{"type":"ScholarlyArticle","title":"Statistical Parsing with Probabilistic Symbol-Refined Tree Substitution Grammars","authors":[{"name":"Hiroyuki Shindo","slug":"hiroyuki-shindo","given":"Hiroyuki","family":"Shindo","affiliation":""},{"name":"Yusuke Miyao","slug":"yusuke-miyao","given":"Yusuke","family":"Miyao","affiliation":""},{"name":"Akinori Fujino","slug":"akinori-fujino","given":"Akinori","family":"Fujino","affiliation":""},{"name":"Masaaki Nagata","slug":"masaaki-nagata","given":"Masaaki","family":"Nagata","affiliation":""}],"abstract":"We present probabilistic Symbol-Refined Tree Substitution Grammars (SR-TSG) for statistical parsing of natural language sentences. An SR-TSG is an extension of the conventional TSG model where each nonterminal symbol can be refined (subcategorized) to fit the training data. Our probabilistic model is consistent based on the hierarchical Pitman-Yor Process to encode backoff smoothing from a fine-grained SR-TSG to simpler CFG rules, thus all grammar rules can be learned from training data in a fully automatic fashion. Our SR-TSG parser achieves the state-of-the-art performance on the Wall Street Journal (WSJ) English Penn Treebank data.","doi":null,"url":"https://ijcai.org/proceedings/2013/461","pdf":"https://ijcai.org/proceedings/2013/0461.pdf","markdown":"https://ijcai.org/proceedings/2013/461.md","bibtex":"https://ijcai.org/proceedings/2013/bibtex/461","volume":{"slug":"2013","title":"Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2013","url":"https://ijcai.org/proceedings/2013/","year":2013,"location":"Beijing, China","dates":"3–9 August 2013","editors":"Francesca Rossi","isbn":"978-1-57735-633-2","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":461,"pages":{"first":3082,"last":3085},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}