Papers by Claudia Hauff
Unsupervised Domain Adaptation for Question Generation with DomainData Selection and Self-training (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing question generation models require large-scale and high-quality training data. |
| Approach: | They propose an unsupervised domain adaptation approach to combat the lack of training data and domain shift issue with domain data selection and self-training. |
| Outcome: | The proposed approach outperforms baselines on three large datasets with different domain similarities, using a transformer-based pre-trained QG model. |
Answer Quality Aware Aggregation for Extractive QA Crowdsourcing (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for creating extractive question answering datasets are crowdsourcing, but results are often inconsistent. |
| Approach: | They propose a method for aggregating answers from different crowd workers that takes into account the relations between the answer, question, and context passage. |
| Outcome: | The proposed method outperforms baselines by 16% on precision and effectively conduct answer aggregation for extractive question answering task. |
On the Calibration and Uncertainty of Neural Learning to Rank Models for Conversational Search (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to rank documents in decreasing order of their probability of relevance are not well calibrated and have several sources of uncertainty. |
| Approach: | They propose to calibrate deterministic neural rankers for conversational search problems . they then use two techniques to model the uncertainty of neural ranker's uncertainty . |
| Outcome: | The proposed rankers output a predictive distribution of relevance as opposed to point estimates. |