Anaphora Resolution Jo˜aoMarques IST – Instituto Superior T´ ecnico L 2 F – Spoken Language Systems Laboratory – INESC ID Lisboa Rua Alves Redol 9, 1000-029 Lisboa, Portugal jsmarques@l2f.inesc-id.pt Abstract This paper describes the implementation of an hybrid ap- proach to Anaphora Resolution (AR) in Portuguese. ARM 2.0. has been incorporated in a fully-pledged Natural Language Processing system (STRING) and evaluated on a large, manually annotated corpus. 1 Introduction In a time when Natural Language Processing (NLP) draws more and more at- tention, the task of anaphora resolution presents itself as critical for many ap- plications such as machine translation, information extraction and question an- swering. For a machine, it is difficult to select the correct entity (antecedent) to which the anaphor (mention) refers, mostly due to the ambiguous nature of natural languages. To overcome this drawback, a great amount of linguistic knowledge (morphological, lexical, syntactic, semantic, and even world knowl- edge) may be required. Anaphora is a major discursive device used to avoid repetition and increase the cohesion of the text, making the interpretation of sentences depend upon the interpretation of the previous ones (1.1). (1.1) Lu´ ıs Figo ´ e um ex-futebolista portuguˆ es. Em 2001, ele foi distin- guido como melhor jogador do Mundo. Lu´ ıs Figo is a former Portuguese football player. In 2001, he was distin- guished as the world’s best player. A human reader immediately understands that, in the second sentence, it was Lu´ ıs Figo that was distinguished as the world’s best player in 2001. However, this deduction actually requires that a link be established between Lu´ ıs Figo in the first sentence and ele (he) in the second. Only then, can the prize mentioned in the second sentence be attributed to Lu´ ıs Figo in the first. Therefore, the interpretation of the second sentence is dependent of the former ensuring in this way, the cohesion between the two sentences of this discourse. Besides contributing to the cohesion of the discourse, the two expressions are co-referential since they both refer to the same person in the real world, Lu´ ıs Figo. Anaphora can also be classified according to the antecedents location: