Many existing deep learning models for natural language processing tasks focus on
learning the compositionality of their inputs, which requires many expensive computations …

Determining semantic similarity between texts is important in many tasks in information
retrieval such as search, query suggestion, automatic summarization and image finding …

The rapid advancement of AI technology has made text generation tools like GPT-3 and
ChatGPT increasingly accessible, scalable, and effective. This can pose serious threat to the …

Owing to the need for a deep understanding of linguistic items, semantic representation is
considered to be one of the fundamental components of several applications in Natural …

Paraphrase detection is important for a number of applications, including plagiarism
detection, authorship attribution, question answering, text summarization, text mining in …

One major deficiency of most semantic representation techniques is that they usually model
a word type as a single point in the semantic space, hence conflating all the meanings that …

We propose Cartography Active Learning (CAL), a novel Active Learning (AL) algorithm that
exploits the behavior of the model on individual instances during training as a proxy to find …

When reading a sentence, individual words can be combined to create more complex
meaning. In this study, we sought to uncover brain regions that reflect the representation of …

Millions of users share their experiences on social media sites, such as Twitter, which in turn
generate valuable data for public health monitoring, digital epidemiology, and other …

Users submit feedback about the software they use through application distributions
platforms, ie, app stores, and social media. Previous research has found that this type of …