Knowledge-Driven Multilingual Text Analysis and Transparent Information Retrieval: Language Technology for Industrial Applications (Cognitive Technologies) - Hardcover

Thurmair, Gregor

Hardcover

ISBN 10: 3031917405 ISBN 13: 9783031917400

Publisher: Springer, 2025

Synopsis

This book presents all components and knowledge sources required for Transparent Information Retrieval. Depending on the respective topic and taking care of their interoperability, both deep and shallow technology is used. The processing starts from the analysis of the text data and collects its results in a multilingual conceptual network, this way enabling Transparent Information Retrieval where users communicate with the system in their native language while the documents could be in a different language, transparent to the users.

 

To do so, the author investigates all text analysis components required for multilingual indexing, starting from preparatory work like language and topic identification, continuing with sentence splitting and tokenization (including Chinese), and describing lexical analysis, also for multiword entries and Named Entities. Entries are then disambiguated both on syntactic (by a tagger) and semantic level (by multilingual word sense disambiguation). The analysis results are collected in a dynamic multilingual ConceptNet, which is an index structure extended by monolingual relations (like synonyms, or head-modifier links) as well as multilingual ones (translations). In addition to many European languages also Turkish, Arabic, Persian, and Chinese are treated.

 

The book concludes with a description of components needed to build the required resources, like crawlers, bilingual term extraction, and tools for defaulting linguistic annotations. For each component, readers will find a technology overview, a discussion of its main challenges in computational treatment, a description of the technical solution selected, and evaluation information.

About this title

About the Author

Gregor Thurmair has a long history and experience in multilingual text processing and machine translation in industrial setups. Starting with the first retrieval and dialogue systems in the 80s, he worked as a researcher, project leader, and technical director both in the development of IR and MT systems (Siemens’ METAL, Linguatec’s Personal Translator) and in Language Engineering projects for terminology, multilingual text analysis, and translation in several EU Projects. He has more than 50 publications; he was a member of the ELRA board, reviewer for the European Commission, and invited speaker in several conferences (LREC, CLEF, MTSummit).

From the Back Cover

This book presents all components and knowledge sources required for Transparent Information Retrieval. Depending on the respective topic and taking care of their interoperability, both deep and shallow technology is used. The processing starts from the analysis of the text data and collects its results in a multilingual conceptual network, this way enabling Transparent Information Retrieval where users communicate with the system in their native language while the documents could be in a different language, transparent to the users.

 

To do so, the author investigates all text analysis components required for multilingual indexing, starting from preparatory work like language and topic identification, continuing with sentence splitting and tokenization (including Chinese), and describing lexical analysis, also for multiword entries and Named Entities. Entries are then disambiguated both on syntactic (by a tagger) and semantic level (by multilingual word sense disambiguation). The analysis results are collected in a dynamic multilingual ConceptNet, which is an index structure extended by monolingual relations (like synonyms, or head-modifier links) as well as multilingual ones (translations). In addition to many European languages also Turkish, Arabic, Persian, and Chinese are treated.

 

The book concludes with a description of components needed to build the required resources, like crawlers, bilingual term extraction, and tools for defaulting linguistic annotations. For each component, readers will find a technology overview, a discussion of its main challenges in computational treatment, a description of the technical solution selected, and evaluation information.

Edition details

• Publisher: Springer
• Publication date: 2025
• Language: English
• ISBN 10: 3031917405
• ISBN 13: 9783031917400
• Binding: Hardcover
• Number of pages: 407