Unni Cathrine Eiken February 2005

Unni Cathrine Eiken February 2005 Unni Cathrine Eiken February 2005

10.04.2013 Views

process. To be as useful as possible, the meaning structures should be normalised and generalisable. The examples above show how normalisation through use of EPAS realises the concept of canonical form to some degree and seems particularly useful for the purpose of the present work. By using grammatic relations such as subject and object as reference points, semantically equivalent sentences, such as (3-2a) and (3-2b), would be given different meaning structures due to the difference in verbal voice. Structuring the meanings conveyed with the sentences in (3-2) within a grammatical relations paradigm would make it necessary to mark the verbal voice as well as the grammatical relations. In addition, active and passive structures would have to be treated differently in the subsequent analysis. Basing the extraction merely on syntactic properties of the sentences in the corpus would make the extracted material very difficult to classify, mainly because similar meanings would be represented differently. The advantages of a normalised and generalisable dataset is further clarified by the following example. Upon a simple grammatical analysis, the sentences shown in (3- 2) can be categorised based on the syntactic roles predicate, subject and object. The result of such a classification is shown in examples (3-5) and (3-6): (3- 5) predicate subject object a. drepe morder kvinne kill b. drepe kill c. drepe kill murderer kvinne woman kvinne woman woman murderer murderer ? The structures in (3-5) above can be extracted upon part of speech tagging of the sentences in (3-2). The active and passive predicate receives the same structure, and as no semantic information is available, the structuring of the arguments is in accordance with their status as subject or object. Attempting to classify these subjects and objects based on their co-occurrence with the predicate produces groupings of words which are not directly generalisable. Murderer 38

and woman occur together both in subject and object position, not reflecting the preferred selectional constrictions within the domain. (3- 6) predicate subject object a. drepe morder kvinne kill murderer woman a. drepes kvinne morder is-killed woman murderer b. drepes kvinne ? is-killed woman Example (3-6) provides a more elegant structuring. Because an extraction method based on syntactic relations is unable to generalise over verbal voice, two separate predicates are extracted, one for the passive and one for the active voice. Even though logically, the same action is performed on the entity the woman in both sentences in (3-6), a method as outlined above would not allow for a straightforward interpretation of this. The generalisation between active and passive versions of the same sentence is lost in such an approach. This would result in a higher number of predicates, and therefore in a less generalisable data material. It is likely that results as outlined above would also be of less use as a referent guessing helper in an anaphora resolution system, precisely because of the lower level of generalisability. 3.2.1 What is represented in the EPAS? Jurafsky and Martin (2000, p. 510) state that all languages have predicate-argument structures at the core of their semantic structure. They further describe that the grammar organises the predicate-argument structure and selectional constraints restrict how other words and phrases can combine with a given word. In this project, a simplified version of predicate-argument structures is used as meaning representation. The EPAS, or meaning representations, are limited to consist of two nominal arguments at the most. Either one of the arguments in an EPAS may be empty/unidentified. This means that the EPAS extracted from my texts will belong to one of the following three patterns: 39

and woman occur together both in subject and object position, not reflecting the preferred<br />

selectional constrictions within the domain.<br />

(3- 6)<br />

predicate subject object<br />

a. drepe morder kvinne<br />

kill murderer woman<br />

a. drepes kvinne morder<br />

is-killed woman murderer<br />

b. drepes kvinne ?<br />

is-killed woman<br />

Example (3-6) provides a more elegant structuring. Because an extraction method based on<br />

syntactic relations is unable to generalise over verbal voice, two separate predicates are<br />

extracted, one for the passive and one for the active voice. Even though logically, the same<br />

action is performed on the entity the woman in both sentences in (3-6), a method as outlined<br />

above would not allow for a straightforward interpretation of this. The generalisation between<br />

active and passive versions of the same sentence is lost in such an approach. This would result in<br />

a higher number of predicates, and therefore in a less generalisable data material. It is likely that<br />

results as outlined above would also be of less use as a referent guessing helper in an anaphora<br />

resolution system, precisely because of the lower level of generalisability.<br />

3.2.1 What is represented in the EPAS?<br />

Jurafsky and Martin (2000, p. 510) state that all languages have predicate-argument structures at<br />

the core of their semantic structure. They further describe that the grammar organises the<br />

predicate-argument structure and selectional constraints restrict how other words and phrases<br />

can combine with a given word. In this project, a simplified version of predicate-argument<br />

structures is used as meaning representation. The EPAS, or meaning representations, are limited<br />

to consist of two nominal arguments at the most. Either one of the arguments in an EPAS may<br />

be empty/unidentified. This means that the EPAS extracted from my texts will belong to one of<br />

the following three patterns:<br />

39

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!