A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Filters
An Automated Dialog System for Conducting Security Interviews for Access Control
[chapter]
2014
IFIP Advances in Information and Communication Technology
This paper demonstrates how an interactive voice response system can be used to generate context-sensitive, yet randomized, dialogs that provide confidence in the trustworthiness of an interviewee based ...
The system uses contextual reasoning and ontological inference to derive new facts dynamically. ...
Context Performance Using a context for question generation requires frequent querying of the ontology. ...
doi:10.1007/978-3-662-45355-1_8
fatcat:pbck6ea5knhvtamvxvd2j6psyi
Natural Language Generation at Scale: A Case Study for Open Domain Question Answering
2019
Proceedings of the 12th International Conference on Natural Language Generation
Second, we perform multi-task learning experiments between open-domain QA and task-oriented dialog, and benchmark our model on a popular NLG dataset. ...
First, we investigate the impact of increasing the number of slot types on the generation quality and experiment with different partitions of the QA data with progressively larger ontologies (up to 369 ...
In our work, we perform open-domain NLG with significantly larger ontologies and also evaluate the impact of adding the context to the input. ...
doi:10.18653/v1/w19-8657
dblp:conf/inlg/CervoneKGHVHG19
fatcat:ikc6in33rvd2fesr3khbnhtfdi
Natural Language Generation at Scale: A Case Study for Open Domain Question Answering
[article]
2019
arXiv
pre-print
Second, we perform multi-task learning experiments between open-domain QA and task-oriented dialog, and benchmark our model on a popular NLG dataset. ...
First, we investigate the impact of increasing the number of slot types on the generation quality and experiment with different partitions of the QA data with progressively larger ontologies (up to 369 ...
In our work, we perform open-domain NLG with significantly larger ontologies and also evaluate the impact of adding the context to the input. ...
arXiv:1903.08097v2
fatcat:rg5siw3onje4pnugbs2grywtfi
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking
[article]
2020
arXiv
pre-print
An ontology-based method selects a value from a candidate-value list for each target slot, while an ontology-free method extracts spans from dialog contexts. ...
Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and ontology-free methods. ...
We thank Salesforce research members for their insightful discussions, and the anonymous reviewers for their helpful and valuable comments. ...
arXiv:1910.03544v4
fatcat:3pahyygknndxjpm3dffy32if3i
FREyA: An Interactive Way of Querying Linked Data Using Natural Language
[chapter]
2012
Lecture Notes in Computer Science
This kind of adjustments -or mappings from words or phrases to ontology concepts/relations, is usually performed during the customisation of NLIs. ...
However, due to different processes used to generate ontologies, the lexicon might be of varying quality. In addition, some words might have different meanings in two different domains or context. ...
Authors would like to thank Ivan Peikov from Ontotext who helped with the configuration of OWLIM which was necessary for performing the experiments reported in this paper. ...
doi:10.1007/978-3-642-25953-1_11
fatcat:xk5x5wlbwngn3bq4nirfix2bqe
Recent Advances and Challenges in Task-oriented Dialog System
[article]
2020
arXiv
pre-print
policy learning to achieve better task-completion performance, and (3) integrating domain ontology knowledge into the dialog model. ...
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 ...
Therefore, decoupling the domain ontology and the dialog model to obtain better adaptation performance is a critical issue. ...
arXiv:2003.07490v3
fatcat:powcuixxargkbp57kpwmjict3y
Knowledge-grounded Dialog State Tracking
[article]
2022
arXiv
pre-print
Knowledge (including structured knowledge such as schema and ontology, and unstructured knowledge such as web corpus) is a critical part of dialog understanding, especially for unseen tasks and domains ...
We query relevant knowledge of various forms based on the dialog context where such information can ground the prediction of dialog states. ...
Acknowledgements We thank Abhinav Rastogi from Google Research, and anonymous reviewers for their constructive suggestions. ...
arXiv:2210.06656v1
fatcat:gjv64urdlrelbh6tl5jyefflvy
Exploiting more associations between slots for multi-domain dialog state tracking
2022
Big Data Mining and Analytics
Dialog State Tracking (DST) aims to extract the current state from the conversation and plays an important role in dialog systems. ...
Experimental results show that our approach has performed well on the Multi-domain Wizard-Of-Oz (MultiWOZ) 2.0 and MultiWOZ2.1 datasets, demonstrating the effectiveness and necessity of incorporating slot-relevant ...
Acknowledgment This work was supported by the National Natural Science Foundation of China (No. 61976247). ...
doi:10.26599/bdma.2021.9020013
fatcat:2n7h4mbovzem5mrnkmcocppgty
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking
[article]
2020
arXiv
pre-print
Instead, all values are extracted from the dialog context on-the-fly. ...
inform operations; (3) a value may be copied over from a different slot that is already contained in the dialog state to resolve coreferences within and across domains. ...
TRADE and MA-DST (Kumar et al., 2020) generate a DS from the input using a copy mechanism to combine the distributions over a pre-defined vocabulary and the vocabulary of current context. ...
arXiv:2005.02877v4
fatcat:orsm7vd4j5hpdkcl5sucvu6ms4
Towards A Separation of Pragmatic Knowledge and Contextual Information
2006
European Conference on Artificial Intelligence
We will argue that pragmatic inferences are impossible without contextual observations and introduce a model of context-adaptive processing using a combination of formal ontologies and analyzers for various ...
by a pragmatic layer to solve the problem of explicating hitherto implicit information contained in the user's utterances and to further the assistance capabilities of dialog systems and how they can ...
Acknowledgements This work has been partially funded by the German Federal Ministry of Research and Technology (BMBF) as part of the SmartWeb project under Grant 01IMD01E and by the Klaus Tschira Foundation ...
dblp:conf/ecai/PorzelZLM06
fatcat:cgml37qoqvb4hn5ysbifystuby
Situated and Interactive Multimodal Conversations
[article]
2020
arXiv
pre-print
Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, in addition to the user's utterances), and perform multimodal actions (e.g ...
to the dialog history. ...
to the data collection platforms, annotation schema development, annotation process, tooling and coordination. ...
arXiv:2006.01460v2
fatcat:yfijtft2v5hjjkwg5nv6wvwcey
The results show that our approach was able to detect 21 strong violations and 18 weak violations from the studied apps. ...
For evaluation, we applied our approach to 120 popular apps from three privacy-relevant app categories: finance, health, and dating. ...
The authors are supported in part by NSF Awards CNS-1330596, CCF-1464425, CNS-1748109, NSA Grant on Science of Security, and DHS grant DHS-14-ST-062-001. ...
doi:10.1145/3180155.3180196
dblp:conf/icse/WangQHSB018
fatcat:haa56ijcinaptjfgiwlc4kmedu
Towards Learning Through Open-Domain Dialog
[article]
2022
arXiv
pre-print
In this paper, we identify the modifications required for a dialog system to be able to learn from the dialog and propose generic approaches that can be used to implement those modifications. ...
The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change ...
Ontologies were originally built by and shared among humans to define a formal context and avoid misunderstandings in communication. ...
arXiv:2202.03040v1
fatcat:723ekej7hfgzrbasdwvjyoifbu
UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2
[article]
2021
arXiv
pre-print
Experimental results on the MultiWOZ datasets show that UBAR achieves state-of-the-art performances in multiple settings, improving the combined score of response generation, policy optimization, and end-to-end ...
Additionally, UBAR is evaluated in a more realistic setting, where its dialog context has access to user utterances and all content it generated such as belief states, system acts, and system responses ...
This work was supported by the Fundamental Research Funds for the Central Universities (No.19lgpy220) and the Program for Guangdong Introducing Innovative and Entrepreneurial Teams (No.2017ZT07X355). ...
arXiv:2012.03539v2
fatcat:u6vy5f77mrbwzp2ngr3gorgm5y
Efficacious Reuse Support as Enabler for Cross-Methodological Web Engineering with Stakeholders
2008
2008 Eighth International Conference on Web Engineering
As well as in traditional software engineering, reuse is a key factor for the efficient and efficacious construction and evolution of complex Web applications. ...
To unfold the full potential of reuse, it incorporates both planned and spontaneous reuse strategies. ...
In addition, the user can use the search results as a starting point to browse through the registry space and perform context switches following the relations defined in the ontology. ...
doi:10.1109/icwe.2008.40
dblp:conf/icwe/FreudensteinBN08
fatcat:kxxqtux43bhupmxuz7qusqwk3y
« Previous
Showing results 1 — 15 out of 20,936 results