Filters








913 Hits in 6.0 sec

Graph Convolutional Network with Sequential Attention for Goal-Oriented Dialogue Systems

Suman Banerjee, Mitesh M. Khapra
2019 Transactions of the Association for Computational Linguistics  
GCN for goal-oriented dialogues.  ...  Domain-specific goal-oriented dialogue systems typically require modeling three types of inputs, namely, (i) the knowledge-base associated with the domain, (ii) the history of the conversation, which is  ...  In this work, we propose to use such graph structures for goal-oriented dialogues.  ... 
doi:10.1162/tacl_a_00284 fatcat:jmwei7kitbgpdmetor3shst7yq

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
From the angle of system type, we discuss task-oriented and open-domain dialogue systems as two streams of research, providing insight into the hot topics related.  ...  Furthermore, we comprehensively review the evaluation methods and datasets for dialogue systems to pave the way for future research.  ...  Memory networks for task-oriented dialogue systems Chen et al. (2019c) argued that stateof-the-art task-oriented dialogue systems tended to combine dialogue history and knowledge base entries in a single  ... 
arXiv:2105.04387v5 fatcat:yd3gqg45rjgzxbiwfdlcvf3pye

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking [article]

Weizhe Lin, Bo-Hsiang Tseng, Bill Byrne
2021 arXiv   pre-print
Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances.  ...  We present a novel hybrid architecture that augments GPT-2 with representations derived from Graph Attention Networks in such a way to allow causal, sequential prediction of slot values.  ...  Acknowledgements We thank Zhilin Wang (University of Washington) for initial discussions and Qingbiao Li (University of Cambridge) for an initial implementation of graph convolution operations.  ... 
arXiv:2104.04466v3 fatcat:siudkvgp3vgjri52nhlgtjcdea

BARCOR: Towards A Unified Framework for Conversational Recommendation Systems [article]

Ting-Chun Wang, Shang-Yu Su, Yun-Nung Chen
2022 arXiv   pre-print
Furthermore, we also design and collect a lightweight knowledge graph for CRS in the movie domain.  ...  Such modular architectures often come with a complicated and unintuitive connection between the modules, leading to inefficient learning and other issues.  ...  Related Work As a specific type of goal-oriented dialogue systems, Conversational Recommendation Systems (CRS) have also moved towards the use of neural networks .  ... 
arXiv:2203.14257v1 fatcat:qhncpcwsxjfxziifz5646mobke

A Weighted Heterogeneous Graph Based Dialogue System [article]

Xinyan Zhao, Liangwei Chen, Huanhuan Chen
2020 arXiv   pre-print
Then this work proposes a graph based deep Q-network (Graph-DQN) for dialogue management.  ...  By combining Graph Convolutional Network (GCN) with DQN to learn the embeddings of diseases and symptoms from both the structural and attribute information in the weighted heterogeneous graph, Graph-DQN  ...  graph based deep Q-network (BG-DQN) for dialogue management 1 .  ... 
arXiv:2010.10699v2 fatcat:vnxpp72advcq5glitfhji3zije

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue [article]

Gaurav Kumar, Rishabh Joshi, Jaspreet Singh, Promod Yenigalla
2019 arXiv   pre-print
and syntactic information by incorporating Graph Convolution Networks (GCN) over their dependency parse.  ...  in a chit-chat system.  ...  BACKGROUND: GRAPH CONVOLUTION NETWORKS GCN for undirected graph: For an undirected graph G = (V, E), where V is the set of n vertices and E is the set of edges, the representation of the node v is given  ... 
arXiv:1912.10160v1 fatcat:xhmmpnsz2fbqtexdhuhgk7p3a4

"Suggest me a movie for tonight": Leveraging Knowledge Graphs for Conversational Recommendation

Rajdeep Sarkar, Koustava Goswami, Mihael Arcan, John P. McCrae
2020 Zenodo  
Recently, the use of external knowledge in the form of knowledge graphs has shown to improve the performance in recommendation and dialogue systems.  ...  Information from knowledge graphs aids in enriching those systems by providing additional information such as closely related products and textual descriptions of the items.  ...  We would also like to thank the anonymous reviewers for their insights on this work.  ... 
doi:10.5281/zenodo.4320720 fatcat:ithjjhf2yzbxngav3tg7cqzsdi

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks [article]

Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria
2021 arXiv   pre-print
This graph is fed to a graph attention network for context propagation among relevant nodes, which effectively captures the dialogue context.  ...  We, however, present a graph attention network-based method for DRE where a graph, that contains meaningfully connected speaker, entity, entity-type, and utterance nodes, is constructed.  ...  Zhang et al. (2018) designed a pruning algorithm for syntactic graphs and add a graph convolution layer on top of the sequential LSTM encoder in the learning process.  ... 
arXiv:2009.05092v3 fatcat:yvl66ojjuzex3py75kbcag5nie

Unsupervised Learning of Deterministic Dialogue Structure with Edge-Enhanced Graph Auto-Encoder

Yajing Sun, Yong Shan, Chengguang Tang, Yue Hu, Yinpei Dai, Jing Yu, Jian Sun, Fei Huang, Luo Si
2021 AAAI Conference on Artificial Intelligence  
It is important for task-oriented dialogue systems to discover the dialogue structure (i.e. the general dialogue flow) from dialogue corpora automatically.  ...  An unsupervised Edge-Enhanced Graph Auto-Encoder (EGAE) architecture is designed to model local-contextual and global-structural information for conversational graph learning.  ...  Acknowledgements We would like to thank all of the anonymous reviewers for their invaluable suggestions and helpful comments.  ... 
dblp:conf/aaai/SunST0DYSHS21 fatcat:v36edeximbdypfln3ymxmg2bvq

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations [article]

Qian Li, Hao Peng, Jianxin Li, Jia Wu, Yuanxing Ning, Lihong Wang, Philip S. Yu, Zheng Wang
2021 arXiv   pre-print
This paper presents a better approach for event extraction by explicitly utilizing the relationships of event arguments. We achieve this through a carefully designed task-oriented dialogue system.  ...  Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction.  ...  To allow task-oriented dialogue system, as shown in Fig. 2.  ... 
arXiv:2106.12384v2 fatcat:blyylym77vdupbrolil2dtmrna

Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review [article]

Hao Wang, Bin Guo, Yating Zeng, Yasan Ding, Chen Qiu, Ying Zhang, Lina Yao, Zhiwen Yu
2022 arXiv   pre-print
The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial  ...  With the gradually complex human-computer interaction requirements (e.g., multimodal inputs, time sensitivity), it is difficult for traditional text-based dialogue system to meet the demands for more vivid  ...  ACKNOWLEDGMENTS This work was partially supported by the National Science Fund for Distinguished Young Scholars (62025205), and the National Natural Science Foundation of China (No. 62032020, 61960206008  ... 
arXiv:2207.00782v1 fatcat:a57laj75xfa43gg4hjvxdh4c4i

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems [article]

Andrea Madotto, Samuel Cahyawijaya, Genta Indra Winata, Yan Xu, Zihan Liu, Zhaojiang Lin, Pascale Fung
2020 arXiv   pre-print
Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable.  ...  We evaluate our solution in five task-oriented dialogue datasets with small, medium, and large KB size.  ...  Graph convolutional network with sequential attention for goal-oriented dialogue systems. Transactions of the Association for Computational Linguistics, 7:485- 500.  ... 
arXiv:2009.13656v1 fatcat:j66wjv37ybcrramu3a75bis4we

A survey of neural models for the automatic analysis of conversation: Towards a better integration of the social sciences [article]

Chloé Clavel and Matthieu Labeau and Justine Cassell
2022 arXiv   pre-print
They take advantage of some of the key attributes of contemporary machine learning, such as recurrent neural networks with attention mechanisms and transformer-based approaches.  ...  These include neural architectures for detecting emotion, dialogue acts, and sentiment polarity.  ...  node classification task using graph convolutional networks (GCNs).  ... 
arXiv:2203.16891v1 fatcat:qt635cgmv5asbjkwzbtjvsf7ei

Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology [article]

Yangjun Zhang, Pengjie Ren, Maarten de Rijke
2020 arXiv   pre-print
With their increased generative capacity of corpusbased conversational agents comes the need to classify and filter out malevolent responses that are inappropriate in terms of content and dialogue acts  ...  First, we present a Hierarchical Malevolent Dialogue Taxonomy (HMDT).  ...  First, graph neural networks (GCNs) have drawn the attention of researchers, with various methods that build graphs and do graph feature engineering [32, 42] .  ... 
arXiv:2008.09706v1 fatcat:zipkjnxpqvfdzliccpraiaafpa

Framework for Deep Learning-Based Language Models using Multi-task Learning in Natural Language Understanding: A Systematic Literature Review and Future Directions

Rahul Manohar Samant, Mrinal Bachute, Shilpa Gite, Ketan Kotecha
2022 IEEE Access  
Unfortunately, these models cannot be generalized for all the NLP tasks with similar performance.  ...  This SLR proposes building steps for a conceptual framework to achieve goals of enhancing the performance of language models in the field of NLU.  ...  [55] employed a GCNN model which uses CNN with graph networks. They learn a Text Graph Convolutional Network (Text GCN) for the corpus after creating a single text graph.  ... 
doi:10.1109/access.2022.3149798 fatcat:k3kdt4eryzdfpk5k6w62jtlskm
« Previous Showing results 1 — 15 out of 913 results