Knowledge Graph Question Answering (KGQA) systems are often based on machine learning algorithms, requiring thousands of question-answer pairs as training examples or natural language processing pipelines that need module fine-tuning. In this paper, we present a novel QA approach, dubbed TeBaQA. Our approach learns to answer questions based on graph isomorphisms from basic graph patterns of SPARQL queries. Learning basic graph patterns is efficient due to the small number of possible patterns. This novel paradigm reduces the amount of training data necessary to achieve state-of-the-art performance. TeBaQA also speeds up the domain adaption process by transforming the QA system development task into a much smaller and easier data compilation task. In our evaluation, TeBaQA achieves state-of-the-art performance on QALD-8 and delivers comparable results on QALD-9 and LC-QuAD v1. Additionally, we performed a fine-grained evaluation on complex queries that deal with aggregation and superlative questions as well as an ablation study, highlighting future research challenges.

Social media plays a significant role in disaster management by providing valuable data about affected people, donations and help requests. Recent studies highlight the need to filter information on social media into fine-grained content labels. However, identifying useful information from massive amounts of social media posts during a crisis is a challenging task. In this paper, we propose I-AID, a multimodel approach to automatically categorize tweets into multi-label information types and filter critical information from the enormous volume of social media data. I-AID incorporates three main components: i) a BERTbased encoder to capture the semantics of a tweet and represent as a low-dimensional vector, ii) a graph attention network (GAT) to apprehend correlations between tweets' words/entities and the corresponding information types, and iii) a Relation Network as a learnable distance metric to compute the similarity between tweets and their corresponding information types in a supervised way. We conducted several experiments on two real publicly-available datasets. Our results indicate that I-AID outperforms state-ofthe-art approaches in terms of weighted average F1 score by +6% and +4% on the TREC-IS dataset and COVID-19 Tweets, respectively.

No abstract

Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets. However, compared to original texts in the same language, translations possess distinct qualities referred to as translationese. Previous research has shown that these translation artifacts influence the performance of a variety of crosslingual tasks. In this work, we propose a novel approach to reducing translationese by extending an established bias-removal technique. We use the Iterative Null-space Projection (INLP) algorithm, and show by measuring classification accuracy before and after debiasing, that translationese is reduced at both sentence and word level. We evaluate the utility of debiasing translationese on a natural language inference (NLI) task, and show that by reducing this bias, NLI accuracy improves. To the best of our knowledge, this is the first study to debias translationese as represented in latent embedding space.

Question answering engines have become one of the most popular type of applications driven by Semantic Web technologies. Consequently, the provision of means to quantify the performance of current question answering approaches on current datasets has become ever more important. However, a large percentage of the queries found in popular question answering benchmarks cannot be executed on current versions of their reference dataset. There is a consequently a clear need to curate question answering benchmarks periodically. However, the manual alteration of question answering benchmarks is often error-prone. We alleviate this problem by presenting QUANT, a novel framework for the creation and curation of question answering benchmarks. QUANT supports the curation of benchmarks by generating smart edit suggestions for question-query pair and for the corresponding metadata. In addition, our framework supports the creation of new benchmark entries by providing predefined quality checks for queries. We evaluate QUANT on 653 questions obtained from QALD-1 to QALD-8 with 10 users. Our results show that our framework generates reliable suggestions and can reduce the curation effort for QA benchmarks by up to 91%.