paper-with-me

Papers

CTRAN: CNN-Transformer-based Network for Natural Language Understanding

2023-03-19 · Mehrdad Rafiepour, Javad Salimi Sartakhti

Intent-detection and slot-filling are the two main tasks in natural language understanding. In this study, we propose CTRAN, a novel encoder-decoder CNN-Transformer-based architecture for intent-detection and slot-filling. In the encoder, we use BERT, followed by several convolutional layers, and rearrange the output using window feature sequence. We use stacked Transformer encoders after the window feature sequence. For the intent-detection decoder, we utilize self-attention followed by a linear layer. In the slot-filling decoder, we introduce the aligned Transformer decoder, which utilizes a zero diagonal mask, aligning output tags with input tokens. We apply our network on ATIS and SNIPS, and surpass the current state-of-the-art in slot-filling on both datasets. Furthermore, we incorporate the language model as word embeddings, and show that this strategy yields a better result when compared to the language model as an encoder.

📄 PDF Abstract BibTeX arXiv:2303.10606

Code (1)

rafiepour/CTran 공식 구현 pytorch

Tasks

DecoderIntent DetectionLanguage ModelingLanguage ModellingNatural Language Understandingslot-fillingSlot FillingWord Embeddings

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
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…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Position-Wise Feed-Forward Layer 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Ranking Creative Language Characteristics in Small Data Scenarios

2020-10-23 · Julia Siekiera, Marius Köppel, Edwin Simpson, Kevin Stowe 외

The ability to rank creative natural language provides an important general tool for downstream language understanding and generation. However, current deep ranking models require substantial amounts of labeled data that…

Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning

2022-03-17 · CVPR 2022 1 · Yangji He, Weihan Liang, Dongyang Zhao, Hong-Yu Zhou 외

This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a prom…

AttributeFew-Shot Image ClassificationFew-Shot LearningSelf-Supervised Learning

Multi-Compound Transformer for Accurate Biomedical Image Segmentation

2021-06-28 · Yuanfeng Ji, Ruimao Zhang, Huijie Wang, Zhen Li 외

The recent vision transformer(i.e.for image classification) learns non-local attentive interaction of different patch tokens. However, prior arts miss learning the cross-scale dependencies of different pixels, the semant…

image-classificationImage ClassificationImage SegmentationSemantic correspondence+1

UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer

2021-09-09 · Haonan Wang, Peng Cao, Jiaqi Wang, Osmar R. Zaiane

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) N…

DecoderImage SegmentationMedical Image SegmentationSegmentation+2

The Volctrans Machine Translation System for WMT20

2020-10-28 · WMT (EMNLP) 2020 11 · Liwei Wu, Xiao Pan, Zehui Lin, Yaoming Zhu 외

This paper describes our VolcTrans system on WMT20 shared news translation task. We participated in 8 translation directions. Our basic systems are based on Transformer, with several variants (wider or deeper Transformer…

Machine TranslationSynthetic Data GenerationTranslation