File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/89/p89-1020_concl.xml
Size: 3,096 bytes
Last Modified: 2025-10-06 13:56:26
<?xml version="1.0" standalone="yes"?> <Paper uid="P89-1020"> <Title>A General Computational Treatment Of The Comparative</Title> <Section position="8" start_page="166" end_page="166" type="concl"> <SectionTitle> 7 Concluding Remarks </SectionTitle> <Paragraph position="0"> We have presented a method for incorporating general comparatives into a system without unduly complicating the system. This is done in the syntactic analysis component by treating the comparatives the same as similar structures so that features of the syntactic analyzer that already exist may be utilized. The various comparative structures are then regularized so that they are in a standard form consisting of a comparative operator and two complete clauses that contain a quantity er or than which is interpreted by the semantic component as a quantity such as how, how many, or how much, as appropriate. A preliminary quantifier analysis component was added to determine whether a sentence containing a higher order operator has any quantifiers which have a wider scope than the operator, and to label those that do.</Paragraph> <Paragraph position="1"> The remainder of the processing is done as usual except for minor modifications.</Paragraph> <Paragraph position="2"> The treatment of the comparative that we have presented is more extensive and general than that of other NLP Systems to date, and also is simple to implement. Only a small number of productions of the BNF component were changed to cover the comparative structures described in this paper. In addition, three restrictions were modified for the comparative, and a set of separate add-on restrictious were included to handle comparative zeroing patterns and scope marker requirements. Special regularization procedures were written to regularize the different comparative forms so that the standard Montague-style compositional translation rules could be used prior to the comparative regularization phase.</Paragraph> <Paragraph position="3"> Although we can process many forms of the comparative, there is still substantial work that remains which involves comparative sentences where the comparative clause itself has been omitted, as in New York banks are starting to offer higher interest rates. In some cases the comparison is between two different time periods; in other cases the comparison involves different types of like objects, such as the interest rates of New York banks compared to the interest rates of Florida banks.</Paragraph> <Paragraph position="4"> The context can often be an aid in helping to recover the missing information, but the recovery problem is still quite a challenge. Sentences with this type of anaphora are very interesting because they occur surprisingly regularly in language, and yet the recovery possibilities are more limited and more controlled than those occurring in discourse in general.</Paragraph> <Paragraph position="5"> Possibly these type of sentences can provide us with clues as to what elements are significant for the recovery of the missing information.</Paragraph> </Section> class="xml-element"></Paper>