---

Mēya is an application of LDC-IL that calculates the edit rate and distance between two given strings. It can be used to calculate the edit rate and distance of any text in comparison with its modified text.

Mēya utilizes the dynamic programming approach of computing the Levenshtein Distance. It constructs a matrix where each cell represents the edit distance between corresponding substrings of the input strings. By iteratively filling the matrix based on edit operations, such as insertion, deletion, or substitution, the algorithm determines the minimum edit distance between the strings. It tokenizes the input strings to calculate the edit distance at the word level. These edit distances are computed to get respective edit rates. it considers series of whitespace as singe space. As part of pre-processing, the given strings are trimmed of leading and trailing spaces.

Writers and editors can utilize Mēya to assess the similarity between different versions of a text. It can be used for quality control of Spell checking, OCR and ASR systems by comparing their output with their post-corrected data.

Mēya operates on two strings provided in the text boxes or can compare text of two text files. It is also capable of handling multiple text files from two distinct folders. When reading text files from the folder containing the original text, it attempts to find and compare them with files of the same name in the folder containing modified text files. If there is no matching file it assigns the edit distance as -1. Once all text files are paired, Mēya displays each file's character and word edit rates in a data grid view, alongside its file name.

Credits: Rajesha N, Linguistic Data Consortium for Indian Languages (LDC-IL), Central Institute of Indian Languages, Mysore.

Meya Interface :