paper-with-me

Papers

Transfer Learning for Context-Aware Spoken Language Understanding

2020-03-03 · Qian Chen, Zhu Zhuo, Wen Wang, Qiuyun Xu

Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly improves SLU performance for multi-turn dialogues. However, collecting a large-scale human-labeled multi-turn dialogue corpus for the target domains is complex and costly. To reduce dependency on the collection and annotation effort, we propose a Context Encoding Language Transformer (CELT) model facilitating exploiting various context information for SLU. We explore different transfer learning approaches to reduce dependency on data collection and annotation. In addition to unsupervised pre-training using large-scale general purpose unlabeled corpora, such as Wikipedia, we explore unsupervised and supervised adaptive training approaches for transfer learning to benefit from other in-domain and out-of-domain dialogue corpora. Experimental results demonstrate that the proposed model with the proposed transfer learning approaches achieves significant improvement on the SLU performance over state-of-the-art models on two large-scale single-turn dialogue benchmarks and one large-scale multi-turn dialogue benchmark.

📄 PDF Abstract BibTeX arXiv:2003.01305

Code (0)

등록된 구현이 없습니다.

Tasks

Spoken Language UnderstandingTask-Oriented Dialogue SystemsTransfer LearningUnsupervised Pre-training

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding

2019-03-20 · NAACL 2019 6 · Jonggu Kim, Jong-Hyeok Lee

To capture salient contextual information for spoken language understanding (SLU) of a dialogue, we propose time-aware models that automatically learn the latent time-decay function of the history without a manual time-d…

dialog state trackingSpoken Language Understanding

Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding

2019-09-24 · Chao-Wei Huang, Yun-Nung Chen

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by…

Spoken Language Understanding

Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterization

2020-04-30 · Libo Qin, Minheng Ni, Yue Zhang, Wanxiang Che 외

Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. However, annotating data for each domain is both financially costly and non-sc…

Spoken Language Understanding

Structured Learning for Context-aware Spoken Language Understanding of Robotic Commands

2017-08-01 · WS 2017 8 · Andrea Vanzo, Danilo Croce, Roberto Basili, Daniele Nardi

Service robots are expected to operate in specific environments, where the presence of humans plays a key role. A major feature of such robotics platforms is thus the ability to react to spoken commands. This requires th…

Spoken Language Understanding

Unsupervised Transfer Learning for Spoken Language Understanding in Intelligent Agents

2018-11-13 · Aditya Siddhant, Anuj Goyal, Angeliki Metallinou

User interaction with voice-powered agents generates large amounts of unlabeled utterances. In this paper, we explore techniques to efficiently transfer the knowledge from these unlabeled utterances to improve model perf…

Language ModelingLanguage ModellingSpoken Language UnderstandingTransfer Learning+1