paper-with-me

홈 › Papers

A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding

2022-11-22 · Lizhi Cheng, Wenmian Yang, Weijia Jia

Multi-Intent Spoken Language Understanding (SLU), a novel and more complex scenario of SLU, is attracting increasing attention. Unlike traditional SLU, each intent in this scenario has its specific scope. Semantic information outside the scope even hinders the prediction, which tremendously increases the difficulty of intent detection. More seriously, guiding slot filling with these inaccurate intent labels suffers error propagation problems, resulting in unsatisfied overall performance. To solve these challenges, in this paper, we propose a novel Scope-Sensitive Result Attention Network (SSRAN) based on Transformer, which contains a Scope Recognizer (SR) and a Result Attention Network (RAN). Scope Recognizer assignments scope information to each token, reducing the distraction of out-of-scope tokens. Result Attention Network effectively utilizes the bidirectional interaction between results of slot filling and intent detection, mitigating the error propagation problem. Experiments on two public datasets indicate that our model significantly improves SLU performance (5.4\% and 2.1\% on Overall accuracy) over the state-of-the-art baseline.

📄 PDF Abstract BibTeX arXiv:2211.12220

Code (0)

등록된 구현이 없습니다.

Tasks

Intent DetectionSemantic Frame Parsingslot-fillingSlot FillingSpoken Language Understanding

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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…

Similar Papers 제목 키워드 기반

Sequential Recommender via Time-aware Attentive Memory Network

2020-05-18 · Wendi Ji, Keqiang Wang, Xiaoling Wang, TingWei Chen 외

Recommendation systems aim to assist users to discover most preferred contents from an ever-growing corpus of items. Although recommenders have been greatly improved by deep learning, they still faces several challenges:…

Recommendation SystemsRetrieval

Out-of-Scope Domain and Intent Classification through Hierarchical Joint Modeling

2021-04-30 · PengFei Liu, Kun Li, Helen Meng

User queries for a real-world dialog system may sometimes fall outside the scope of the system's capabilities, but appropriate system responses will enable smooth processing throughout the human-computer interaction. Thi…

ClassificationGeneral Classificationintent-classificationIntent Classification+1

MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations

2024-03-16 · Hanlei Zhang, Xin Wang, Hua Xu, Qianrui Zhou 외

Multimodal intent recognition poses significant challenges, requiring the incorporation of non-verbal modalities from real-world contexts to enhance the comprehension of human intentions. Existing benchmark datasets are …

Intent RecognitionMultimodal Intent Recognition

Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection

2021-06-08 · JianGuo Zhang, Kazuma Hashimoto, Yao Wan, Zhiwei Liu 외

Pre-trained Transformer-based models were reported to be robust in intent classification. In this work, we first point out the importance of in-domain out-of-scope detection in few-shot intent recognition tasks and then …

intent-classificationIntent ClassificationIntent DetectionIntent Recognition

SCAN: A Spatial Context Attentive Network for Joint Multi-Agent Intent Prediction

2021-01-29 · Jasmine Sekhon, Cody Fleming

Safe navigation of autonomous agents in human centric environments requires the ability to understand and predict motion of neighboring pedestrians. However, predicting pedestrian intent is a complex problem. Pedestrian …

Social NavigationTrajectory Prediction