Filters








1,649 Hits in 2.9 sec

Automatic Intent-Slot Induction for Dialogue Systems [article]

Zengfeng Zeng, Dan Ma, Haiqin Yang, Zhen Gou, Jianping Shen
2021 arXiv   pre-print
domains and unseen intent-slot discovery for generalizable dialogue systems.  ...  Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems.  ...  ACKNOWLEDGMENTS The authors are grateful to the anonymous reviewers for their insightful feedback, to Xuan Li for helpful discussions during the course of this research.  ... 
arXiv:2103.08886v1 fatcat:2athxpih2rd4ldghrc3ezc3npa

Hierarchical Multi-task Learning for Organization Evaluation of Argumentative Student Essays

Wei Song, Ziyao Song, Lizhen Liu, Ruiji Fu
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In contrast, we propose a neural hierarchical multi-task learning approach for jointly optimizing sentence and paragraph level discourse element identification and organization evaluation.  ...  Acknowledgments We thank the anonymous reviewers for their detailed and constructive comments. The first three authors contributed equally. Yue Zhang is the corresponding author.  ...  We would like to acknowledge funding support from National Natural Science Foundation of China under Grant No.61976180 and the Westlake University and Bright Dream Joint Institute for Intelligent Robotics  ... 
doi:10.24963/ijcai.2020/532 dblp:conf/ijcai/MinQTL020 fatcat:zxowwg7uybbq7b5ip3lt2o7u4m

Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems

Yun-Nung Chen
2015 Proceedings of the ACL-IJCNLP 2015 Student Research Workshop  
Given unlabeled dialogues, we investigate an unsupervised approach for automatic induction of semantic slots, basic semantic units used in SDSs.  ...  Rudnicky, "Unsupervised Induction and Filling of Semantic Slots for Spoken Dialogue Systems Using Frame-Semantic Parsing," in Proceedings of 2013 IEEE Workshop on Automatic Speech Recognition and Understanding  ... 
doi:10.3115/v1/p15-3001 dblp:conf/acl/Chen15 fatcat:kfxqwlfgpfgl7maz25j42nebme

DR 4.4: Natural Multimodal Interaction Final Pro- totype

Bernd Kiefer, Ivana Kruijff-Korbayova, Anna Welker, Rifca Peters, Sarah McLeod
2019 Zenodo  
The dialogue policies and the linguistic resources have been adapted accordingly.  ...  Most eorts in year 4 are targeted towards the nal integrated system for the experiments over an extended time range.  ...  Acknowledgements The research described in this paper has been funded by the Horizon 2020 Framework Programme of the European Union within the project PAL (Personal Assistant for healthy Lifestyle) under  ... 
doi:10.5281/zenodo.3443669 fatcat:ez7jk76vmncshlzoivgqftx4ji

Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems [article]

Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo M. Ponti, Anna Korhonen, Ivan Vulić
2021 arXiv   pre-print
coverage and dialogue capabilities of current ToD systems.  ...  In fact, acquiring annotations or human feedback for each component of modular systems or for data-hungry end-to-end systems is expensive and tedious.  ...  In this work, we focus our attention on dialogue systems that operate on text input and generate text output -such systems are then extendable to true conversational systems by prepending an automatic  ... 
arXiv:2104.08570v2 fatcat:bi5xizz4wzct5fpiuk3ikotjta

Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding [article]

Anjishnu Kumar, Arpit Gupta, Julian Chan, Sam Tucker, Bjorn Hoffmeister, Markus Dreyer, Stanislav Peshterliev, Ankur Gandhe, Denis Filiminov, Ariya Rastrow, Christian Monson, Agnika Kumar
2018 arXiv   pre-print
It imposes inductive biases that allow it to learn robust SLU models from extremely small and sparse datasets and, in doing so, removes significant barriers to entry for software developers and dialogue  ...  systems researchers.  ...  Dialogue Subroutines ASK supports the specification of dialogue subroutines for common tasks, a unified dialogue model automates simple procedural dialogue capabilities, such as slot elicitation (e.g.,  ... 
arXiv:1711.00549v4 fatcat:utvdudvbmrgivipefqtragdiiu

A Survey on Spoken Language Understanding: Recent Advances and New Frontiers [article]

Libo Qin, Tianbao Xie, Wanxiang Che, Ting Liu
2021 arXiv   pre-print
Spoken Language Understanding (SLU) aims to extract the semantics frame of user queries, which is a core component in a task-oriented dialog system.  ...  Specifically, we give a thorough review of this research field, covering different aspects including (1) new taxonomy: we provide a new perspective for SLU filed, including single model vs. joint model  ...  How time matters: Learning time-decay at- classification for task-oriented dialogue systems: A sur- tention for contextual spoken language understanding in vey.  ... 
arXiv:2103.03095v2 fatcat:krhrfeomafd6nds2m4o5djbzby

Conversational Semantic Parsing [article]

Armen Aghajanyan, Jean Maillard, Akshat Shrivastava, Keith Diedrick, Mike Haeger, Haoran Li, Yashar Mehdad, Ves Stoyanov, Anuj Kumar, Mike Lewis, Sonal Gupta
2020 arXiv   pre-print
Notably, we improve the best known results on DSTC2 by up to 5 points for slot-carryover.  ...  The structured representation for semantic parsing in task-oriented assistant systems is geared towards simple understanding of one-turn queries.  ...  Traditional dialog systems operate through a flat representation, usually composed of a single intent and a list of slots with non-overlapping content from the utterance (Bapna et al., 2017; .  ... 
arXiv:2009.13655v1 fatcat:my3ko4nji5aijn5mayilnsn7vm

Evolvable dialogue state tracking for statistical dialogue management

Kai Yu, Lu Chen, Kai Sun, Qizhe Xie, Su Zhu
2015 Frontiers of Computer Science  
Statistical dialogue management is the core of cognitive spoken dialogue systems (SDS) and has attracted great research interest.  ...  In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed.  ...  . • System act type an indication feature for each dialogue act type whether it exists in the last system act. • Acttype-slot a feature giving the indication of whether each (acttype, slot) pair exists  ... 
doi:10.1007/s11704-015-5209-4 fatcat:xu3ktur3xbdelhpryvvsysdugi

On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise [article]

Sailik Sengupta, Jason Krone, Saab Mansour
2021 arXiv   pre-print
Intent Classification (IC) and Slot Labeling (SL) models, which form the basis of dialogue systems, often encounter noisy data in real-word environments.  ...  IC accuracy and +15 points for SL F1 on average.  ...  Acknowledgements We would like to thank the anonymous reviewers at multiple venues and the Amazon Lex team for their insightful feedbacks and constructive suggestions.  ... 
arXiv:2104.07149v2 fatcat:fj3tvh6b6bgx3bbq5bq4rckzam

Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System

Zhuoran Wang, Hongliang Chen, Guanchun Wang, Hao Tian, Hua Wu, Haifeng Wang
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
This paper proposes a Markov Decision Process and reinforcement learning based approach for domain selection in a multidomain Spoken Dialogue System built on a distributed architecture.  ...  In addition, it is shown that by using a model parameter tying trick, the extensibility of the system can be preserved, where dialogue components in new domains can be easily plugged in, without re-training  ...  The authors would also like to thank Qiaoqiao She, Duo Cai and the HCI-APP group at Baidu for volunteering to participate in the human subject experiments.  ... 
doi:10.3115/v1/d14-1007 dblp:conf/emnlp/WangCWTWW14 fatcat:4s2ysnzx4rei5ioftyfgeb2gyu

Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey [article]

Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Erik Cambria
2022 arXiv   pre-print
Furthermore, we comprehensively review the evaluation methods and datasets for dialogue systems to pave the way for future research.  ...  We speculate that this work is a good starting point for academics who are new to the dialogue systems or those who want to quickly grasp up-to-date techniques in this area.  ...  Huang et al. (2020a) proposed Graph-enhanced Representations for Automatic Dialogue Evaluation (GRADE), a novel evaluation metric for opendomain dialogue systems.  ... 
arXiv:2105.04387v5 fatcat:yd3gqg45rjgzxbiwfdlcvf3pye

Recent Advances and Challenges in Task-oriented Dialog System [article]

Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Xiaoyan Zhu
2020 arXiv   pre-print
We also discuss three critical topics for task-oriented dialog systems: (1) improving data efficiency to facilitate dialog modeling in low-resource settings, (2) modeling multi-turn dynamics for dialog  ...  In this paper, we survey recent advances and challenges in task-oriented dialog systems.  ...  A bunch of well-defined automatic metrics have been designed for different components in the system. For language understanding, slot F1 and intent accuracy are used.  ... 
arXiv:2003.07490v3 fatcat:powcuixxargkbp57kpwmjict3y

Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding

Yun-Nung Chen, William Yang Wang, Anatole Gershman, Alexander Rudnicky
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
Spoken dialogue systems (SDS) typically require a predefined semantic ontology to train a spoken language understanding (SLU) module.  ...  In addition to the annotation cost, a key challenge for designing such an ontology is to define a coherent slot set while considering their complex relations.  ...  Acknowledgments We thank anonymous reviewers for their useful comments and Prof. Manfred Stede for his mentoring. We are also grateful to MetLife's support.  ... 
doi:10.3115/v1/p15-1047 dblp:conf/acl/ChenWGR15 fatcat:nlb4lvynjvf5hegldu4togauce

Extending the Classifier Algorithms in Machine Learning to Improve the Performance in Spoken Language Understanding Systems Under Deficient Training Data

Sheetal Jagdale, Milind Shah
2020 Advances in Science, Technology and Engineering Systems  
One of the open domain challenges for Spoken Dialogue System (SDS) is to maintain a natural conversation for rarely visited domain i.e. domain with fewer data.  ...  The SLU reported in literature incorporate classifiers for the task of identifying the domain of user utterance, understanding the intent of the user, and filling slots-value pair.  ...  Block diagram of SLU SLU is an important component of the SDS system which converts user utterance to a semantic form consisting of dialogue act and slot value pair.  ... 
doi:10.25046/aj050655 fatcat:hliqg6v4xbeodi3lzj4h6onjji
« Previous Showing results 1 — 15 out of 1,649 results