Question Generation (QG) systems have shown promising results in reducing the time and effort required to create questions for students. Typically, a first step in QG is to select the content to design a question for. In an educational setting, it is crucial that the resulting questions cover the most relevant/important pieces of knowledge the student should have acquired. Yet, current QG systems either consider just a single sentence or paragraph (thus do not include a selection step), or do not consider this educational viewpoint of content selection. Aiming to fill this research gap with a solution for educational document level QG, we thus propose to select contents for QG based on relevance and topic diversity. We demonstrate the effectiveness of our proposed content selection strategy for QG on 2 educational datasets. In our performance assessment, we also highlight limitations of existing QG evaluation metrics in light of the content selection problem.

The ability to track fine-grained emotions in customer service dialogues has many real-world applications, but has not been studied extensively. This paper measures the potential of prediction models on that task, based on a real-world dataset of Dutch Twitter conversations in the domain of customer service. We find that modeling emotion trajectories has a small, but measurable benefit compared to predictions based on isolated turns. The models used in our study are shown to generalize well to different companies and economic sectors.

This work presents the contribution from the Text-to-Knowledge team of Ghent University (UGent-T2K) to the MultiDoc2Dial shared task on modeling dialogs grounded in multiple documents. We propose a pipeline system, comprising (1) document retrieval, (2) passage retrieval, and (3) response generation. We engineered these individual components mainly by, for (1)-(2), combining multiple ranking models and adding a final LambdaMART reranker, and, for (3), by adopting a Fusion-in-Decoder (FiD) model. We thus significantly boost the baseline system’s performance (over +10 points for both F1 and SacreBLEU). Further, error analysis reveals two major failure cases, to be addressed in future work: (i) in case of topic shift within the dialog, retrieval often fails to select the correct grounding document(s), and (ii) generation sometimes fails to use the correctly retrieved grounding passage. Our code is released at this link.

In online domain-specific customer service applications, many companies struggle to deploy advanced NLP models successfully, due to the limited availability of and noise in their datasets. While prior research demonstrated the potential of migrating large open-domain pretrained models for domain-specific tasks, the appropriate (pre)training strategies have not yet been rigorously evaluated in such social media customer service settings, especially under multilingual conditions. We address this gap by collecting a multilingual social media corpus containing customer service conversations (865k tweets), comparing various pipelines of pretraining and finetuning approaches, applying them on 5 different end tasks. We show that pretraining a generic multilingual transformer model on our in-domain dataset, before finetuning on specific end tasks, consistently boosts performance, especially in non-English settings.

Short text clustering is a challenging problem when adopting traditional bag-of-words or TF-IDF representations, since these lead to sparse vector representations of the short texts. Low-dimensional continuous representations or embeddings can counter that sparseness problem: their high representational power is exploited in deep clustering algorithms. While deep clustering has been studied extensively in computer vision, relatively little work has focused on NLP. The method we propose, learns discriminative features from both an autoencoder and a sentence embedding, then uses assignments from a clustering algorithm as supervision to update weights of the encoder network. Experiments on three short text datasets empirically validate the effectiveness of our method.