Slot-Gated Modeling for Joint Slot Filling and Intent Prediction

Goo, Chih Wen; Guang, Gao; Hsu, Yun Kai; Huo, Chih Li; Chen, Tsung Chieh; Hsu, Keng Wei; Chen, Yun Nung

doi:10.18653/v1/n18-2118

Cited by 408 publications

(209 citation statements)

References 8 publications

Supporting

Mentioning

173

Contrasting

Unclassified

Order By: Relevance

“…All our models were trained on a machine with 8 NVIDIA Tesla V100 GPUs, each with 16GB of memory. When using pretrained encoders, we leveraged gradual unfreezing to effectively tune the language Method Accuracy exact match intent Joint BiRNN [7] 80.70 92.60 Attention BiRNN [16] 78.90 91.10 Slot Gated Full Attention [5] 82.20 93.60 CapsuleNLU [36] 83 While training, the cross entropy loss function was modified with label smoothing with ϵ = 0.1. We used the Adam [12] optimizer with noam learning rate schedule [33], each adjusted differently for different datasets.…”

Section: Methodsmentioning

confidence: 99%

“…Source: play the song don't stop believin by journey Target: PlaySongIntent SongName( @pt r 3 @pt r 4 @pt r 5 )SongName ArtistName( @pt r 7 )ArtistName…”

Section: Query Formulationmentioning

confidence: 99%

“…Joint BiRNN [7] 73.20 96.90 Attention BiRNN [16] 74.10 96.70 Slot Gated Full Attention [5] 75.50 97.00 CapsuleNLU [36] 80 this baseline by replacing its embedding and encoder layers with a language model pretrained on a subset of Alexa's live traffic. These components were fine-tuned on the two datasets described in Section 3.4.…”

Section: Accuracy Exact Match Intentmentioning

confidence: 99%

See 2 more Smart Citations

Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

Rongali

Soldaini

Monti

et al. 2020

Proceedings of the Web Conference 2020

127

View full text Add to dashboard Cite

Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical slot-filling systems have been used to parse "simple" queries; that is, queries that contain a single action and can be decomposed into a set of non-overlapping entities. More recently, shift-reduce parsers have been proposed to process more complex utterances. These methods, while powerful, impose specific limitations on the type of queries that can be parsed; namely, they require a query to be representable as a parse tree.In this work, we propose a unified architecture based on Sequence to Sequence models and Pointer Generator Network to handle both simple and complex queries. Unlike other works, our approach does not impose any restriction on the semantic parse schema. Furthermore, experiments show that it achieves state of the art performance on three publicly available datasets (ATIS, SNIPS, Facebook TOP), relatively improving between 3.3% and 7.7% in exact match accuracy over previous systems. Finally, we show the effectiveness of our approach on two internal datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Source: play the song don't stop believin by journey Target: PlaySongIntent SongName( @pt r 3 @pt r 4 @pt r 5 )SongName ArtistName( @pt r 7 )ArtistName…”

Section: Query Formulationmentioning

confidence: 99%

Section: Accuracy Exact Match Intentmentioning

confidence: 99%

See 1 more Smart Citation

Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

Rongali

Soldaini

Monti

et al. 2020

Proceedings of the Web Conference 2020

127

View full text Add to dashboard Cite

show abstract

“…End-to-end SLU architecture Train: (Utterances, Speakers) (115660, 77) Validation: (Utterances, Speakers) (3118, 10) Test: (Utterances, Speakers) (3793, 10) Unique Intents 31 Unique: (Actions, Objects, Locations)(6,14,4) …”

mentioning

confidence: 99%

End-to-End Architectures for ASR-Free Spoken Language Understanding

Palogiannidi¹,

Gkinis²,

Mastrapas³

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Spoken Language Understanding (SLU) is the problem of extracting the meaning from speech utterances. It is typically addressed as a two-step problem, where an Automatic Speech Recognition (ASR) model is employed to convert speech into text, followed by a Natural Language Understanding (NLU) model to extract meaning from the decoded text. Recently, end-to-end approaches were emerged, aiming at unifying the ASR and NLU into a single SLU deep neural architecture, trained using combinations of ASR and NLU-level recognition units. In this paper, we explore a set of recurrent architectures for intent classification, tailored to the recently introduced Fluent Speech Commands (FSC) dataset, where intents are formed as combinations of three slots (action, object, and location). We show that by combining deep recurrent architectures with standard data augmentation, state-of-the-art results can be attained, without using ASR-level targets or pretrained ASR models. We also investigate its generalizability to new wordings, and we show that the model can perform reasonably well on wordings unseen during training 1 .

show abstract

“…Recently, joint intent classification and slot labeling SLU models based on recurrent neural networks has been shown to achieve state-of-the-art performance on benchmark datasets [Hakkani-Tür et al, 2016;Liu and Lane, 2016;Kim et al, 2017a;Goo et al, 2018;Wang et al, 2018]. However, these models often suffer from poor slot labeling accuracy when an utterance contain slots with large semantic variability, dissimilar to those encountered during training e.g.…”

Section: Introductionmentioning

confidence: 99%

Iterative Delexicalization for Improved Spoken Language Understanding

2019

View full text Add to dashboard Cite

Recurrent neural network (RNN) based joint intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems. However, these models suffer from poor performance for slots which often encounter large semantic variability in slot values after deployment (e.g. message texts, partial movie/artist names). While greedy delexicalization of slots in the input utterance via substring matching can partly improve performance, it often produces incorrect input. Moreover, such techniques cannot delexicalize slots with out-of-vocabulary slot values not seen at training. In this paper, we propose a novel iterative delexicalization algorithm, which can accurately delexicalize the input, even with out-of-vocabulary slot values. Based on model confidence of the current delexicalized input, our algorithm improves delexicalization in every iteration to converge to the best input having the highest confidence. We show on benchmark and in-house datasets that our algorithm can greatly improve parsing performance for RNN based models, especially for out-of-distribution slot values.

show abstract

Slot-Gated Modeling for Joint Slot Filling and Intent Prediction

Cited by 408 publications

References 8 publications

Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

End-to-End Architectures for ASR-Free Spoken Language Understanding

Iterative Delexicalization for Improved Spoken Language Understanding

Contact Info

Product

Resources

About