Table 2.

Overview on the quality of definition extraction and definitional question answering

Xu et al. (2003)	F=0.31, 1st rank in TREC2003
Yang et al. (2003)	F=0.26, 2nd rank in TREC2003
Echihabi et al. (2003)	F=0.27, 3rd rank in TREC2003
Han et al. (2006)	F=0.16
Degórski et al. (2008)	F=0.30

In the TREC2003 task on definitional question answering, the best system achieved a F-measure of F=0.31. In information retrieval, quality is often measured as F-measure (F), the harmonic mean of precision and recall (see ‘Methods’ section)