Shinobu Takamatsu

Page segmentation based on thinning of background

This paper presents a new method of page segmentation based on the analysis of background (white areas). The proposed method is capable of segmenting pages with non-rectangular layout as well as with various angles of skew. The characteristics of the method are as follows: (1) thinning of the background enables us to represent white areas of any shape as connected thin lines or chains and the robustness for tilted page images is also achieved by the representation; and (2) based on this representation, the task of page segmentation is defined as to find the loops enclosing printed areas. The task is achieved by eliminating unnecessary chains using not only a feature of white areas, but also a feature of black areas divided by a chain. Based on the experimental results and the comparison with previous methods, we discuss the advantages and limitations of the proposed method.

Semi-automatic program construction from specifications using library modules

A method of semiautomatic specification refinement and program generation using library modules, is described. Users write their specifications and modify and rearrange them so that they can be refined with the aid of the library modules. When a specification is given, a refinement system, called MAPS (module-aided program construction system) searches for library modules applicable to the given specification, replaces the specification with a more detailed description written in the operation part of the modules, and converts the refined specification into a program written in a programming language designated by the user. Case-like expressions or pseudo-natural language expressions are used for describing users specifications and specifications for library modules. >

Feedback of correcting information in postediting to a machine translation system

This paper presents an attempt to construct a feedback system PECOF which improves a Japanese-English Machine Translation system by feedback of correcting information given by posteditors. PECOF analyzes the error-correcting information by using an English-Japanese Machine Translation system which works in the reverse direction to the original MT system, compares the intermediate expressions of the corrected patterns with those of the erroneous parts of the original MT output at every transfer stage and identifies the responsible parts of the original Japanese-English MT system. Then PECOF corrects the irrelevant parts of the database or adds error correcting patterns to a document of postediting to ask users for further examinations for corrections.

Automated procedures for the improvement of a machine translation system by feedback from postediting

In recent years, machine translation has enjoyed limited practical use with the aid of postediting. This paper proposes that feedback of a posteditors corrections to a machine translation system can improve the translation system. We discuss some concrete approaches to the implementation of such a feedback mechanism. Our experimental system analyzes error-correcting information given by posteditors, compares the intermediate expressions of the postedited translation with those of the original translation and identifies the inappropriate or faulty parts of a transfer process so they can be corrected.

A method of post‐processing for character recognition based on syntactic and semantic analysis of sentences

Post-processing of character recognition refers to the processing used to correct the errors in character recognition. When the input is a string representing a sentence in the highly precise error correction, it is desired that the syntactic as well as semantic examinations should be made at the sentence level. This paper assumes that the morphemes, syntax and semantics of the input sentence can be analyzed, and proposes a method that uses the syntactic and semantic analysis in the post-processing. The proposed method receives the list of candidate characters up to the fifth, and outputs the sentence that is adequate from the viewpoints of both syntax and semantics. The method features the following three points: (1) in word matching, it is examined also whether or not a sentence adequate from the viewpoints of syntax and semantics can be composed, and then the inadequate words extraction is inhibited; (2) characters having stronger syntactic and semantic constraints, such as the single-character particle and the conjugational suffix, are estimated top-down. Then, the case where the adequate character is not contained in the candidates can be handled; and (3) the words for which the adequateness cannot be determined from the syntactic or semantic viewpoint are selected by character re-recognition processing. An experiment is executed for 50 sample sentences. The character recognition rate is improved from 83.0 percent to 98.0 percent, and the sentence recognition rate is improved from 10.0 percent to 94.0 percent. Compared to the method based only on word matching, the sentence recognition rate is improved by more than 20 percent. In other words, the effectiveness of the proposed method is demonstrated.

Interpretation of conceptual diagrams from line segments and strings

A conceptual diagram is a kind of diagram which represents a logical structure among concepts using simple physical objects (loops, lines and character strings). This paper presents a method of interpretation of conceptual diagrams. In conceptual diagrams, a single physical object plays various logical roles depending on surrounding physical objects, because there are no specific ruled of writing conceptual diagrams. To cope with this problem, we introduce the strategy of hypothesis generation and verification; hypothesized interpretations are verified by relaxation which takes account of logical relations to other physical objects. From the experimental results using 50 conceptual diagrams, we discuss the effectiveness of our method.