The Language Technology Group conducts research and development in a number of areas. Some of the current and past LTG projects are listed here.
- EdIE-EHR: Natural language processing technology for raw text in electronic healthcare records.
- Digitising Scotland: Coding of occupations and causes of death.
- Gaelic Language Technology: work on speech and text processing for Gaelic
- GeoGazScot: Geoparsing the Gazetteers of Scotland.
- COVID-19 Clinical Guideline Browser: A tool for sharing and understanding hospital guidelines
- Plague.TXT: Extracting Epidemiological Data from Historic Outbreak Reports.
- Palimpsest: Text mining literature set in Edinburgh. The Palimpsest database of geo-referenced literary excerpts can be accessed via the LitLong.org interface.
- Trading Consequences: Text mining large data collections for information commodity trading in the 19th century.
- Hiberlink: Assessing the extent of “reference rot”
- S-CASE: Parsing software requirements.
- BotaniTours: Aggregating and mining information on botanical points of interest in the Scottish Borders.
- DEEP: The Digitisation of England’s Placenames
- Google Ancient Places: Finding Ancient Mediterranean Places in Literature • SYNC3 Large-scale news and blog analysis.
- BOPCRIS: Named entity tagging of historical parliamentary proceedings. • TXV Text mining applied to the recruitment domain.
- TXM: Text mining for biomedial content.
- EASIE: Combining shallow semantics and domain knowledge.
- SEER: Machine learning for named entity recognition. • SUM Summarisation of legal texts.
- CROSSMARC: Cross-retail multi-agent retail comparison.