Résumé
OBJECTIVES: Anaphora recognition is a process to identify exactly which noun has been used previously and relates to a pronoun that is included in a specific sentence later. Therefore, anaphora recognition is an essential element of a dialogue agent system. In the current study, all the merits of rule-based, machine learning-based, semantic-based anaphora recognition systems were combined to design and realize a new hybrid-type anaphora recognition system with an optimum capacity. METHODS: Anaphora recognition rules were encoded on the basis of the internal traits of referred expressions and adjacent contexts to realize a rule-based system and to serve as a baseline. A semantic database, related to predicate instances of sentences including referred expressions, was constructed to identify semantic co-relationships between the referent candidates (to which semantic tags were attached) and the semantic information of predicates. This approach would upgrade the anaphora recognition system by reducing the number of referent candidates. Additionally, to realize a machine learning-based system, an anaphora recognition model was developed on the basis of training data, which indicated referred expressions and referents. The three methods were further combined to develop a new single hybrid-based anaphora recognition system. RESULTS: The precision rate of the rule-based systems was 54.9%. However, the precision rate of the hybrid-based system was 63.7%, proving it to be the most efficient method. CONCLUSIONS: The hybrid-based method, developed by the combination of rule-based and machine learning-based methods, represents a new system with enhanced functional capabilities as compared to other pre-existing individual methods.
Sujets)
Prestations des soins de santé , Traitement du langage naturel , SémantiqueRésumé
O poema “A mesa”, numa primeira leitura, consistiria na fala de um filho dirigida a seu pai: lançando a hipótese de uma festa em homenagem ao pai, o filho passa a descrever como seria esse “grande jantar”. Mas, evidentemente, o Poeta vai muito além da mera descrição. Com efeito, ao reunir a família inteira - os mortos e os vivos - as dimensões temporais e espaciais acabam por se fundir: passado e presente se condensam num mesmo espaço e objeto, a mesa. Cabe indagar, afinal de contas: 1. Como é esse fazer poético do ubíquo e do icônico? 2. Com que mecanismo e instrumentos linguísticos o Poeta constrói essa reunião de vivos e mortos em tomo da mesa, num só tempo e espaço? 3. Por que reunir a família toda e o que busca o Poeta nesse percurso em volta da mesa? Nosso propósito, neste artigo, é responder essas perguntas.
The poem “The table”, on a first reading, would consist in the speech of a son addressed to his father: introducing the hypothesis of a party to honor his father, the son begins to describe what this “great dinner” might be. But it is evident that the Poet goes far beyond a mere description. Indeed, by bringing together the whole family - the dead and alive ones - the temporal and spatial dimensions end up merging: past and present are condensed in a single space and object, the table. It is worth asking, after all: 1. How is this poetics of the ubiquitous and iconic? 2. Through what mechanism and linguistic tools does the Poet build this meeting between the living and dead ones around the table, at a single time and space? 3. Why gathering the whole family and what does the Poet seek in this path around the table? Our purpose, in this paper, is to answer these questions.