Enhancing Access to Media Collections and Archives Using Computational Linguistic Tools

In this paper, we outline the strategies, methodology, and infrastructure needed to bring advanced computational linguistic tools to researchers and archivists in the humanities. We discuss three use cases involving the application of the Language Application Grid (LAPPS), an open, web-based infrastructure providing interoperable access to hundreds of computational linguistic (CL) component web services, together with facilities for multistep analyses via tools pipelining, performance evaluation, and resource delivery. These include: CL analysis of corpora restricted under copyright; the challenge posed by radio and television media collections; and the use of LAPPS for assisting archivists in their collection and cataloguing efforts. We believe that the adoption and use of CL platforms such as LAPPS by the digital humanities (DH) will help foster better communication, sharing, and research between the two communities.