RESEARCH
Digital Archive Systems
Digital Archive Systems are systems that are envisaged and designed for
specific types of digital artefact collections mostly related to the
humanities. The IMS group has contributed to the design and development
of some digital archive systems, one of them has been named Imaginum Patavinae Scientiae Archivum (IPSA).
Music information retrieval
Music Information Retrieval (MIR) is an emerging research area that focuses on the content-based retrieval of musical documents against musical queries. We developed an approach to automatically extract music content descriptors from both documents and queries in a notated form. This approach allows also for tuning the exhaustivity and specificity of retrieval results. Unlike pattern-matching based approaches, it is scalable for large collections of documents. A further step has been done in the direction of indexing of documents in audio format through automatic alignment of the audio signal with the corresponding events in the score.
The retrieval of information contained in documents spread across P2P networks
Peer-to-Peer (P2P) networks provide access to collections of data which can be both structured and unstructured. In the latter case, if an IR service is available in a P2P network, a user can search for relevant documents stored in peers connected to his own computer, mobile phone or PDA. A weighing model is studied and proposed to reduce network exploration and maximize retrieval performance.
For further information, please contact Massimo Melucci
Annotation and Digital Library Services
Interaction with Digital Library (DL) content can be enhanced by the use of digital annotations. Annotating DL documents is a means to support cognitive functions like remembering, thinking or clarifying, thus enhancing the user’s experience of studying and retrieving content. Moreover, shared annotations support discussion and cooperative work among DL users. With annotations, users can interpret documents, and annotations also support the effective use of a digital library by helping the user approaching a document through interpretations. Thus, the use of annotations in a DL environment seems very promising, in that it should bring DL users' knowledge together, build community and create new knowledge.
Information Retrieval in Context
It is assumed that contextual data can be used effectively to constrain retrieval of information thereby reducing the complexity of the retrieval process. The challenge is to understand, modeling and capture context. At IMS, context modeling and discovery is addressed by using mathematical yet computational notions.
For further information, please contact Massimo Melucci
Automatic text categorization
Automatic Text Categorization (ATC), the assignment of natural language written texts to one or more predefined categories, is an important task of a lot of management information applications. For example, it might be used as an indexing mechanism for text retrieval, as a component of an information filtering system, and as end of itself when categorization of documents is of iterest. During the last years, the main approach to the problem has been based on machine learning techniques: a general inductive process automatically builds a classifier by learning, from a set of preclassified documents, the characteristic of the categories. This approach has led to effective algorithms, considerable savings in terms of time, and straightforward portability to different domains.
PAST RESEARCH SUBJECTS
Link Analysis for Information RetrievalLink analysis techniques are recent techniques used to try to increase the performance of Web search engines. They all use the information that can be inferred from the directed graph ... Read More... |
Passage retrievalThe number and size of Web collections and databases storing unstructured textual data that are made available to the final user present high degrees of heterogeneity at the level of ... Read More... |
Language Independent StemmingMultilingual Information Retrieval has been used to refer to various tasks ranging from monolingual IR in languages other than English to IR on single documents containing text in more than ... Read More... |
Automatic segmentation and alignmentThe segmentation of an unstructured media in a subset of coherent parts is an important task that may have applications in different domains. Our approach is based on the idea ... Read More... |
Automatic Hypertext ConstructionThe increasing availability of online textual document collections, whose size is too large to enable a manual authoring and construction of the hypertext, is the main reason for which fully ... Read More... |