A Deep Reinforcement Learning Based Multimodal Coaching Model (DCM) for Slot Filling in Spoken Language Understanding(SLU)

Wang, Yu; Patel, Abhishek; Shen, Yilin; Jin, Hongxia

doi:10.21437/interspeech.2018-1379

Cited by 10 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AC-NCR model is trained based on deep reinforcement learning (DRL) technique. Deep reinforcement learning has been widely used in a variety of NLP and machine learning tasks [5,6,7,8]. The input to the model is a state s t , and its output is an action a t .…”

Section: Ac-ncr Model Designmentioning

confidence: 99%

An End-To-End Actor-Critic-Based Neural Coreference Resolution System

Wang

Shen

Jin

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

The target of a coreference resolution system is to cluster all mentions that refer to the same entity in a given context. All coreference resolution systems need to solve two subtasks; one task is to detect all of the potential mentions, and the other is to learn the linking of an antecedent for each possible mention. In this paper, we propose an actor-critic-based neural coreference resolution system, which can achieve both mention detection and mention clustering by leveraging an actorcritic deep reinforcement learning technique and a joint training algorithm. We experiment on the BERT model to generate different input span representations. Our model with the BERT span representation achieves the state-of-the-art performance among the models on the CoNLL-2012 Shared Task English Test Set.

show abstract

Section: Ac-ncr Model Designmentioning

confidence: 99%

An End-To-End Actor-Critic-Based Neural Coreference Resolution System

Wang

Shen

Jin

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This encoding was then used as an input for Slot Labeling, thereby capturing the global information from the input. Reference [17] proposed the use of a Deep Reinforcement Learning (DRL) based multimodal Coaching Model (DCM), where authors used a new reward mechanism for the RL based Slot Tagging. Even without any feedback from the user, this model was capable of understanding whatever has been wrongly labelled.…”

Section: B Slot Labellingmentioning

confidence: 99%

Parallel Intent and Slot Prediction using MLB Fusion

Bhasin

Natarajan

Mathur

et al. 2020

2020 IEEE 14th International Conference on Semantic Computing (ICSC)

View full text Add to dashboard Cite

Intent and Slot Identification are two important tasks in Spoken Language Understanding (SLU). For a natural language utterance, there is a high correlation between these two tasks. A lot of work has been done on each of these using Recurrent-Neural-Networks (RNN), Convolution Neural Networks (CNN) and Attention based models. Most of the past work used two separate models for intent and slot prediction. Some of them also used sequence-to-sequence type models where slots are predicted after evaluating the utterance-level intent. In this work, we propose a parallel Intent and Slot Prediction technique where separate Bidirectional Gated Recurrent Units (GRU) are used for each task. We posit the usage of MLB (Multimodal Low-rank Bilinear Attention Network) fusion for improvement in performance of intent and slot learning. To the best of our knowledge, this is the first attempt of using such a technique on text based problems. Also, our proposed methods outperform the existing state-of-the-art results for both intent and slot prediction on two benchmark datasets

show abstract

“…In previous years, several studies were carried out to improve and evaluate the performance of NLU tasks. Former works evaluated the impact of using different techniques to improve slot filling [ 4 , 5 , 6 ] and intent detection [ 7 , 8 ]. Interestingly, research in joint NLU (jointly learning both intent detection and slot filling) achieved better results in both tasks [ 9 , 10 ].…”

Section: Introductionmentioning

confidence: 99%

A Study on the Impacts of Slot Types and Training Data on Joint Natural Language Understanding in a Spanish Medication Management Assistant Scenario

Roca

Rosset

García

et al. 2022

Sensors

View full text Add to dashboard Cite

This study evaluates the impacts of slot tagging and training data length on joint natural language understanding (NLU) models for medication management scenarios using chatbots in Spanish. In this study, we define the intents (purposes of the sentences) for medication management scenarios and two types of slot tags. For training the model, we generated four datasets, combining long/short sentences with long/short slots, while for testing, we collect the data from real interactions of users with a chatbot. For the comparative analysis, we chose six joint NLU models (SlotRefine, stack-propagation framework, SF-ID network, capsule-NLU, slot-gated modeling, and a joint SLU-LM model) from the literature. The results show that the best performance (with a sentence-level semantic accuracy of 68.6%, an F1-score of 76.4% for slot filling, and an accuracy of 79.3% for intent detection) is achieved using short sentences and short slots. Our results suggest that joint NLU models trained with short slots yield better results than those trained with long slots for the slot filling task. The results also indicate that short slots could be a better choice for the dialog system because of their simplicity. Importantly, the work demonstrates that the performance of the joint NLU models can be improved by selecting the correct slot configuration according to the usage scenario.

show abstract

A Deep Reinforcement Learning Based Multimodal Coaching Model (DCM) for Slot Filling in Spoken Language Understanding(SLU)

Cited by 10 publications

References 26 publications

An End-To-End Actor-Critic-Based Neural Coreference Resolution System

An End-To-End Actor-Critic-Based Neural Coreference Resolution System

Parallel Intent and Slot Prediction using MLB Fusion

A Study on the Impacts of Slot Types and Training Data on Joint Natural Language Understanding in a Spanish Medication Management Assistant Scenario

Contact Info

Product

Resources

About