Papers by Shlomo Chazan
Optimized Tokenization for Transcribed Error Correction (2023.emnlp-main)
Copied to clipboard
| Challenge: | transcribed-like data is often used to correct recurring errors, but training with synthetic data is difficult. |
| Approach: | They propose to use synthetic transcribed-like data to train error correction models . they show that synthetic data outperforms the common approach of random perturbations . |
| Outcome: | The proposed method outperforms the common method using random perturbations in transcribed data and language-specific adjustments to the vocabulary of a BPE tokenizer. |
Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks (2025.acl-long)
Copied to clipboard
| Challenge: | a growing number of recorded human speech is recorded for automated processing, resulting in errors in the transcripts . a configurable framework is proposed to analyze transcript noise impact across noise levels and transcript-cleaning techniques. |
| Approach: | They propose a configurable framework for assessing task models in diverse noisy settings . framework facilitates investigation of task model behavior, which can support effective SLU solutions. |
| Outcome: | The proposed framework can analyze model behavior in various noise levels and transcript-cleaning techniques. |