Handing in a paper or exercise and merely receiving "bad" or "incorrect" as feedback is not very helpful when the goal is to improve.Unfortunately, this is currently the kind of feedback given by many Automatic Short Answer Grading (ASAG) systems.One of the reasons for this is a lack of content-focused elaborated feedback datasets.To encourage research on explainable and understandable feedback systems, we present the Short Answer Feedback dataset (SAF).Similar to other ASAG datasets, SAF contains learner responses and reference answers to German and English questions.However, instead of only assigning a label or score to the learners' answers, SAF also contains elaborated feedback explaining the given score.Thus, SAF enables supervised training of models that grade answers and explain where and why mistakes were made.This paper discusses the need for enhanced feedback models in real-world pedagogical scenarios, describes the dataset annotation process, gives a comprehensive analysis of SAF, and provides T5-based baselines for future comparison. 1

Practice is essential for language learning. This is true for writing as well as speaking. However, in contrast to writing, it can be challenging to offer students sufficient time to practice speaking while receiving corrective feedback from a teacher. Considering the importance of corrective feedback for language mastery, automatic feedback systems could provide vital assistance through additional supervised speaking exercise. For this reason, this paper proposes an end-to-end feedback generation pipeline to correct grammar errors in unconstrained speech. The approach consists of four steps, converting raw speech files into transcripts with automatic speech recognition, removing disfluency, correcting grammatical errors, and preparing the feedback for presentation to the user. An explorative analysis of the pipeline with English language learners indicates that out-of-the-box automatic speech recognition models degrade in performance when used by language learners. However, training the model with only 15 minutes of learners’ speech decreases the word error rate almost by half.

Learners comprehend complex texts only if they understand the concepts involved, and assessing their comprehension works best if the assessment targets those concepts. Hence, assessment systems, such as question generators, often profit from learning-relevant concepts as input to solve their tasks. However, automatically detecting a given text’s relevant concepts is non-trivial. If a concept is deemed relevant heavily depends on the context and thus on automatic text understanding. Recent advancements in supervised machine learning improved state-of-the-art automatic text understanding. However, those methods need training corpora to learn the association between the relevant concepts and their text’s context. This work shows that textbooks comprise all the necessary information to construct such corpora. We introduce and evaluate an open-source automatic back-of-the-book index extractor and a corpus construction algorithm to derive training corpora from a set of high-quality PDF textbooks. We furthermore investigate to what extent state-of-the-art machine learning models can learn to extract concepts from constructed corpora. The results show that the models have decent performance and provide evidence generalization to unseen concepts.

DDoS attack detection is crucial in computer networks to meet the reliability and accessibility requirements of online services. The ability of machine learning to discriminate between DDoS attacks and benign flows makes it a promising candidate for DDoS detection. Correctly classifying the flows with high performance in near real-time is a critical issue for an ML-based DDoS detector to reduce the damages of DDoS attacks. In order to improve the performance of classification and reduce the prediction time, we propose a multi-aspect Ensemble Feature Selection (EFS) for DDoS attack detection in this work. The presented EFS selects the most relevant features of each attack separately, leveraging a combination of statistical filtering approaches and machine learning methods. We evaluate our method on two different datasets to demonstrate the EFS robustness toward model-specific biases. Last, we demonstrate that the prediction time is reduced leveraging the proposed EFS.