arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.07253cs.CLcs.AIcs.LGcs.SDeess.AS
收藏

用于端到端口语语言理解的预训练网络与连续Token接口的集成

Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding

Clova AI, NAVER Corp.(NAVER公司Clova AI);Inha University(仁荷大学)

Seunghyun Seo, Donghyun Kwak, Bowon Lee

摘要:

大多数端到端(E2 E)SLU网络利用预先训练的ASR网络,但仍然缺乏理解话语语义的能力,这对于SLU任务至关重要。为了解决这个问题,最近提出的研究使用预训练的NLU网络。然而,充分利用两个预先训练的网络并不是一件小事;人们提出了许多解决方案,例如知识蒸馏,跨模态共享嵌入以及与接口的网络集成。我们提出了一种简单而强大的集成方法,E2 E SLU网络与新的接口,连续令牌接口(CTI),连接表示的ASR和NLU网络时,这两个网络是预先训练相同的词汇。因为唯一的区别是噪声水平,所以我们直接将ASR网络的输出馈送到NLU网络。因此,我们可以以E2 E方式训练我们的SLU网络,而无需额外的模块,如Gumbel-Softmax。我们使用SLURP(一个具有挑战性的SLU数据集)评估我们的模型,并在意图分类和插槽填充任务上获得最先进的分数。我们还验证了NLU网络,预先训练与掩蔽语言模型,可以利用CTI的嘈杂的文本表示。此外,我们表明,即使在与CTI集成后,我们的模型也可以通过从异构数据中进行多任务学习来训练。

英文摘要:

Most End-to-End (E2E) SLU networks leverage the pre-trained ASR networks but still lack the capability to understand the semantics of utterances, crucial for the SLU task. To solve this, recently proposed studies use pre-trained NLU networks. However, it is not trivial to fully utilize both pre-trained networks; many solutions were proposed, such as Knowledge Distillation, cross-modal shared embedding, and network integration with Interface. We propose a simple and robust integration method for the E2E SLU network with novel Interface, Continuous Token Interface (CTI), the junctional representation of the ASR and NLU networks when both networks are pre-trained with the same vocabulary. Because the only difference is the noise level, we directly feed the ASR network's output to the NLU network. Thus, we can train our SLU network in an E2E manner without additional modules, such as Gumbel-Softmax. We evaluate our model using SLURP, a challenging SLU dataset and achieve state-of-the-art scores on both intent classification and slot filling tasks. We also verify the NLU network, pre-trained with Masked Language Model, can utilize a noisy textual representation of CTI. Moreover, we show our model can be trained with multi-task learning from heterogeneous data even after integration with CTI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑