Fragmentation strictly raises optimal finite-context log-loss on Markov sources while tokenization can make a short token window equivalent to a longer source window under reliability and compression conditions.
hub
Neural Machine Translation of Rare Words with Subword Units
28 Pith papers cite this work. Polarity classification is still indexing.
28
Pith papers citing it
abstract
Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper, we introduce a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units. This is based on the intuition that various word classes are translatable via smaller units than words, for instance names (via character copying or transliteration), compounds (via compositional translation), and cognates and loanwords (via phonological and morphological transformations). We discuss the suitability of different word segmentation techniques, including simple character n-gram models and a segmentation based on the byte pair encoding compression algorithm, and empirically show that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English-German and English-Russian by 1.1 and 1.3 BLEU, respectively.
hub tools
representative citing papers
Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.
Subword tokenization impairs phonological knowledge encoding in LMs, but an IPA-based fine-tuning method restores it with minimal impact on other capabilities.
MIXAR is the first autoregressive pixel-based language model for eight languages and scripts, with empirical gains on multilingual tasks, robustness to unseen languages, and further improvements when scaled to 0.5B parameters.
Dual Triangle Attention achieves effective bidirectional attention with built-in positional inductive bias via dual triangular masks, outperforming standard bidirectional attention on position-sensitive tasks and showing strong masked language modeling results with or without positional embeddings.
Chronos pretrains transformer models on tokenized time series to deliver strong zero-shot forecasting across diverse domains.
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
OPT releases open decoder-only transformers up to 175B parameters that match GPT-3 performance at one-seventh the carbon cost, along with code and training logs.
T5 casts all NLP tasks as text-to-text generation, systematically explores pre-training choices, and reaches strong performance on summarization, QA, classification and other tasks via large-scale training on the Colossal Clean Crawled Corpus.
Language models fine-tuned via RL on 5k-60k human preference comparisons produce stylistically better text continuations and human-preferred summaries that sometimes copy input sentences.
Deep learning generalization error follows power-law scaling with training set size across multiple domains, with model size scaling sublinearly with data size.
BabelDOC uses an intermediate representation to decouple layout from content for improved layout-preserving PDF translation.
Perturbation probing identifies tiny sets of FFN neurons that control refusal templates and language routing in LLMs, enabling precise ablations and directional interventions that alter behavior on benchmarks while preserving safety.
VulStyle pre-trains on 4.9M functions using code, non-terminal ASTs, and stylometry features, then fine-tunes to achieve SOTA F1 gains of 4-48% on BigVul and VulDeePecker.
The paper derives an algebraic condition for when data-knowledge pairs are jointly informative enough to uniquely solve Lyapunov equations.
FAST applies discrete cosine transform to robot action sequences for efficient tokenization, enabling autoregressive VLAs to succeed on high-frequency dexterous tasks and scale to 10k hours of data while matching diffusion VLA performance with up to 5x faster training.
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
Scaling an autoregressive Transformer to 20B parameters for text-to-image generation using image token sequences achieves new SOTA zero-shot FID of 7.23 and fine-tuned FID of 3.22 on MS-COCO.
LaMDA shows that fine-tuning on human-value annotations and consulting external knowledge sources significantly improves safety and factual grounding in large dialog models beyond what scaling alone achieves.
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
An interpretable deep learning framework with a new tokenizer is used to quantify how grammatical gender information is distributed between lemmas and sentential context during the Latin-to-Occitan transition.
DNA pretraining suffers from inappropriate evaluation datasets, flawed neighbor-masking, and neglected vocabulary design; the authors supply guidelines and a reproducible testbed to fix them.
LLMs handle skin tone emoji modifiers better than dedicated embedding models but display systemic disparities in sentiment and semantic consistency across tones.
Empirical tests on software engineering tasks show Chinese prompts do not reduce token usage or improve success rates over English for LLM coding.
citing papers explorer
No citing papers match the current filters.