Joint A* CCG Parsing and Semantic Role Labelling
نویسندگان
چکیده
Joint models of syntactic and semantic parsing have the potential to improve performance on both tasks—but to date, the best results have been achieved with pipelines. We introduce a joint model using CCG, which is motivated by the close link between CCG syntax and semantics. Semantic roles are recovered by labelling the deep dependency structures produced by the grammar. Furthermore, because CCG is lexicalized, we show it is possible to factor the parsing model over words and introduce a new A∗ parsing algorithm— which we demonstrate is faster and more accurate than adaptive supertagging. Our joint model is the first to substantially improve both syntactic and semantic accuracy over a comparable pipeline, and also achieves state-of-the-art results for a nonensemble semantic role labelling model.
منابع مشابه
Joint A∗ CCG Parsing and Semantic Role Labeling
Joint models of syntactic and semantic parsing have the potential to improve performance on both tasks—but to date, the best results have been achieved with pipelines. We introduce a joint model using CCG, which is motivated by the close link between CCG syntax and semantics. Semantic roles are recovered by labelling the deep dependency structures produced by the grammar. Furthermore, because C...
متن کاملبرچسبزنی خودکار نقشهای معنایی در جملات فارسی به کمک درختهای وابستگی
Automatic identification of words with semantic roles (such as Agent, Patient, Source, etc.) in sentences and attaching correct semantic roles to them, may lead to improvement in many natural language processing tasks including information extraction, question answering, text summarization and machine translation. Semantic role labeling systems usually take advantage of syntactic parsing and th...
متن کاملBrutus: A Semantic Role Labeling System Incorporating CCG, CFG, and Dependency Features
We describe a semantic role labeling system that makes primary use of CCG-based features. Most previously developed systems are CFG-based and make extensive use of a treepath feature, which suffers from data sparsity due to its use of explicit tree configurations. CCG affords ways to augment treepathbased features to overcome these data sparsity issues. By adding features over CCG wordword depe...
متن کاملAssigning Function Labels to Unparsed Text
In this paper, we propose a novel solution to the problem of assigning function labels to syntactic constituents. This task is a useful intermediate step between syntactic parsing and semantic role labelling. What distinguishes our proposal from other attempts in function or semantic role labelling is that we perform the learning of function labels at the same time as parsing. We reach state-of...
متن کاملSemantic Role Labelling without Deep Syntactic Parsing
This article proposes a method of Semantic Role Labelling for languages with no reliable deep syntactic parser and with limited corpora annotated with semantic roles. Reasonable results may be achieved with the help of shallow parsing, provided that features used for training such shallow parsers include both lexical semantic information (here: hypernymy) and syntactic information.
متن کامل