What is left to be understood in ATIS?

By Gökhan Tür, Dilek Z. Hakkani-Tür, Larry Heck. 2010

249 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

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. Li Deng
3. Dong Yu
4. Mohit Bansal
5. Richard Socher
6. Bing Liu
7. Yoshua Bengio
8. Caiming Xiong

In Natural Language Processing

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

Citations in the corpus

• MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text (2013, background): “Yet these techniques are necessarily evaluated individually, rather than by how much they advance us towards the end goal.”
• Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling (2016, methodology): “In this work, we follow the ATIS corpus(1) setup used in [6, 7, 9, 19].”
• Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding (2015, unknown): “Note that authors in [13], [15], [27], [29], [38] used a different preprocessing technique, and hence their results are not directly comparable.”
• Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining (2020, methodology): “Now, a decade later, we should ask ourselves again, how much has the field progressed, and what is left to be done? Self-supervised language models (LMs), such as BERT [6], and end-to-end SLU [7, 8, 9] appear to have addressed the problems posed in [3].”
• A Joint Model of Intent Determination and Slot Filling for Spoken Language Understanding (2016, methodology): “In this paper, we use the ATIS corpus used in [Tur et al., 2010].”
• Spoken language understanding using long short-term memory neural networks (2014, methodology): “We evaluated the standard LSTM and our extensions on the ATIS database [16] [23] [40].”
• Joint Slot Filling and Intent Detection via Capsule Neural Networks (2018, methodology): “Datasets For each task, we evaluate our proposed models by applying it on two real-word datasets: SNIPS Natural Language Understanding benchmark1 (SNIPS-NLU) and the Airline Travel Information Systems (ATIS) dataset (Tur et al., 2010).”
• Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing (2020, background): “or this dataset and reported that despite really low error rates, there exist many unseen categories and sequences in the dataset that can benefit from incorporating linguistically motivated features [31]. This supports the continued utility of ATIS as a research corpus. 3.4 Internal Datasets Our in”
• Recurrent Neural Networks with External Memory for Spoken Language Understanding (2015, methodology): “In order to compare the proposed model with alternative modeling techniques, we conducted experiments on a well studied language understanding dataset, Air Travel Information System (ATIS) [22–24].”
• Recent advances in deep learning based dialogue systems: a systematic survey (2021, unknown): “Natural Language Understanding; Dialogue State Tracking Tur et al. (2010)”
• Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling (2016, methodology): “We used the ATIS corpus, which has been widely used as the benchmark for NLU (Price, 1990; Dahl et al., 1994; Wang et al., 2006; Tur et al., 2010). shows an example sentence and its semantic slot labels in In-Out-Begin (IOB) representation.”
• BERT for Joint Intent Classification and Slot Filling (2019, methodology): “The ATIS dataset (Tür et al., 2010) is widely used in NLU research, which includes audio recordings of people making flight reservations.”
• A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling (2018, methodology): “Our Bi-model structure with a decoder achieves state-of-the-art result on the benchmark ATIS data (Hemphill et al., 1990; Tur et al., 2010), with about 0.”
• Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding (2013, result): “pl script [22] and compare it to a CRF baseline.”
• Joint semantic utterance classification and slot filling with recursive neural networks (2014, methodology): “We evaluated the RecNN models on the ATIS database [21, 22].”
• Multilingual and Cross-Lingual Intent Detection from Spoken Data (2021, background): “A crucial functionality of Natural Language Understanding (NLU) components in task-oriented dialogue systems is intent detection (ID) (Young et al., 2002; Tür et al., 2010; Coucke et al., 2018).”
• Deep Unknown Intent Detection with Margin Loss (2019, methodology): “We have conducted experiments on two publicly available benchmark dialogue datasets, including SNIPS and ATIS (T¨ur et al., 2010).”
• Random features for Kernel Deep Convex Network (2013, methodology): “We conduct slot-filling experiments on the ATIS dataset following similar settings as described in [16].”