Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model
Recent advances in conditional recurrent language modelling have mainly focused on network architectures (e.g., attention mechanism), learning algorithms (e.g., scheduled sampling and sequence-level training) and novel applications (e.g., image/video description generation, speech recognition, etc.) On the other hand, we notice that decoding algorithms/strategies have not been investigated as much, and it has become standard to use greedy or beam search. In this paper, we propose a novel decoding strategy motivated by an earlier observation that nonlinear hidden layers of a deep neural network stretch the data manifold. The proposed strategy is embarrassingly parallelizable without any communication overhead, while improving an existing decoding algorithm. We extensively evaluate it with attention-based neural machine translation on the task of En->Cz translation.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingMachine Translationspeech-recognitionSpeech RecognitionTranslationVideo DescriptionSimilar Papers 제목 키워드 기반
Putting Machine Translation in Context with the Noisy Channel Model
We show that Bayes' rule provides a compelling mechanism for controlling unconditional document language models, using the long-standing challenge of effectively leveraging document context in machine translation. In our…
Document TranslationLanguage ModelingLanguage ModellingMachine Translation+3Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
Discrete diffusion language models (dLLMs) accelerate text generation by unmasking multiple tokens in parallel. However, parallel decoding introduces a distributional mismatch: it approximates the joint conditional using…
Text GenerationMaximum Likelihood Decoding of Quantum Error Correction Codes
Quantum error correction (QEC) is indispensable for realizing fault-tolerant quantum computation, yet its effectiveness hinges critically on the classical decoding algorithm that interprets noisy syndrome measurements. A…
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs …
Text GenerationAIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
The linear-chain Conditional Random Field (CRF) model is one of the most widely-used neural sequence labeling approaches. Exact probabilistic inference algorithms such as the forward-backward and Viterbi algorithms are t…
ChunkingVariational Inference