Question Generation (QG) aims to automate the task of composing questions for a passage
with a set of chosen answers found within the passage. In recent years, the introduction of …

Multi-hop question generation (QG) is the process of generating answer related questions,
which requires aggregating multiple pieces of information and reasoning from different parts …

In this paper, we present our system for the EvoNLP 2022 shared task Temporal Meaning
Shift (TempoWiC). Different from the typically used discriminative model, we propose a …

In this paper, we describe our DCU-Lorcan system for the FinCausal 2022 shared task: span-
based cause and effect extraction from financial documents. We frame the FinCausal 2022 …

Conventional automatic evaluation metrics, such as BLEU and ROUGE, developed for
natural language generation (NLG) tasks, are based on measuring the n-gram overlap …

Past works that investigate out-of-domain performance of QA systems have mainly focused
on general domains (eg news domain, wikipedia domain), underestimating the importance …

After the increased reliance on online education, online assessment became an essential
tool for educators to remotely monitor and evaluate students' understanding in order to assist …

An advanced driver simulator methodology facilitates a well-connected interaction between
the environment and drivers. Multiple traffic information environment language processing …

Recent years have witnessed the emergence of Pre-trained Language Models (PLMs), such
as ELMo, GPT, BERT, XLNet, GPT-3 and InstructGPT [Wang et al., 2018, Peters et al., 2018 …

Pre-trained language models such as BERT and XLNet have greatly improved the
performance of many NLP tasks. These models can capture rich semantic patterns from …