Filters








406,669 Hits in 6.7 sec

DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue [article]

Shikib Mehri, Mihail Eric, Dilek Hakkani-Tur
2020 arXiv   pre-print
To progress research in this direction, we introduce DialoGLUE (Dialogue Language Understanding Evaluation), a public benchmark consisting of 7 task-oriented dialogue datasets covering 4 distinct natural  ...  A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains.  ...  In this work we propose DialoGLUE, a public benchmark consisting of 7 diverse task-oriented spoken-language datasets across 4 distinct natural language understanding tasks including intent prediction,  ... 
arXiv:2009.13570v2 fatcat:tzcnyusgajgn5osewdyuiabczm

LanguageRefer: Spatial-Language Model for 3D Visual Grounding [article]

Junha Roh, Karthik Desingh, Ali Farhadi, Dieter Fox
2021 arXiv   pre-print
For robots to understand human instructions and perform meaningful tasks in the near future, it is important to develop learned models that comprehend referential language to identify common objects in  ...  In this paper, we introduce a spatial-language model for a 3D visual grounding problem.  ...  Introduction For a robot to communicate seamlessly with humans to perform meaningful tasks in indoor environments, it should understand the natural language utterances and ground it to the elements in  ... 
arXiv:2107.03438v3 fatcat:s6phn7dcbbhsdna47uwn67twze

Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems [article]

Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, Pascale Fung
2019 arXiv   pre-print
Finally, with very few word pairs, our model achieves significant zero-shot adaptation performance improvements in both cross-lingual dialogue state tracking and natural language understanding (i.e., intent  ...  In order to circumvent the expensive and time-consuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented  ...  Natural Language Understanding Our NLU model is illustrated in Figure 2 as a multi-task problem.  ... 
arXiv:1911.09273v1 fatcat:bazx4femujbntnwgb4j6bjmfxm

Attention-Informed Mixed-Language Training for Zero-Shot Cross-Lingual Task-Oriented Dialogue Systems

Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, Pascale Fung
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Finally, with very few word pairs, our model achieves significant zero-shot adaptation performance improvements in both cross-lingual dialogue state tracking and natural language understanding (i.e., intent  ...  In order to circumvent the expensive and time-consuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented  ...  Natural Language Understanding Our NLU model is illustrated in Figure 2 as a multi-task problem.  ... 
doi:10.1609/aaai.v34i05.6362 fatcat:h322k7c6zfa5rnfy2g5vnxs2pe

Deep Learning for Dialogue Systems

Yun-Nung Chen, Asli Celikyilmaz, Dilek Hakkani-Tür
2017 Proceedings of ACL 2017, Tutorial Abstracts  
The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling.  ...  However, how to successfully apply deep learning based approaches to a dialogue system is still challenging.  ...  Natural Language Generation The RNNbased models have been applied to language generation for both chit-chat and task-orientated dialogue systems (Vinyals and Le, 2015; Wen et al., 2015b) .  ... 
doi:10.18653/v1/p17-5004 dblp:conf/acl/ChenCH17 fatcat:eyltpy5guna6bfsczav3vji7x4

Modelling Natural Language, Programs, and their Intersection

Graham Neubig, Miltiadis Allamanis
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts  
This also encompasses natural language code search, which retrieves relevant code snippets based on natural language queries. • Modelling the natural language elements of source code: As mentioned above  ...  Some examples of relevant tasks include: • Automatic explanation of programs in natural language (code-to-language): Highly connected with the task of grounded natural language generation in the NLP community  ...  In this tutorial, we will focus on machine learning models of source code and natural language tailored to tackle these tasks.  ... 
doi:10.18653/v1/n18-6001 dblp:conf/naacl/NeubigA18 fatcat:uufv3ygllnbhbltlti66752oqe

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System [article]

Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang
2022 arXiv   pre-print
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.  ...  In this study, we present PPTOD, a unified plug-and-play model for task-oriented dialogue.  ...  natural language understanding (NLU)).  ... 
arXiv:2109.14739v2 fatcat:dsy25xhxlbbk3f2qccoluwtpiy

Natural language understanding of map navigation queries in Roman Urdu by joint entity and intent determination

Javeria Hassan, Muhammad Ali Tahir, Adnan Ali
2021 PeerJ Computer Science  
Natural language understanding (NLU) is the first step for a task-oriented dialogue system.  ...  Navigation based task-oriented dialogue systems provide users with a natural way of communicating with maps and navigation software.  ...  It can be seen that NLU is a central step in the task oriented dialogue system; therefore, the accuracy of natural language understanding greatly affects the output of the whole dialogue system.  ... 
doi:10.7717/peerj-cs.615 fatcat:dd7ng2xxwnccrl4n365a42dxvq

Accelerating Natural Language Understanding in Task-Oriented Dialog [article]

Ojas Ahuja, Shrey Desai
2020 arXiv   pre-print
Task-oriented dialog models typically leverage complex neural architectures and large-scale, pre-trained Transformers to achieve state-of-the-art performance on popular natural language understanding benchmarks  ...  Moreover, we perform acceleration experiments on CPUs, where we observe our multi-task model predicts intents and slots nearly 63x faster than even DistilBERT.  ...  Tasks and Datasets We build convolutional models for intent detection and slot filling, two popular natural language understanding tasks in the task-oriented dialog stack.  ... 
arXiv:2006.03701v1 fatcat:is2dx34gtndhjdrylgy5n233gm

Task-Oriented Dialogue System as Natural Language Generation [article]

Weizhi Wang, Zhirui Zhang, Junliang Guo, Yinpei Dai, Boxing Chen, Weihua Luo
2021 arXiv   pre-print
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify  ...  Experimental results conducted on the DSTC8 Track 1 benchmark and MultiWOZ dataset demonstrate that our proposed approach significantly outperforms baseline models with a remarkable performance on automatic  ...  Finally, the natural language generation (NLG) module maps the system action to a natural language response.  ... 
arXiv:2108.13679v2 fatcat:65gmtkg565azzhvgkxdq2527vy

A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions [article]

Siddharth Karamcheti, Edward C. Williams, Dilip Arumugam, Mina Rhee, Nakul Gopalan, Lawson L. S. Wong, Stefanie Tellex
2017 arXiv   pre-print
Our robot-simulation results demonstrate that a system successfully interpreting both goal-oriented and action-oriented task specifications brings us closer to robust natural language understanding for  ...  We introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding Network (DRAGGN), for task grounding and execution that handles natural language from either category as input, and generalizes  ...  In Conference on Empirical Methods in Natural Language Processing. Yoav Artzi and Luke Zettlemoyer. 2013. Weakly supervized learning of semantic parsers for mapping instructions to actions.  ... 
arXiv:1707.08668v1 fatcat:ifbsnjm3pvdqzd7nedvs55qi2e

A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions

Siddharth Karamcheti, Edward Clem Williams, Dilip Arumugam, Mina Rhee, Nakul Gopalan, Lawson L.S. Wong, Stefanie Tellex
2017 Proceedings of the First Workshop on Language Grounding for Robotics  
Our robotsimulation results demonstrate that a system successfully interpreting both goaloriented and action-oriented task specifications brings us closer to robust natural language understanding for human-robot  ...  We introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding Network (DRAGGN), for task grounding and execution that handles natural language from either category as input, and generalizes  ...  In Conference on Empirical Methods in Natural Language Processing. Yoav Artzi and Luke Zettlemoyer. 2013. Weakly supervized learning of semantic parsers for mapping  ... 
doi:10.18653/v1/w17-2809 dblp:conf/acl/KaramchetiWARGW17 fatcat:aqv5k2cd6nazxbce6r5ig46wdq

ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language [article]

Phi Nguyen Van, Tung Cao Hoang, Dung Nguyen Manh, Quan Nguyen Minh, Long Tran Quoc
2022 arXiv   pre-print
ViWOZ is the first multi-turn, multi-domain tasked oriented dataset in Vietnamese, a low-resource language.  ...  Most of the current task-oriented dialogue systems (ToD), despite having interesting results, are designed for a handful of languages like Chinese and English.  ...  In the field of task-oriented dialogue systems, Natural Language Understanding (NLU) is the only module having diverse language datasets.  ... 
arXiv:2203.07742v1 fatcat:6t2j2hv5mndszolerxedxcp2mi

Hello, It's GPT-2 – How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems [article]

Paweł Budzianowski, Ivan Vulić
2019 arXiv   pre-print
We propose a task-oriented dialogue model that operates solely on text input: it effectively bypasses explicit policy and language generation modules.  ...  Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar  ...  Domain Transfer for (Task-Oriented) Dialogue Modeling We now briefly discuss several advances in modeling of natural language that facilitate applicability of pretrained generative models in task-oriented  ... 
arXiv:1907.05774v2 fatcat:n2zjh5vgf5fsbpyr43mtnw74o4

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

Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Xiaoyan Zhu
2020 arXiv   pre-print
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities  ...  We believe that this survey, though incomplete, can shed a light on future research in task-oriented dialog systems.  ...  Natural Language Understanding Given a user utterance, the natural language understanding (NLU) component maps the utterance to a structured semantic representation.  ... 
arXiv:2003.07490v3 fatcat:powcuixxargkbp57kpwmjict3y
« Previous Showing results 1 — 15 out of 406,669 results