How useful are similarity word lists for indirect anaphora resolution
Susanne Salmon-Alt, Renata La Rocca Vieira, Caroline Gasperin · HAL (Le Centre pour la Communication Scientifique Directe) · 2005
This work tests the use of word similarity lists for anaphora resolution in Portuguese and French corpora. We applied an automatic lexical acquisition technique over parsed texts to identify semantically similar words. We then made use of this lexical knowledge to resolve coreferential definite descriptions where the head noun of the anaphor is different from the head noun of its antecedent, which we call indirect anaphora. We compare the results in both languages with a baseline algorithm. Our proposed technique achieved an Fmeasure of 0.26 for Portuguese and 0.09 for French.