File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/98/p98-1116_intro.xml
Size: 1,038 bytes
Last Modified: 2025-10-06 14:06:36
<?xml version="1.0" standalone="yes"?> <Paper uid="P98-1116"> <Title>Generation that Exploits Corpus-Based Statistical Knowledge</Title> <Section position="3" start_page="704" end_page="704" type="intro"> <SectionTitle> 2 Abstract Meaning Representation </SectionTitle> <Paragraph position="0"> The AMR language is composed of concepts from the SENSUS knowledge base (Knight and Luk, 1994}, including all of WordNet 1.5 (Miller, 1990), and keywords relating these concepts to each other) An AMR is a labeled directed graph, or feature structure, derived from the PENMAN Sentence Plan Language (Penman, 1989). The most basic AMR is of the form (label / concept), e.g.: ~ (ml / \[dog<canidl) The slash is shorthand for a type (or instance) feature, and in logic notation this AMR might be written as instance(m1, dog). This AMR can represent &quot;the dog,&quot; &quot;the dogs,&quot; &quot;a dog,&quot; or &quot;dog,&quot; etc. A concept can be modified using keywords:</Paragraph> </Section> class="xml-element"></Paper>