English
Related papers

Related papers: Differentiable Sampling with Flexible Reference Wo…

200 papers

Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus…

Computation and Language · Computer Science 2021-09-01 Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth target input tokens with predicted ones during training.…

Computation and Language · Computer Science 2021-07-23 Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Despite strong performance in many sequence-to-sequence tasks, autoregressive models trained with maximum likelihood estimation suffer from exposure bias, i.e. the discrepancy between the ground-truth prefixes used during training and the…

Computation and Language · Computer Science 2023-01-11 Michalis Korakakis , Andreas Vlachos

Scheduled sampling is a technique for avoiding one of the known problems in sequence-to-sequence generation: exposure bias. It consists of feeding the model a mix of the teacher forced embeddings and the model predictions from the previous…

Computation and Language · Computer Science 2019-06-28 Tsvetomila Mihaylova , André F. T. Martins

The past several years have witnessed the rapid progress of end-to-end Neural Machine Translation (NMT). However, there exists discrepancy between training and inference in NMT when decoding, which may lead to serious problems since the…

Computation and Language · Computer Science 2017-10-18 Zi-Yi Dou , Hao Zhou , Shu-Jian Huang , Xin-Yu Dai , Jia-Jun Chen

To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we…

Machine Learning · Computer Science 2019-09-17 Sébastien Jean , Orhan Firat , Melvin Johnson

In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source…

Computation and Language · Computer Science 2017-02-16 Christian Hadiwinoto , Hwee Tou Ng

Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from…

Computation and Language · Computer Science 2018-09-24 Marzieh Fadaee , Christof Monz

Neural machine translation (NMT) often makes mistakes in translating low-frequency content words that are essential to understanding the meaning of the sentence. We propose a method to alleviate this problem by augmenting NMT systems with…

Computation and Language · Computer Science 2016-10-06 Philip Arthur , Graham Neubig , Satoshi Nakamura

In simultaneous machine translation, the objective is to determine when to produce a partial translation given a continuous stream of source words, with a trade-off between latency and quality. We propose a neural machine translation (NMT)…

Computation and Language · Computer Science 2020-06-01 Patrick Wilken , Tamer Alkhouli , Evgeny Matusov , Pavel Golik

Discrete diffusion language models (dLLMs) have recently emerged as a promising alternative to traditional autoregressive approaches, offering the flexibility to generate tokens in arbitrary orders and the potential of parallel decoding.…

Machine Learning · Computer Science 2026-04-28 Enshu Liu , Xuefei Ning , Yu Wang , Zinan Lin

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…

Computation and Language · Computer Science 2026-01-15 Giorgio Franceschelli , Mirco Musolesi

Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a…

Computation and Language · Computer Science 2018-04-17 Roman Novak , Michael Auli , David Grangier

The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches. However, on the closely related task of word alignment, traditional…

Computation and Language · Computer Science 2019-09-06 Sarthak Garg , Stephan Peitz , Udhyakumar Nallasamy , Matthias Paulik

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…

Computation and Language · Computer Science 2021-09-10 Chunting Zhou , Daniel Levy , Xian Li , Marjan Ghazvininejad , Graham Neubig

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring…

Computation and Language · Computer Science 2021-05-28 Fusheng Wang , Jianhao Yan , Fandong Meng , Jie Zhou

Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its performance is highly dependent on the quality of the underlying human preference data.…

Machine Learning · Computer Science 2026-03-10 Zixuan Huang , Yikun Ban , Lean Fu , Xiaojie Li , Zhongxiang Dai , Jianxin Li , Deqing Wang

Decoding methods for large language models often trade-off between diversity of outputs and parallelism of computation. Methods such as beam search and Gumbel top-k sampling can guarantee a different output for each element of the beam, but…

Computation and Language · Computer Science 2023-06-02 Luke Vilnis , Yury Zemlyanskiy , Patrick Murray , Alexandre Passos , Sumit Sanghai

Self-training has proven effective for improving NMT performance by augmenting model training with synthetic parallel data. The common practice is to construct synthetic data based on a randomly sampled subset of large-scale monolingual…

Computation and Language · Computer Science 2021-06-03 Wenxiang Jiao , Xing Wang , Zhaopeng Tu , Shuming Shi , Michael R. Lyu , Irwin King

Maximum-likelihood estimation (MLE) is widely used in sequence to sequence tasks for model training. It uniformly treats the generation/prediction of each target token as multi-class classification, and yields non-smooth prediction…

Computation and Language · Computer Science 2018-12-13 Chengyue Gong , Xu Tan , Di He , Tao Qin
‹ Prev 1 2 3 10 Next ›