我们介绍了一种用于跨语言训练ASR系统的方法,使用目标语言绝对没有转录的训练数据,并且没有相关语言的语音知识。我们的方法使用了一种解密算法的新应用,该算法仅在目标语言中仅操作不配对的语音和文本数据。我们将此破译应用于由通用电话识别器产生的电话序列,由语言语音语料库培训,我们遵循平稳半监督培训,以获得新语言的声学模型。据我们所知,这是零资源交叉语言ASR的第一种实用方法,不依赖于任何手工制作的语音信息。我们对来自Globalphone语料库的读语音进行了实验,并表明可以在目标语言中仅在20分钟的数据上学习解密模型。当用于生成半监督培训的伪标签时,我们获得了比在同一数据上培训的等同完全监督模型的25%至仅5%的绝对差。
translated by 谷歌翻译
最近,与“预训练,及时和预测”的新范式相比,与“预训练,微调”范式相比,新的范式“预训练,及时和预测”取得了显着的成就。在基于及时的GPT-3成功之后,一系列基于蒙版的语言模型(MLM)(例如Bert,Roberta)及时学习方法变得流行并广泛使用。但是,另一个有效的预训练的判别模型Electra可能被忽略了。在本文中,我们尝试使用拟议的替换代替令牌检测(RTD)基于基于的及时学习方法来完成零摄像的几个NLP任务。实验结果表明,基于RTD-Prompt学习的Electra模型可达到令人惊讶的最先进的零拍性能。在数字上,与MLM-Roberta-Large和MLM-Bert-Large相比,我们的RTD-Electra-Large在所有15个任务上平均提高了约8.4%和13.7%。特别是在SST-2任务上,我们的RTD-Electra-Large在没有任何培训数据的情况下达到了令人惊讶的90.1%精度。总体而言,与预先训练的蒙版语言模型相比,预先训练的代替令牌检测模型在零拍学习中的性能更好。因此,Electra是一位出色的零球学习者。源代码可在以下网址获得:https://github.com/nishiwen1214/rtd-electra。
translated by 谷歌翻译
预先训练的蒙版语言模型通过将下游任务作为文本填充来成功执行几次学习。但是,作为全镜头环境中的强大替代方案,诸如Electra之类的判别预训练模型不适合范式。在这项工作中,我们调整了基于及时的几次学习来进行电信,并表明它在广泛的任务中优于蒙面的语言模型。Electra是预先训练的,以区分令牌是产生还是原始。我们自然地将其扩展到基于迅速的几次学习,通过培训来评分目标选项的原创性,而无需引入新参数。我们的方法很容易适应涉及多token预测的任务,而无需额外的计算开销。分析表明,Electra学习分布与下游任务更好。
translated by 谷歌翻译
Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to downstream NLP tasks, they generally require large amounts of compute to be effective. As an alternative, we propose a more sample-efficient pre-training task called replaced token detection. Instead of masking the input, our approach corrupts it by replacing some tokens with plausible alternatives sampled from a small generator network. Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not. Thorough experiments demonstrate this new pre-training task is more efficient than MLM because the task is defined over all input tokens rather than just the small subset that was masked out. As a result, the contextual representations learned by our approach substantially outperform the ones learned by BERT given the same model size, data, and compute. The gains are particularly strong for small models; for example, we train a model on one GPU for 4 days that outperforms GPT (trained using 30x more compute) on the GLUE natural language understanding benchmark. Our approach also works well at scale, where it performs comparably to RoBERTa and XLNet while using less than 1/4 of their compute and outperforms them when using the same amount of compute.
translated by 谷歌翻译