DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection
Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel lightweight fully convolutional architecture, called DialogConv, for response selection. DialogConv is exclusively built on top of convolution to extract matching features of context and response. Dialogues are modeled in 3D views, where DialogConv performs convolution operations on embedding view, word view and utterance view to capture richer semantic information from multiple contextual views. On the four benchmark datasets, compared with state-of-the-art baselines, DialogConv is on average about 8.5x smaller in size, and 79.39x and 10.64x faster on CPU and GPU devices, respectively. At the same time, DialogConv achieves the competitive effectiveness of response selection.
Code (0)
등록된 구현이 없습니다.
Tasks
CPUGPURetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection
Current end-to-end retrieval-based dialogue systems are primarily based on Recurrent Neural Networks or Transformers with attention mechanisms. Despite promising results have been achieved, these models usually suffer fr…
RetrievalA Lightweight Attention-based Deep Network via Multi-Scale Feature Fusion for Multi-View Facial Expression Recognition
Convolutional neural networks (CNNs) and their variations have shown effectiveness in facial expression recognition (FER). However, they face challenges when dealing with high computational complexity and multi-view head…
Facial Expression RecognitionFacial Expression Recognition (FER)feature selectionLM-MCVT: A Lightweight Multi-modal Multi-view Convolutional-Vision Transformer Approach for 3D Object Recognition
In human-centered environments such as restaurants, homes, and warehouses, robots often face challenges in accurately recognizing 3D objects. These challenges stem from the complexity and variability of these environment…
3D Object RecognitionObjectObject RecognitionFully $1\times1$ Convolutional Network for Lightweight Image Super-Resolution
Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel ($3\times3$ or more). However, the heavy computational footprint of such models pr…
Computational EfficiencyImage Super-ResolutionSuper-ResolutionLearning light field synthesis with Multi-Plane Images: scene encoding as a recurrent segmentation task
In this paper we address the problem of view synthesis from large baseline light fields, by turning a sparse set of input views into a Multi-plane Image (MPI). Because available datasets are scarce, we propose a lightwei…