Papers by Christopher Klein
Constrained Language Models Yield Few-Shot Semantic Parsers (2021.emnlp-main)
Copied to clipboard
Richard Shin, Christopher Lin, Sam Thomson, Charles Chen, Subhro Roy, Emmanouil Antonios Platanios, Adam Pauls, Dan Klein, Jason Eisner, Benjamin Van Durme
| Challenge: | Large pretrained language models excel at generating natural language, but they are not efficient for task specific semantic parsing. |
| Approach: | They propose to use large pretrained language models as few-shot semantic parsers . they paraphrase inputs into a controlled sublanguage resembling English . |
| Outcome: | The proposed model can generate surprisingly accurate models on multiple tasks with minimal code and data. |
DELPHI: Data for Evaluating LLMs’ Performance in Handling Controversial Issues (2023.emnlp-industry)
Copied to clipboard
| Challenge: | a recent study of controversy-handling in large language models (LLMs) has shown that people may become increasingly dependent on such systems for information. |
| Approach: | They propose to construct a controversial questions dataset using a subset of a publicly available dataset. |
| Outcome: | The proposed dataset presents challenges concerning knowledge recency, safety, fairness, and bias. |
Improving Human-Labeled Data through Dynamic Automatic Conflict Resolution (2020.coling-main)
Copied to clipboard
| Challenge: | a scalable method for estimating the noisiness of labels produced by crowdsourcing annotation tasks is developed. |
| Approach: | They propose a scalable method for estimating the noisiness of labels produced by crowdsourcing semantic annotation tasks and reducing the resulting error by 20-30%. |
| Outcome: | The proposed method reduces the error of the labeling process by 20-30% compared to other common labeling strategies. |