Malte Pietsch


pdf bib
GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval
Timo Möller | Julian Risch | Malte Pietsch
Proceedings of the 3rd Workshop on Machine Reading for Question Answering

A major challenge of research on non-English machine reading for question answering (QA) is the lack of annotated datasets. In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. To improve the reproducibility of the dataset creation approach and foster QA research on other languages, we summarize lessons learned and evaluate reformulation of question/answer pairs as a way to speed up the annotation process. An extractive QA model trained on GermanQuAD significantly outperforms multilingual models and also shows that machine-translated training data cannot fully substitute hand-annotated training data in the target language. Finally, we demonstrate the wide range of applications of GermanQuAD by adapting it to GermanDPR, a training dataset for dense passage retrieval (DPR), and train and evaluate one of the first non-English DPR models.

pdf bib
Semantic Answer Similarity for Evaluating Question Answering Models
Julian Risch | Timo Möller | Julian Gutsch | Malte Pietsch
Proceedings of the 3rd Workshop on Machine Reading for Question Answering

The evaluation of question answering models compares ground-truth annotations with model predictions. However, as of today, this comparison is mostly lexical-based and therefore misses out on answers that have no lexical overlap but are still semantically similar, thus treating correct answers as false. This underestimation of the true performance of models hinders user acceptance in applications and complicates a fair comparison of different models. Therefore, there is a need for an evaluation metric that is based on semantics instead of pure string similarity. In this short paper, we present SAS, a cross-encoder-based metric for the estimation of semantic answer similarity, and compare it to seven existing metrics. To this end, we create an English and a German three-way annotated evaluation dataset containing pairs of answers along with human judgment of their semantic similarity, which we release along with an implementation of the SAS metric and the experiments. We find that semantic similarity metrics based on recent transformer models correlate much better with human judgment than traditional lexical similarity metrics on our two newly created datasets and one dataset from related work.


pdf bib
COVID-QA: A Question Answering Dataset for COVID-19
Timo Möller | Anthony Reina | Raghavan Jayakumar | Malte Pietsch
Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020

We present COVID-QA, a Question Answering dataset consisting of 2,019 question/answer pairs annotated by volunteer biomedical experts on scientific articles related to COVID-19. To evaluate the dataset we compared a RoBERTa base model fine-tuned on SQuAD with the same model trained on SQuAD and our COVID-QA dataset. We found that the additional training on this domain-specific data leads to significant gains in performance. Both the trained model and the annotated dataset have been open-sourced at: