Semantic Syntactical Matrix Analysis

1203 Words5 Pages

Existing STS approaches discard syntactic information associated with words. In this paper, we propose Semantic-Syntactic Short text similarity Approach based on Keyword extraction and Syntactical Scaled Mapping Method for (SAG) System. First Phase, the Statistical Scaled Syntactical Relation (SSSR) Model based on the Link Parser (LP) uses statistical to Scale SR in short answer structure. Second phase: proposed Key Words Extraction and Syntactic Relation Mapping (WESRM) Approach to extract main words from each ESC and assign the SSR to each extracted word. Finally, Semantic-Syntactical Matrix (SSM) to integrate the scaled syntactic relations with WUP knowledge-based model to grade SA. To evaluate our system, Difference Measurement (DM) and …show more content…

The features in the context are rare due to short ranging from a single to a dozen of words. This affects the grading process of such answer length [1]. This guides most SAG systems to focus on semantic similarity features [17] [3]. Most exist systems ignore syntactic information. Here, the students respond with an unstructured and a non-well-formed bag of words which apart from Model Answer (MA). Here, the systems used semantic similarity rather than the syntactic structure which assigns a high grade to student answer [2]. Claimed made that short answers often composed many syntactic errors which led to erroneous grading results [4] [5]. Meanwhile, [6] found the frequent errors are not serious syntactical errors which impeded answer …show more content…

To the best of our knowledge, the parser is not used extensively in SAG systems. Link Parser (LG) Parser used by [22] to extract syntactic relations between words. Similar links of sentences located with each word. Wu and Palmer knowledge-based semantic similarity model applied to locate semantic similarities between each related word pair in the model answers and student answers, in case both pairs have a similar syntactic relation. Here, the Syntactic relations used to strict the semantic similarity between each pair. The maximum similarity of each row in the matrix calculated as the log of total grades summation. The words presented in pair manner which prevents to distinguish relations between each word with others in the text syntactical relations structure, which made the syntactical information and other syntactical text structures

Open Document