Comment: Findings of ACL: EMNLP 2020

Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks. Whereas the previous methods project wor...

<p>It is widely accepted that orbital variations are responsible for the generation of glacial cycles during the late Pleistocene. However, the relative contributions of the orbital forcing compared to <span class="inline-formula">CO₂</span> variations and ot...

Previous researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that support important evidences for sentiment analysis and s...

How can we effectively regularize BERT? Although BERT proves its effectiveness in various NLP tasks, it often overfits when there are only a small number of training instances. A promising direction to regularize BERT is based on pruning its attention heads with a proxy...

This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to extract a collection of mid-level ...

Comment: To be published in: Lecture Notes in Artificial Intelligence, 1st International Conference on Artificial Intelligence in HCI, AI-HCI, Held as Part of HCI International 2020, Kopenhagen, Denmark, July 19-24, Springer

Toxic comments in online platforms are an unavoidable social issue under the cloak of anonymity. Hate speech detection has been actively done for languages such as English, German, or Italian, where manually labeled corpus has been released. In this work, we first prese...

Text summarization refers to the process that generates a shorter form of text from the source document preserving salient information. Many existing works for text summarization are generally evaluated by using recall-oriented understudy for gisting evaluation (ROUGE) ...

<jats:p>Anatomically Modern Humans are the sole survivor of a group of hominins that inhabited our planet during the last ice age and that included, among others, <jats:italic>Homo neanderthalensis</jats:italic>, <jats:italic>Homo denisova</jats:italic>, and <jats:itali...