Papers by Edwin Simpson
A Bayesian Approach for Sequence Tagging with Crowds (D19-1)
Copied to clipboard
| Challenge: | Existing methods for sequence tagging are data hungry and annotators are unreliable . current methods do not account for common types of span annotation error . |
| Approach: | They propose a Bayesian method for aggregating sequence tags that models sequential dependencies between annotations and ground-truth labels. |
| Outcome: | The proposed method outperforms existing methods on crowdsourced data and reduces crowdsourcing costs through active learning. |
Interactive Text Ranking with Bayesian Optimization: A Case Study on Community QA and Summarization (2020.tacl-1)
Copied to clipboard
| Challenge: | Existing methods that focus on learning a ranking across the whole candidate space are lacking user or task-specific training data. |
| Approach: | They propose an interactive ranking approach that actively selects pairs of candidates, from which the user selects the best. |
| Outcome: | The proposed approach outperforms existing methods in community question answering and extractive multidocument summarization and is an effective reward function for reinforcement learning. |
Efficient Methods for Natural Language Processing: A Survey (2023.tacl-1)
Copied to clipboard
Marcos Treviso, Ji-Ung Lee, Tianchu Ji, Betty van Aken, Qingqing Cao, Manuel R. Ciosici, Michael Hassid, Kenneth Heafield, Sara Hooker, Colin Raffel, Pedro H. Martins, André F. T. Martins, Jessica Zosa Forde, Peter Milder, Edwin Simpson, Noam Slonim, Jesse Dodge, Emma Strubell, Niranjan Balasubramanian, Leon Derczynski, Iryna Gurevych, Roy Schwartz
| Challenge: | Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data, but using only scale to improve performance means resource consumption also grows. |
| Approach: | They propose to use data, time, storage, or energy to improve model performance. |
| Outcome: | The proposed methods and findings provide guidance for conducting NLP under limited resources and point towards promising research directions for developing more efficient methods. |
Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for factuality checking require dataset-specific threshold tuning, while LLM-based approaches often use direct prompting. |
| Approach: | They propose to use a reading comprehension task to check for true/false claim factuality and prompt LLMs with explicit test-taking strategies for efficient reasoning. |
| Outcome: | The proposed method reduces token usage by over 80% compared to unguided open-ended reasoning and achieves competitive performance to more expensive alternatives. |
Aggregating and Learning from Multiple Annotators (2021.eacl-tutorials)
Copied to clipboard
| Challenge: | NLP is based on high-quality annotated datasets, but many other tasks have unique characteristics not considered by standard models of annotation. |
| Approach: | tutorial aims to connect NLP researchers with state-of-the-art aggregation models for canonical language annotation tasks. |
| Outcome: | This tutorial aims to connect NLP researchers with state-of-the-art aggregation models for a diverse set of canonical language annotation tasks. |
Predicting Humorousness and Metaphor Novelty with Gaussian Process Preference Learning (P19-1)
Copied to clipboard
| Challenge: | Inability to quantify key aspects of creative language is a frequent obstacle to natural language understanding. |
| Approach: | They propose a Bayesian approach for predicting humorousness and metaphor novelty using Gaussian process preference learning (GPPL) . |
| Outcome: | The proposed approach achieves a Spearman’s of 0.56 against gold using word embeddings and linguistic features. |
Improving Factual Consistency Between a Response and Persona Facts (2021.eacl-main)
Copied to clipboard
| Challenge: | Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with persona facts. |
| Approach: | They propose to fine-tune these models by reinforcement learning and an efficient reward function that explicitly captures the consistency between a response and persona facts as well as semantic plausibility. |
| Outcome: | The proposed model improves the rate of responses that are factually consistent with persona facts over its supervised counterpart while maintaining the language quality of responses. |
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems (N19-1)
Copied to clipboard
Steffen Eger, Gözde Gül Şahin, Andreas Rücklé, Ji-Ung Lee, Claudia Schulz, Mohsen Mesgar, Krishnkant Swarnkar, Edwin Simpson, Iryna Gurevych
| Challenge: | Recent studies show that visual similarity can play a decisive role in assessing the meaning of characters. |
| Approach: | They investigate the impact of visual adversarial attacks on current NLP systems . they explore three shielding methods that significantly improve the robustness of the models . |
| Outcome: | The proposed methods improve performance but still fall behind non-attack scenarios. |
Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation metrics are unreliable for factual consistency tasks, limiting their effectiveness as signals for shaping model behaviour. |
| Approach: | They propose an automated training pipeline that improves factual consistency in summaries by aggregating scores from different weak metrics. |
| Outcome: | The proposed approach improves factual consistency in summaries by aggregating scores from weak metrics. |