TerMine

Web Demonstration

Automatic recognition of multi-word terms and acronyms

Plain text (Only ASCII characters allowed)

Local text file (*.txt in ASCII encoding or *.pdf; 2MB maximum)

URL (HTML or PDF content; 2MB maximum)

POS tagger: TreeTagger version 3.1 GENIA Tagger version 2.1

Preserve break lines in the source document

Usage

1. Select the data entry method (text, file upload, or URL).
2. Choose a POS tagger (TreeTagger for general text, GENIA for biomedical text).
3. Click Analyze.

C‑value term extraction benefits from sufficient text for termhood scoring; try the sample buttons for a quick demo.

Limitations

• Documents larger than 2MB are rejected to protect the server; use the TerMine Processing Service for larger jobs.
• Text must be ASCII-encoded.
• Layout of original HTML/PDF may not be reproduced.
• Some HTML/PDF may not be extractable.

Background

TerMine integrates C‑Value multiword term extraction and AcroMine acronym recognition. Terms are recognized using linguistic analysis (POS tagging, extraction of adjective/noun sequences) and statistical analysis (termhood scoring) for scalable, high‑throughput processing.

References

• Frantzi, K., Ananiadou, S. & Mima, H. (2000) Automatic recognition of multi‑word terms. International Journal of Digital Libraries 3(2), 117–132.
• Okazaki, N. & Ananiadou, S. (2006) Building an abbreviation dictionary using a term recognition approach. Bioinformatics.
• GENIA Tagger — POS tagging, shallow parsing, and NER for biomedical text.
• TreeTagger — language‑independent POS tagger.