Vinciarelli Alessandro
IDIAP Research Institute, Rue du Simplon 4, 1920 Martigny, Switzerland.
IEEE Trans Pattern Anal Mach Intell. 2005 Dec;27(12):1882-95. doi: 10.1109/TPAMI.2005.248.
This work presents categorization experiments performed over noisy texts. By noisy, we mean any text obtained through an extraction process (affected by errors) from media other than digital texts (e.g., transcriptions of speech recordings extracted with a recognition system). The performance of a categorization system over the clean and noisy (Word Error Rate between approximately 10 and approximately 50 percent) versions of the same documents is compared. The noisy texts are obtained through handwriting recognition and simulation of optical character recognition. The results show that the performance loss is acceptable for Recall values up to 60-70 percent depending on the noise sources. New measures of the extraction process performance, allowing a better explanation of the categorization results, are proposed.
这项工作展示了对噪声文本进行的分类实验。所谓噪声文本，是指通过从数字文本以外的媒体（如用识别系统提取的语音记录转录文本）进行提取过程（受错误影响）而获得的任何文本。我们比较了分类系统在相同文档的干净版本和噪声版本（字错误率约在10%至约50%之间）上的性能。噪声文本是通过手写识别和光学字符识别模拟获得的。结果表明，根据噪声源不同，召回率高达60%至70%时，性能损失是可以接受的。我们还提出了提取过程性能的新度量方法，以便更好地解释分类结果。
