A Shortest-path Method for Arc-factored Semantic Role Labeling
نویسندگان
چکیده
We introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments. Our main contribution is to formulate SRL in terms of shortest-path inference, on the assumption that the SRL model is restricted to arc-factored features of the syntactic paths behind semantic roles. Overall, our method for SRL is a novel way to exploit larger variability in the syntactic realizations of predicate-argument relations, moving away from pipeline architectures. Experiments show that our approach improves the robustness of the predictions, producing arc-factored models that perform closely to methods using unrestricted features from the syntax.
منابع مشابه
ALGORITHMS FOR BIOBJECTIVE SHORTEST PATH PROBLEMS IN FUZZY NETWORKS
We consider biobjective shortest path problems in networks with fuzzy arc lengths. Considering the available studies for single objective shortest path problems in fuzzy networks, using a distance function for comparison of fuzzy numbers, we propose three approaches for solving the biobjective prob- lems. The rst and second approaches are extensions of the labeling method to solve the sing...
متن کاملShortest Path Problem with Gamma Probability Distribution Arc Length
We propose a dynamic program to find the shortest path in a network having gamma probability distributions as arc lengths. Two operators of sum and comparison need to be adapted for the proposed dynamic program. Convolution approach is used to sum two gamma probability distributions being employed in the dynamic program.
متن کاملFinding the Shortest Path in Dynamic Network using Labeling Algorithm
This study concerns the problem of finding shortest paths from one node to all other nodes in networks for which arc costs can vary with time, each arc has a transit time and parking with a corresponding time-varying cost is allowed at the nodes. it show that this problem is equivalent to a classical shortest path problem in a timeexpanded network. The label correcting algorithm is used for fin...
متن کاملChinese Semantic Role Labeling with Dependency-Driven Constituent Parse Tree Structure
This paper explores a tree kernel-based method for nominal semantic role labeling (SRL). In particular, a new dependency-driven constituent parse tree (D-CPT) structure is proposed to better represent the dependency relations in a CPT-style structure, which employs dependency relation types instead of phrase labels in CPT. In this way, D-CPT not only keeps the dependency relationship informatio...
متن کاملJoint Arc-factored Parsing of Syntactic and Semantic Dependencies
In this paper we introduce a joint arc-factored model for syntactic and semantic dependency parsing. The semantic role labeler predicts the full syntactic paths that connect predicates with their arguments. This process is framed as a linear assignment task, which allows to control some well-formedness constraints. For the syntactic part, we define a standard arc-factored dependency model that ...
متن کامل