A lack of corpora has so far limited advances in integrating human gaze data as a
supervisory signal in neural attention mechanisms for natural language processing (NLP) …

Automatic summary assessment is useful for both machine-generated and human-produced
summaries. Automatically evaluating the summary text given the document enables, for …

The overwhelming amount of online text information available today has increased the need
for more research on its automatic summarization. In this work, we describe our participation …

We introduce a new readability tutoring system, Read & Improve, a freely available online
resource aimed at supporting learners of English and English Language Teaching (ELT) …

Summarization is the process of compressing a document into a shorter form that contains
all the relevant information. It is useful in many applications, for example, a brief summary of …

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical
similarity which cannot well capture semantics nor linguistic quality and require a reference …

Neural networks (NNs) are often used as part of systems applied in domains such as
Computer Vision or Natural Language Processing (NLP), and diagrams are a prevalent way …

Evaluating machine-generated summaries without a human-written reference summary has
been a need for a long time. In this paper, we present a proof-of-concept study to a summary …

Throughout the last decade, a traditional language classroom is no longer the only space
where formal learning occurs. Paper-based textbooks are being substituted with appealing …