About this Research Topic
The proposed Research Topic will focus on the cutting-edge research in computational linguistics applied to literary data.
In the last 20 years, language technology has made significant progress. Document search and retrieval, question answering, summarization, machine translation—they all have achieved the impressive levels of performance, high enough to be usable in research and industry. The focus of the field, however, has mainly been on documents customarily read for information: news articles, scientific papers, even tweets.
The objective of literature is quite different. It is not so much to educate the reader about hard facts as it is to move, to inspire, to make one ponder rather abstract questions, or simply to make one admire the beauty and artistry of the author’s language. The language used in prose and poetry is also quite different: more metaphorical, symbolic, musical. Technically this translates into complex syntax, a far larger vocabulary and more non-trivial interpretation. All these properties make it a challenge to process literary language computationally.
In this Research Topic, we welcome selected papers that explore how one can adapt state-of-the-art methods in language technology to make literary data more accessible, searchable, or interpretable.
Two broad categories of papers are likely: papers that focus on reader applications, and papers that apply language technology to large- or small-scale analysis of a certain genre, with the aim of drawing objective conclusions.
Most of the expected submissions will come from a series of annual research Workshops on Computational Linguistics for Literature (see for example, https://sites.google.com/site/clfl2016/home ). We pre-selected the most interesting and promising papers from the 2015 and 2016 events, and confirmed that the authors would be interested in expanding their work for a journal publication.
The aim of this Research Topic is to showcase how in-depth methods in natural language technology can lead to interesting, exciting, and insightful applications for readers or literary scholars. Our background is in the area promoted by the Association for Computational Linguistics, in a community intimately familiar with the methods, but maybe less so with literature-related questions. (There also is now a vibrant community of researchers in Digital Humanities, who are much more familiar with the area of literary inquiry, though perhaps not with the latest language-processing technology.)
This Research Topic will be a forum for researchers who apply their, possibly adjusted, methods to a challenging type of language data. We want to encourage the authors of pioneering publications in this vein to expand and broaden their work, and to make it worthy of a journal publication.
Keywords: Corpus analysis of literature, story analysis, computational analysis of poetry, machine translation of literature, sentiment analysis in poetry, ancient text decipherment and reconstruction
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.