Your English writing platform
Discover LudwigExact(7)
Our aim is the expert evaluation of automatic multi-word term indexing.
This shows the difficulty of multi-word term detection, even for word-based STD systems.
WL-Kaldi system performs the best both for single-word and multi-word term detection, as expected from the overall STD results.
It must be noted that a multi-word term is considered OOV in case any of the words that form the term is OOV.
Results also show that multi-word term detection is still a challenging task in STD even for word-based STD systems.
However, for multi-word term detection, paired t-tests show that the improvement of this system is only statistically significant compared with WL-ATWV-Kaldi and WL-WER-Kaldi systems (p<10−2).
Similar(53)
ExtTerm also precisely detects multi-word terms of arbitrarily lengths, e.g. with more than 2 words.
On the one hand, the OOV word problem affects in a greater extent multi-word terms.
Contrary, multi-word terms and foreign terms tend to decrease the STD performance, as expected.
Table 15 Results of the STD ALBAYZIN 2014 evaluation on test data for single-word terms and multi-word terms.
Results show performance degradation from single-word to multi-word terms for STD systems based on word units.
Write better and faster with AI suggestions while staying true to your unique style.
Since I tried Ludwig back in 2017, I have been constantly using it in both editing and translation. Ever since, I suggest it to my translators at ProSciEditing.

Justyna Jupowicz-Kozak
CEO of Professional Science Editing for Scientists @ prosciediting.com