چکیده:
Semantic role labeling is the task of attaching semantic tags to the words according to the event represented by the sentence. Persian semantic role labeling is a challenging task and most methods proposed so far depend on a huge number of manually extracted features and are applied on feature engineering to attain high performance. On the other hand, considering the Free-Word-Order and Subject-Object-Verb-Order characteristics of Persian, the arguments of the verbal predicate are often distant and create long-range dependencies. The long-range dependencies can hardly be modeled by these methods. Our goal is to achieve a better performance only with minimal feature engineering and also to capture long-range dependencies in a sentence. To these ends, in this paper a deep model for semantic role labeling is developed with the help of dependency tree for Persian. In our proposed method, for each verbal predicate, the potential arguments are identified by dependency relations, and then the dependency path for each pair of predicate and its candidate argument is embedded using the information in the dependency trees. In the next step, we employed a bi-directional recurrent neural network with long short-term memory units to transform word features into semantic role scores. Experiments have been done on the First Semantic Role Corpus in Persian Language and the corpus provided by the authors. The achieved Macro-average F1-measure is 80.01 for the first corpus and 82.48 for the second one.
خلاصه ماشینی:
Persian semantic role labeling is a challenging task and most methods proposed so far depend on a huge number of manually extracted features and are applied on feature engineering to attain high performance.
To these ends, in this paper a deep model for semantic role labeling is developed with the help of dependency tree for Persian.
Semantic Role Labeling, Full-Syntactic Parsing, Shallow Syntactic Parsing, Dependency Tree, Phrase-structure Tree, Persian language Introduction The goal of natural language processing with machine, as an interdisciplinary science between the language science and computer science, is to understand human language and, in a higher level, to generate it in the world of intelligent computing.
In general, SRL is accomplished in two ways (Yang & Zong, 2016): • Rule-based approach: this method analyses semantic roles of sentence components using the rules defined by linguists for a variety of sentences with different grammatical structures.
In this paper, we focus on Persian semantic role labeling with the help of recurrent neural networks and dependency trees.
To identify and classify arguments, they used a LSTM neural network trained with a dependency parsing tree path and with the features introduced by Xue and Palmer (2004), i.
The second corpus has added a semantic layer to the Uppsala Persian Dependency Treebank (UPDT, which is a collection of sentences with their corresponding dependency trees, including 48 types of syntactic roles and 31 types of POS tags) (Seraji, Ginter, & Nivre, 2016).
Conclusion In this paper, a deep-learning-based method for the semantic role labeling of Persian sentences was developed.