Manual classification of works of literature with genre/form concepts is a time-consuming task requiring domain expertise. Building automated systems based on language understanding can help humans to achieve this work faster and more consistently. Towards this direction, we present a case study on automatic classification of Greek literature books of the 19th century. The main challenges in this problem are the limited number of literature books and resources of that age and the quality of the source text. We propose an automated classification system based on the Bidirectional Encoder Representations from Transformers (BERT) model trained on books from the 20th and 21st century. We also dealt with BERT’s constraint on the maximum sequence length of the input, leveraging the TextRank algorithm to construct representative sentences or phrases from each book. The results show that BERT trained on recent literature books correctly classifies most of the books of the 19th century despite the disparity between the two collections. Additionally, the TextRank algorithm improves the performance of BERT.

Semantic Indexing of 19th-Century Greek Literature Using 21st-Century Linguistic Resources

El reconocimiento de las formas documentales en las búsquedas de información de calidad: una apuesta por la educación en la “docudiversidad”

This study provides analysis of a large online survey that was distributed to the cataloging community in 2018. The survey aimed to answer a number of important research questions to gain a general sense of the current state of Library of Congress Genre/Form Terms (LCGFT) usage. Findings include an overall broad acceptance of LCGFT, suggesting that the LCGFT project has been successfully embraced as a new controlled vocabulary; however, the adoption of the vocabulary remains uneven, especially between different types of institutions and different areas of the LCGFT vocabulary. Additionally, training points to a much-needed area for improvement as the survey found that the vast majority of non-users of LCGFT had never received vocabulary training. Survey results also suggest that retrospective LCGFT application, particularly using automated means, presents forthcoming challenges for librarians and library IT staff. Despite these limitations and challenges, survey results make it clear that LCGFT has become a widely accepted part of the bibliographic universe that helps to make genre and form information explicitly accessible to library users.

/pdf/genre-form-access-in-library-catalogs-a-survey-on-the-1blyquwc5b.pdf

Genre/Form Access in Library Catalogs: A Survey on the Current State of LCGFT Usage

The purpose of this paper is to report on a quantitative analysis of the LCGFT vocabulary within a large set of MARC bibliographic data retrieved from the OCLC WorldCat database. The study aimed to provide a detailed analysis of the outcomes of the LCGFT project, which was launched by the Library of Congress (LC) in 2007. Findings point to a moderate increase in LCGFT use over time; however, the vocabulary has not been applied to the fullest extent possible in WorldCat. Further, adoption has been inconsistent between the various LCGFT disciplines. These and other findings discussed here suggest that retrospective application of the vocabulary using automated means should be investigated by catalogers and other technical services librarians. Indeed, as the data used for the analysis show somewhat uneven application of LCGFT, and with nearly half a billion records in WorldCat, it remains a certainty that much of LCGFT’s full potentials for genre/form access and retrieval will remain untapped until innovative solutions are introduced to further increase overall vocabulary usage in bibliographic databases.

Colin Bitter

Papers

Genre/Form Access in Library Catalogs: A Survey on the Current State of LCGFT Usage

On the State of Genre/Form Vocabulary: A Quantitative Analysis of LCGFT Data in WorldCat