. |
KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models for visual and language understanding are not capable of multimodal reasoning. |
| Approach: | They propose a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. |
| Outcome: | The proposed model performs state-of-the-art on the Visual Commonsense Generation task. |
Telling BERT’s Full Story: from Local Attention to Global Aggregation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent work discouraging the use of attention distributions for explaining a model’s behaviour suggests that attention distribution can provide insights into local behaviour of attention heads. |
| Approach: | They propose a distinction between local patterns revealed by attention and global patterns that refer back to the input and analyze BERT from both angles. |
| Outcome: | The proposed model can explain local behaviour of attention heads by comparing local and global patterns from both angles. |
A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples (2020.coling-main)
Copied to clipboard
| Challenge: | Existing techniques to generate adversarial examples for natural language are limited . previous research on adversarials focused on images, but this is not the case with natural language. |
| Approach: | They propose a geometry-inspired attack for generating natural language adversarial examples . they use deep neural networks to iteratively approximate the decision boundary . |
| Outcome: | The proposed attack fools natural language models with high success rates while replacing a few words. |
UltraSparseBERT: 99% Conditionally Sparse Language Modelling (2024.acl-short)
Copied to clipboard
| Challenge: | UltraSparseBERT uses 0.3% of its neurons during inference, compared to similar BERT models. |
| Approach: | They propose a BERT variant that selectively engages just 12 out of 4095 neurons for each layer inference. |
| Outcome: | The proposed model employs 0.3% of its neurons during inference while performing on par with similar models. |
Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for zero-shot text classification involve heavy human engineering or complicated self-training pipelines. |
| Approach: | They propose to fit unlabeled text with a Bayesian Gaussian Mixture Model and use class names to cluster them. |
| Outcome: | The proposed approach outperforms prompt-based methods on topic and sentiment datasets and outperformed previous studies significantly on unbalanced datasets. |