2026-05-24T18:22:07Zhttps://keep.lib.asu.edu/oai/requestoai:keep.lib.asu.edu:node-1557392024-12-20T18:25:12Zoai_pmh:alloai_pmh:repo_items155739
https://hdl.handle.net/2286/R.I.45031
http://rightsstatements.org/vocab/InC/1.0/
All Rights Reserved
2017
65 pages
Masters Thesis
Academic theses
Text
eng
Agarwal, Shubham
Baral, Chitta
Li, Baoxin
Yang, Yezhou
Arizona State University
Masters Thesis Computer Science 2017
In this thesis, I propose a new technique of Aligning English sentence words<br/><br/>with its Semantic Representation using Inductive Logic Programming(ILP). My<br/><br/>work focusses on Abstract Meaning Representation(AMR). AMR is a semantic<br/><br/>formalism to English natural language. It encodes meaning of a sentence in a rooted<br/><br/>graph. This representation has gained attention for its simplicity and expressive power.<br/><br/>An AMR Aligner aligns words in a sentence to nodes(concepts) in its AMR<br/><br/>graph. As AMR annotation has no explicit alignment with words in English sentence,<br/><br/>automatic alignment becomes a requirement for training AMR parsers. The aligner in<br/><br/>this work comprises of two components. First, rules are learnt using ILP that invoke<br/><br/>AMR concepts from sentence-AMR graph pairs in the training data. Second, the<br/><br/>learnt rules are then used to align English sentences with AMR graphs. The technique<br/><br/>is evaluated on publicly available test dataset and the results are comparable with<br/><br/>state-of-the-art aligner.
Computer Science
Aligning English Sentences with Abstract Meaning Representation Graphs using Inductive Logic Programming