The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

Multi-domain learning (MDL) refers to learning a set of models simultaneously, where each
model is specialized to perform a task in a particular domain. Generally, a high labeling …

The mental disorder of online users is determined using social media posts. The major
challenge in this domain is to avail the ethical clearance for using the user generated text on …

Since an unprecedented amount of online information in the form of unstructured texts is
generated daily, researchers have started to focus on the development of robust …

Multi-domain text classification (MDTC) aims to leverage all available resources from
multiple domains to learn a predictive model that can generalize well on these domains …

Multi-domain text classification can automatically classify texts in various scenarios. Due to
the diversity of human languages, texts with the same label in different domains may differ …

Multi-domain sentiment classification deals with the scenario where labeled data exists for
multiple domains but is insufficient for training effective sentiment classifiers that work across …

In multi-domain learning (MDL) scenarios, high labeling effort is required due to the
complexity of collecting data from various domains. Active Learning (AL) presents an …

One of the challenges of developing a summarization model arises from the difficulty in
measuring the factual inconsistency of the generated text. In this study, we reinterpret the …

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of
models on datasets collected from different domains. Conventional approaches emphasize …