Call for papers

Workshop on Computational Linguistics for Literature

Co-located with

The 2013 Conference of the North American Chapter

of the Association for Computational Linguistics: Human Language Technologies

June 14, 2013

Atlanta, Georgia, USA

All information, including announcements and updates, can be found on the workshop's Web site:

https://sites.google.com/site/clfl2013/

MOTIVATION AND SCOPE

The amount of literary material available on-line keeps growing rapidly. Not only are there machine-readable texts from libraries, collections and e-book stores, but there is also more and more “live” literature – e-zines, blogs, self-published e-books and so on. We need tools which would help navigate, visualize and perhaps even appreciate the high volume of available literature.

Literary texts are quite different from technical and formal documents which have been the main focus of NLP research. Most forms of statistical language processing rely on lexical information in one way or another. In literature, the primary mode is narrative rather than exposition. Stories may be cognitively easier to read than certain expository genres, such as scientific documents, but it is a challenging form of discourse for NLP tools and methods. For example, literary prose lacks overt discourse markers more often available in expository genres. Also, even conventional literary texts exhibit far less unity of time, space and topic than most formal discourse. Learning to handle these challenges in literary data may help move past heavy reliance on surface clues in general.

Literature also differs from other genres because of the needs of its typical audience. Reading, searching or browsing literature online is a different task than searching for the latest news on a particular topic. Search criteria would be rather abstract: not a keyword, but a literary style, similarity to another work, point of view and so on. When looking for a summary or a digest, a reader may prefer to know or visualize a text's broad characteristics than facts which summarize the plot. In particular, usual extraction-based summarization methods seldom work for literary narrative.

Large amounts of digitized literary data also make it possible to analyze literature synchronically and diachronically, and to provide insight into both literary history and contemporary trends. Literary theories used to arise from an in-depth study of relatively few works. This form of analysis is detailed, informed and necessarily subjective. Modern, large-scale quantitative studies cannot replace close reading, but they offer broad-coverage, objective insights into a corpus or a genre of literature. The specifics of literary writing require that it be treated differently than other types of data; it is important to outline the differences and perhaps propose solutions.

We invite papers which touch upon these areas, but we are open to other ideas which promote the processing of literary narrative or related forms of discourse.

TOPICS OF INTEREST

Note: papers on other closely related topics will also be considered.

  • the needs of the readers and how those needs translate into meaningful NLP tasks;

  • searching for literature;

  • recommendation systems for literature;

  • computational modelling of narratives, computational narratology;

  • summarization of literature;

  • finding similar books;

  • differences between literature and other genres as relevant to computational linguistics;

  • discourse structure in literature;

  • emotion analysis for literature;

  • profiling and authorship attribution;

  • identification and analysis of literature genres;

  • building and analyzing social networks of characters;

  • generation of literary narrative, dialogue or poetry;

  • modelling dialogue literary style for generation.

SUBMISSION

We invite submission of long and short papers, describing completed or ongoing research on systems, studies, theories and models which can inform the area of computational linguistics for literature. Long papers should be at most 8 pages, plus unlimited space for references. Short papers should be at most 4 pages plus references, and can be appropriate for either oral or poster presentation. Accepted long papers, and perhaps selected short papers, will be presented as talks. In addition, we encourage submission of position papers -- mapping out research ideas and programs -- of up to 6 pages plus references.

There will be double-blind review of research papers: submissions must be anonymized. Position papers will undergo single-blind review: please sign them.

Style files and sample PDFs:

Look for FORMAT at http://naacl2013.naacl.org/CFP.aspx

Important dates (click!)