About this Research Topic
Automatic Text Summarization (ATS) aims at generating a concise version of a document while preserving its most important topics and content. Even though ATS is not a new field of research, it has gained a lot of attention from research communities in the recent years. This renewed interest is motivated, on the one hand, by modern neural network-based approaches able to achieve very promising results and, on the other hand, by the availability of large-scale datasets containing hundreds of thousands of document-summary pairs. Moreover, the possibility of handle heterogeneous texts ranging from user generated content extracted from the web to high-specific documentation, such as technical/scientific papers, opens new challenges in this research area. ATS, thus, represents a key tool not only for reducing information content, but also for evaluating information relevance and adequateness of answers in a specific context of application.
This Research Topic is intended to provide an overview of the research being carried out in the area of Natural Language Processing (NLP) and, in particular of ATS, to accelerate knowledge diffusion as well as enable the development of new tools, datasets and resources that are in line with the need of research and industrial communities. To this end, the Research Topic promotes an interdisciplinary vision, aiming at gathering researchers with broad expertise in various fields — machine learning, natural language, cognitive science, and psychology — to discuss their cutting edge work as well as perspectives on future directions in this exciting space of ATS for different sources of information.
The interests of this topic are focused (but not limited to) to address the following problems:
- abstractive and extractive summarization
- supervised/unsupervised and topic-based/query-based summarization
- single and multi-document summarization
- multiple text genres (News, tweets, product reviews, meeting conversations, forums, lectures, student feedback, emails, medical records, books, research articles, etc)
- multilingual and cross-lingual summarization
- creation of new datasets and annotations, especially for non-English languages
- development of new evaluation metrics, also taking into account morpho-syntactic and semantic aspects
- simulation of cognitive processes of human summarization
Original contributions addressing these issues are sought, covering the whole range of theoretical and practical aspects, technologies and systems.
Keywords: Automatic Text Summarization, Natural Language Processing, Long Documents, Human-like Summarization, Linguistics Constraints.
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.