CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding

@article{Liu2019CMNetAN,
  title={CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding},
  author={Yijin Liu and Fandong Meng and Jinchao Zhang and Jie Zhou and Yufeng Chen and Jinan Xu},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.06937}
}
Spoken Language Understanding (SLU) mainly involves two tasks, intent detection and slot filling, which are generally modeled jointly in existing works. [...] Key Method The CM-block firstly captures slot-specific and intent-specific features from memories in a collaborative manner, and then uses these enriched features to enhance local context representations, based on which the sequential information flow leads to more specific (slot and intent) global utterance representations.Expand
Towards Fine-Grained Transfer: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
TLDR
An Adaptive Graph-Interactive Framework for joint multiple intent detection and slot filling is proposed, where an intent-slot graph interaction layer is applied to each token adaptively to model the strong correlation between the slot and intents. Expand
A Joint and Domain-Adaptive Approach to Spoken Language Understanding
TLDR
This paper formulate SLU as a constrained generation task and utilize a dynamic vocabulary based on domainspecific ontology and results show that the joint model can be effectively adapted to a new domain. Expand
HAN: Higher-order Attention Network for Spoken Language Understanding
  • Dongsheng Chen, Zhiqi Huang, Yuexian Zou
  • Computer Science
  • ArXiv
  • 2021
TLDR
This paper proposes to replace the conventional attention with the proposed Bilinear attention block and shows that the introduced Higherorder Attention Network (HAN) brings improvement for the SLU task. Expand
Knowing Where to Leverage: Context-Aware Graph Convolutional Network With an Adaptive Fusion Layer for Contextual Spoken Language Understanding
TLDR
A context-aware graph convolutional network (GCN) with an adaptive fusion layer for contextual SLU is proposed to automatically aggregate the contextual information, which frees the model from the manually designed heuristic aggregation function. Expand
A Survey on Spoken Language Understanding: Recent Advances and New Frontiers
TLDR
A thorough review of this research field, covering different aspects including new taxonomy, which provides a new perspective for SLU filed, and some emerging areas in complex SLU as well as the corresponding challenges. Expand
SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling
TLDR
A multi-intent NLU framework, called SLIM, to jointly learn multiintent detection and slot filling based on BERT, which introduces an explicit slot-intent classifier to learn the many-to-one mapping between slots and intents. Expand
An Effective Non-Autoregressive Model for Spoken Language Understanding
  • Lizhi Cheng, Weijia Jia, Wenmian Yang
  • Computer Science
  • ArXiv
  • 2021
TLDR
A novel non-autoregressive SLU model named LayeredRefine Transformer is proposed, which contains a Slot Label Generation (SLG) task and a Layered Refine Mechanism (LRM), which can efficiently obtain dependency information during training and spend no extra time in inference. Expand
TD-GIN: Token-level Dynamic Graph-Interactive Network for Joint Multiple Intent Detection and Slot Filling
TLDR
This paper proposes a Token-level Dynamic Graph-Interactive Network (TD-GIN) for joint multiple intent detection and slot filling, where it model the interaction between multiple intents and each token slot in a unified graph architecture. Expand
Depth-Adaptive Graph Recurrent Network for Text Classification
TLDR
This paper proposes a depth-adaptive mechanism for the S-LSTM, which allows the model to learn how many computational steps to conduct for different words as required, and integrates an extra RNN layer to inject sequential information. Expand
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
TLDR
A similarity-based few-shot learning scheme is proposed, named Contrastive Prototype Merging network (ConProm), that learns to bridge metric spaces of intent and slot on data-rich domains, and then adapt the bridged metric space to specific few- shot domain. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 45 REFERENCES
A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding
TLDR
A novel self-attentive model with gate mechanism to fully utilize the semantic correlation between slot and intent and outperforms other popular methods by a large margin in terms of both intent detection error rate and slot filling F1-score is proposed. Expand
End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding
TLDR
The experiments on Microsoft Cortana conversational data show that the proposed memory network architecture can effectively extract salient semantics for modeling knowledge carryover in the multi-turn conversations and outperform the results using the state-of-the-art recurrent neural network framework (RNN) designed for single-turn SLU. Expand
A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling
TLDR
New Bi-model based RNN semantic frame parsing network structures are designed to perform the intent detection and slot filling tasks jointly, by considering their cross-impact to each other using two correlated bidirectional LSTMs (BLSTM). Expand
A Joint Model of Intent Determination and Slot Filling for Spoken Language Understanding
TLDR
A joint model is proposed based on the idea that the intent and semantic slots of a sentence are correlative, and it outperforms the state-of-the-art approaches on both tasks. Expand
Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM
TLDR
Experimental results show the power of a holistic multi-domain, multi-task modeling approach to estimate complete semantic frames for all user utterances addressed to a conversational system over alternative methods based on single domain/task deep learning. Expand
Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding
TLDR
This paper implemented and compared several important RNN architectures, including Elman, Jordan, and hybrid variants, and implemented these networks with the publicly available Theano neural network toolkit and completed experiments on the well-known airline travel information system (ATIS) benchmark. Expand
Joint Slot Filling and Intent Detection via Capsule Neural Networks
TLDR
A capsule-based neural network model is proposed which accomplishes slot filling and intent detection via a dynamic routing-by-agreement schema and a re-routing schema is proposed to further synergize the slot filling performance using the inferred intent representation. Expand
Joint semantic utterance classification and slot filling with recursive neural networks
TLDR
Recursive neural networks can be used to perform the core spoken language understanding (SLU) tasks in a spoken dialog system, more specifically domain and intent determination, concurrently with slot filling, in one jointly trained model. Expand
Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling
TLDR
This paper enhances LSTM-based sequence labeling to explicitly model label dependencies and proposes another enhancement to incorporate the global information spanning over the whole input sequence to predict the label sequence. Expand
Simple, Fast, Accurate Intent Classification and Slot Labeling
TLDR
This work proposes a class of label-recurrent, dilated, convolutional IC+SL systems that are accurate, achieving a 30% error reduction in SL over the state-of-the-art performance on the Snips dataset, as well as fast, at 2x the inference and 2/3 to 1/2 the training time of comparable recurrent models. Expand
...
1
2
3
4
5
...