Related papers: Minimum Bayes Risk Decoding for Error Span Detecti…

We propose a novel neural sequence prediction method based on \textit{error-correcting output codes} that avoids exact softmax normalization and allows for a tradeoff between speed and performance. Instead of minimizing measures between the…

In most error correction coding (ECC) frameworks, the typical error metric is the bit error rate (BER) which measures the number of bit errors. For this metric, the positions of the bits are not relevant to the decoding, and in many noise…

Recent masked diffusion models (MDMs) have shown competitive performance compared to autoregressive models (ARMs) for language modeling. While most literature has focused on performance enhancing sampling procedures, efficient sampling from…

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…

Among the many ways to model signals, a recent approach that draws considerable attention is sparse representation modeling. In this model, the signal is assumed to be generated as a random linear combination of a few atoms from a…

Large Language Models (LLMs) have become an indispensable part of natural language processing tasks. However, autoregressive sampling has become an efficiency bottleneck. Multi-Draft Speculative Decoding (MDSD) is a recent approach where,…

One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We propose to use word…

We analyze the best achievable performance of Bayesian learning under generative models by defining and upper-bounding the minimum excess risk (MER): the gap between the minimum expected loss attainable by learning from data and the minimum…

The asymptotic iterative decoding performances of low-density parity-check (LDPC) codes using min-sum (MS) and sum-product (SP) decoding algorithms on memoryless binary-input output-symmetric (MBIOS) channels are analyzed in this paper. For…

In this paper, we propose a policy-guided Monte Carlo Tree Search (MCTS) decoder that achieves near maximum-likelihood decoding (MLD) performance for short block codes. The MCTS decoder searches for test error patterns (TEPs) in the…

The recent advancements in large language models (LLMs) have been extraordinary, yet the escalating inference costs associated with them present challenges in real-world applications. To address these challenges, we propose a novel approach…

Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous…

Meta-Learning is a family of methods that use a set of interrelated tasks to learn a model that can quickly learn a new query task from a possibly small contextual dataset. In this study, we use a probabilistic framework to formalize what…

Efficient high-performance decoding of topological stabilizer codes has the potential to crucially improve the balance between logical failure rates and the number and individual error rates of the constituent qubits. High-threshold…

Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements. At the…

In this paper, we present our submissions to the unified WMT25 Translation Evaluation Shared Task. For the Quality Score Prediction subtask, we create a new generation of MetricX with improvements in the input format and the training…

Parallelism has become a central concern in modern decoding frameworks aiming to meet stringent throughput and latency requirements. Guessing Random Additive Noise Decoding (GRAND) is a recently proposed decoding paradigm that tests…

The most commonly used metrics for evaluating automatic speech transcriptions, namely Word Error Rate (WER) and Character Error Rate (CER), have been heavily criticized for their poor correlation to human perception and their inability to…

Automatic Mean Opinion Score (MOS) prediction is crucial to evaluate the perceptual quality of the synthetic speech. While recent approaches using pre-trained self-supervised learning (SSL) models have shown promising results, they only…