Whether to consider stop words in Jelinek Mercer Smoothing in Exercise

Whether to consider stop words in Jelinek Mercer Smoothing in Exercise

por Fakhruddin Bootwala -
Número de respostas: 2

Hello,

Please let me know whether to consider stop list while calculating.

image%20%281%29.png

Regards,

Fakhruddin

Em resposta a 'Fakhruddin Bootwala'

Re: Whether to consider stop words in Jelinek Mercer Smoothing in Exercise

por Goran Glavaš -
Hi Fakhruddin,

The stop-word removal is not explicitly mentioned, so you can assume that we're not removing stopwords as a preprocessing step (i.e., stopwords also contribute to the document length counts needed for estimating the unigram probabilities).

Also, please don't copy your solutions to exercises here in the forum in the future, as this is the forum read by all students (so you're sharing your solution with everybody). If you have questions about your solution, reach out to Saad per email.

Best,
Goran