MIT Press

Table 3

Processing steps for one of the search results of the query snow leopard.

step	output
initial snippet	“Get the facts on snow leopards. Endangered Species Act (ESA): the snow leopard is listed as endangered”
tokenization	{ get, the, facts, on, snow, leopards, endangered, species, act, esa, leopard, is, listed, as }
compounding and lemmatization	{ get, fact, on, snow, leopard, snow_leopard, endangered, species, endangered_species, act, be, listed, as }
stopword and query words removal	{ fact, endangered, species, endangered_species, act, listed }

step	output
initial snippet	“Get the facts on snow leopards. Endangered Species Act (ESA): the snow leopard is listed as endangered”
tokenization	{ get, the, facts, on, snow, leopards, endangered, species, act, esa, leopard, is, listed, as }
compounding and lemmatization	{ get, fact, on, snow, leopard, snow_leopard, endangered, species, endangered_species, act, be, listed, as }
stopword and query words removal	{ fact, endangered, species, endangered_species, act, listed }