Convolutional neural network based triangular CRF for joint intent detection and slot filling

By Puyang Xu, Ruhi Sarikaya. 2013

347 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jianfeng Gao
2. Bing Liu
3. Li Deng
4. Mohit Bansal
5. Richard Socher
6. Philip S. Yu
7. Caiming Xiong
8. Xiaodong He

In Information Systems

1. Li Deng
2. Tong Zhang
3. Rie Johnson
4. Jianfeng Gao
5. Philip S. Yu
6. Wen-tau Yih
7. Bing Liu
8. Dilek Z. Hakkani-Tür

Citations in the corpus

• Towards Open Intent Discovery for Conversational Text (2019, methodology): “Recent approaches have drawn upon progress in CNN, RNN, and CRF based language models to improve intent detection [11, 22, 24, 31, 36, 49, 52].”
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks (2014, methodology): “…on token-level applications (e.g., POS tagging) by Collobert et al. (2011), CNN has been used in systems for entity search, sentence modeling, word embedding learning, product feature mining, and so on (Xu and Sarikaya, 2013; Gao et al., 2014; Shen et al., 2014; Kalchbrenner et a r X i v : 1412 .”
• Bidirectional LSTM-CRF Models for Sequence Tagging (2015, background): “In speech language understanding community, recurrent neural network (Mesnil et al., 2013; Yao et al., 2014) and convolutional nets (Xu and Sarikaya, 2013) based models have been recently proposed.”
• Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling (2016, methodology): “We use the same 10-fold cross validation setup as in [9] and [20].”
• A Joint Model of Intent Determination and Slot Filling for Spoken Language Understanding (2016, methodology): “For ATIS, as in [Yao et al., 2013], to deal with unseen words in the test set, we marked all words with only one occurrence in the training data as hUNKi and used this label to represent those unseen words in the test set.”
• ONENET: Joint domain, intent, slot prediction for spoken language understanding (2017, methodology): “17 3 Independent domain Joint intent and slot [15] 91.”
• Joint Slot Filling and Intent Detection via Capsule Neural Networks (2018, methodology): “Intent Detection With recent developments in deep neural networks, user intent detection models (Hu et al., 2009; Xu and Sarikaya, 2013; Zhang et al., 2016; Liu and Lane, 2016; Zhang et al., 2017; Chen et al., 2016; Xia et al., 2018) are proposed to classify user intents given their diversely expres”
• Joint semantic utterance classification and slot filling with recursive neural networks (2014, methodology): “As for slot filling, RecNN (with Viterbi) most notably achieves better results than the popular CRF approach, and rivals the recurrent neural network (RNN) and the CNN+TriCRF2.”
• Data Augmentation by Data Noising for Open-vocabulary Slots in Spoken Language Understanding (2019, background): “Xu and Sarikaya (2013) and Vu (2016) proposed models for SLU using Convolutional Neural Networks and many other researchers used recurrent neural networks (RNNs).”
• Recurrent Neural Networks with External Memory for Spoken Language Understanding (2015, neutral): “11 CNN [27] 94.”
• Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling (2016, methodology): “11 CNN-CRF (Xu and Sarikaya, 2013) 94.”
• Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding (2015, methodology): “On text, CNN has been gaining attention, used in systems for tagging, entity search, sentence modeling, and so on [4, 5, 26, 7, 21, 12, 25, 22, 24, 13], to make use of the 1D structure (word order) of text data.”
• Reconstructing Capsule Networks for Zero-shot Intent Classification (2019, background): “Zero-shot intent classification is an important and challenging task for many natural language understanding applications (Hu et al., 2009; Liu and Lane, 2016; Nam et al., 2016; Xu and Sarikaya, 2013), in which new intents emerge constantly and they cannot be easily recognized.”
• A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling (2018, methodology): “The ATIS dataset used in this paper follows the same format as in (Liu and Lane, 2015; Mesnil et al., 2015; Xu and Sarikaya, 2013; Liu and Lane, 2016a).”
• BERT for Joint Intent Classification and Slot Filling (2019, methodology): “Joint modeling approaches include CNN-CRF (Xu and Sarikaya, 2013), RecNN (Guo et al., 2014), joint RNN-LSTM (Hakkani-T¨ur et al., 2016), attention-based BiRNN (Liu and Lane, 2016), and slot-gated attention-based model (Goo et al., 2018).”
• User Information Augmented Semantic Frame Parsing Using Progressive Neural Networks (2018, methodology): “Recent research focuses on the joint model to learn two tasks together [9, 10, 11, 2].”
• Zero-shot User Intent Detection via Capsule Neural Networks (2018, background): “With recent developments in deep neural networks, user intent detection models (Hu et al., 2009; Xu and Sarikaya, 2013; Zhang et al., 2016; Liu and Lane, 2016; Chen et al., 2016b) are proposed to classify user intents given their diversely”