Levenshtein
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Sequence Reconstruction for Substitution Channel: New Sufficient Conditions and Algorithms
Announce Type: new Abstract: In the sequence reconstruction problem, a codeword $\x$ is transmitted through several identical channels where each channel produces a noisy read of $\x$, and the problem is to analyze how to uniquely reconstruct $\x$ based on these noisy reads. Levenshtein has studied the minimum number of reads which guarantees unique reconstruction of $\x$, which is one sufficient condition for unique reconstruction. In this paper, we move on to a different perspective and...
Multi-task Learning is Not Enough: Representational Entanglement in Dual-output Second Language Speech Recognition
arXiv:2606.06065v2 Announce Type: replace Abstract: Second-language (L2) speech recognition often requires transcriptions of pronunciations and intended meanings. Multi-task learning (MTL) is a natural approach because it assumes that shared representations benefit both outputs. However, this paper shows that this assumption does not hold across Korean and English.
NormEval: A Unified Multi-Metric Framework for Evaluating Semantic Fidelity in Text Normalization
arXiv:2511.20409v2 Announce Type: replace Abstract: Text normalization methods such as stemming and lemmatization are fundamental components of NLP pipelines. As new normalization tools are developed for diverse languages, evaluation methodologies remain fragmented, relying on Compression Ratio, downstream accuracy, or sequence-to-sequence prediction scores in isolation, failing to distinguish between beneficial vocabulary reduction and harmful semantic distortion.
Multi-task Learning is Not Enough: Representational Entanglement in Dual-output Second Language Speech Recognition
Announce Type: new Abstract: Second-language (L2) speech recognition often requires transcriptions of pronunciations and intended meanings. Multi-task learning (MTL) is a natural approach because it assumes that shared representations benefit both outputs. However, this paper shows that this assumption does not hold across Korean and English.