Filters








439 Hits in 4.4 sec

Wizard of Wikipedia: Knowledge-Powered Conversational agents [article]

Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston
<span title="2019-02-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To that end we collect and release a large dataset with conversations directly grounded with knowledge retrieved from Wikipedia.  ...  In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date.  ...  The aim is for those strands to come together to obtain an engaging and knowledgeable conversational agent. Wizard: I'm impressed!  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.01241v2">arXiv:1811.01241v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2qllsju26jhwnlbftl4y5eo7ke">fatcat:2qllsju26jhwnlbftl4y5eo7ke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191017045259/https://arxiv.org/pdf/1811.01241v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9e/26/9e26cae4aaed4ac8e73290e76cb39efbf0230831.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.01241v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deletion discussions in Wikipedia

Jodi Schneider, Alexandre Passant, Stefan Decker
<span title="">2012</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/a6gr3ghqmbd5jp4r4tndroyc2a" style="color: black;">Proceedings of the Eighth Annual International Symposium on Wikis and Open Collaboration - WikiSym &#39;12</a> </i> &nbsp;
Deletion of articles is a common process in Wikipedia, in order to ensure the overall quality of the encyclopedia.  ...  In this paper, we study deletion in Wikipedia, drawing from factor analysis, and taking an in-depth, content-analysis-based approach.  ...  When procedural knowledge about Wikipedia is valued more than content expertise, this limits the effectiveness of decisions and risks deleting content that is worthwhile but not well-defended.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2462932.2462955">doi:10.1145/2462932.2462955</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wikis/SchneiderPD12.html">dblp:conf/wikis/SchneiderPD12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pcfocidlq5b7hj3yogn3rjsybu">fatcat:pcfocidlq5b7hj3yogn3rjsybu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170202013141/http://jodischneider.com/pubs/wikisym2012.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f7/c1/f7c1f79d9caf798553aa326c80a5c82d58b028be.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2462932.2462955"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

How Do You Want Your Chatbot? An Exploratory Wizard-of-Oz Study with Young, Urban Indians [chapter]

Indrani Medhi Thies, Nandita Menon, Sneha Magapu, Manisha Subramony, Jacki O'Neill
<span title="">2017</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
An offshoot of personal digital assistants are A.I. powered text-messaging chatbots.  ...  A chatbot is an artificially intelligent chat agent that simulates human-like conversation, for example, by allowing users to type questions and, in return, generating meaningful answers to those questions  ...  The Wizard The Wizard was a writer and content creator on the team working on the personality of the A.I. powered chatbot that we were building.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-67744-6_28">doi:10.1007/978-3-319-67744-6_28</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ijin2uq4m5cehpabpcx4wecun4">fatcat:ijin2uq4m5cehpabpcx4wecun4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322143950/https://www.microsoft.com/en-us/research/wp-content/uploads/2017/10/IndraniInteract_2017_cameraready.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e2/4b/e24b275073915d008038294f5ee98a625259ce7c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-67744-6_28"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Critical Point of View: A Wikipedia Reader

Geert Lovink, Nathaniel Tkacz, Joseph M. Reagle, Dan O'Sullivan, Lawrence Liang, Amila Akdag Salah, Cheng Gao, Krzystztof Suchecki, Andrea Scharnhorst, R. Stuart Geiger, Edgar Enyedy, Peter B. Kaufman (+19 others)
<span title="">2012</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tol7woxlqjeg5bmzadeg6qrg3e" style="color: black;">Social Science Research Network</a> </i> &nbsp;
Institute of Network Cultures, Amsterdam 2011 ISBN 978-90-78146-13-1  ...  The agentive and generative capacities of the database designs of Wikipedia and TAMI become clear: each design materializes particular kinds of knowledge and knowers.  ...  TAMI's design is understood as playing an agentive role in both the ordering of knowledge in TAMI and in the emergence of new kinds of knowers and knowledge.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.2075015">doi:10.2139/ssrn.2075015</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ufngx3eoazbtfe5pgtvovak6q4">fatcat:ufngx3eoazbtfe5pgtvovak6q4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170923080342/https://pure.uva.nl/ws/files/1341841/105459_cpov_reader_7.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.2075015"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ssrn.com </button> </a>

The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents [article]

Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, Jason Weston
<span title="2020-04-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources  ...  By multi-tasking on such a broad large-scale set of data, we hope to both move towards and measure progress in producing a single unified agent that can perceive, reason and converse with humans in an  ...  Wizard of wikipedia: Knowledge-powered conversational agents. In Proceedings of the International Confer- ence on Learning Representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.03768v2">arXiv:1911.03768v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xafwif4fbfaptm3jho67tukpeq">fatcat:xafwif4fbfaptm3jho67tukpeq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903234808/https://arxiv.org/pdf/1911.03768v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ae/f7/aef75886d218e793b37f445cdcdb0a7742846803.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.03768v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Knowledge Injection into Dialogue Generation via Language Models [article]

Yi-Lin Tuan, Wei Wei, William Yang Wang
<span title="2021-04-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
, in many conversations. To reduce this homogeneity, external knowledge such as the speaker's profile and domain knowledge is applied as an additional condition to diversify a model's output.  ...  The required knowledge to develop an effective conversation, however, is not always available, which is different from prior work's assumption that a model always has acquired sufficient knowledge before  ...  collected a wizard-apprentice conversation dataset grounded on Wikipedia articles.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.14614v2">arXiv:2004.14614v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rgw4of5ncfha3aja2sqr6gqh3e">fatcat:rgw4of5ncfha3aja2sqr6gqh3e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200506064703/https://arxiv.org/pdf/2004.14614v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.14614v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation [article]

Yu Li, Baolin Peng, Yelong Shen, Yi Mao, Lars Liden, Zhou Yu, Jianfeng Gao
<span title="2021-12-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources.  ...  It can achieve comparable performance with state-of-the-art methods under a fully-supervised setting and significantly outperforms other methods in zero-shot and few-shot settings.  ...  Wizard of wikipedia: Knowledge-powered conversational shot settings and can generalize to different knowl- agents.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.07924v1">arXiv:2112.07924v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aw6sd4ilu5fjbfagtc42g74dhe">fatcat:aw6sd4ilu5fjbfagtc42g74dhe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211222152201/https://arxiv.org/pdf/2112.07924v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c9/88/c9887809b4303f361976b4731d563c10f24dd147.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.07924v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

KILT: a Benchmark for Knowledge Intensive Language Tasks [article]

Fabio Petroni, Aleksandra Piktus, Angela Fan, Patrick Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, Vassilis Plachouras, Tim Rocktäschel (+1 others)
<span title="2021-05-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
All tasks in KILT are grounded in the same snapshot of Wikipedia, reducing engineering turnaround through the re-use of components, as well as accelerating research into task-agnostic memory architectures  ...  While some models do well on individual tasks, developing general models is difficult as each task might require computationally expensive indexing of custom knowledge sources, in addition to dedicated  ...  Wizard of wikipedia: Knowledge-powered conversational agents. Proceedings of the International Conference on Learning Representations (ICLR).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.02252v4">arXiv:2009.02252v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/44gk5nyhrvckriymi7wsrxze7m">fatcat:44gk5nyhrvckriymi7wsrxze7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210414050644/https://arxiv.org/pdf/2009.02252v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/62/cd/62cd8c6766379ad66fa5d8d52742e58c422cc10a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.02252v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Teach Me What to Say and I Will Learn What to Pick: Unsupervised Knowledge Selection Through Response Generation with Pretrained Generative Models [article]

Ehsan Lotfi, Maxime De Bruyn, Jeska Buhmann, Walter Daelemans
<span title="2021-10-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
sources) instead of trying to pick the best knowledge option.  ...  Knowledge Grounded Conversation Models (KGCM) are usually based on a selection/retrieval module and a generation module, trained separately or simultaneously, with or without having access to a gold knowledge  ...  With the release of large knowledge grounded conversational datasets like Wizard of Wikipedia (Dinan et al., 2019) , Topical-chat (Gopalakrishnan et al., 2019) and Holl-E (Moghe et al., 2018) , the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02067v1">arXiv:2110.02067v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f365fgrdungcbeoor7sr4ql3sy">fatcat:f365fgrdungcbeoor7sr4ql3sy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211007025801/https://arxiv.org/pdf/2110.02067v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/49/6b/496be520383328b0d3811a6ee6adbb64a19ed091.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02067v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation [article]

Chujie Zheng, Minlie Huang
<span title="2022-01-14">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show that prompted language models perform superiorly to conversational models, and further analyze various factors that influence the effects of prompting.  ...  We first propose a simple prompting method for GDG tasks, where different constructs of model input, such as the grounding source and the conversation context, are distinguished through continuous or discrete  ...  This work was also supported by the Guoqiang Institute of Tsinghua University, with Grant No. 2019GQG1 and 2020GQG0005.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.06513v2">arXiv:2109.06513v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bhcbaictdvhc7j7s7wu5zwh4ba">fatcat:bhcbaictdvhc7j7s7wu5zwh4ba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220119233438/https://arxiv.org/pdf/2109.06513v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c7/8b/c78bb96ee119950b4f6a9dc0155199826b0bc8c8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.06513v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Q^2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering [article]

Or Honovich, Leshem Choshen, Roee Aharoni, Ella Neeman, Idan Szpektor, Omri Abend
<span title="2021-09-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To foster proper evaluation, we curate a novel dataset of dialogue system outputs for the Wizard-of-Wikipedia dataset, manually annotated for factual consistency.  ...  Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability.  ...  Acknowledgements This work was carried out as part of a Master Sponsored Research Agreement between the Hebrew University and Google, and was also supported by a gift from Google.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.08202v2">arXiv:2104.08202v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/awwtvz4nmjbzvhmhkkx5z4mjtu">fatcat:awwtvz4nmjbzvhmhkkx5z4mjtu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210915114200/https://arxiv.org/pdf/2104.08202v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fa/c6/fac600d915bf9fd15813ff7bcb6f0a17065c6ea9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.08202v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Empirical study on BlenderBot 2.0 Errors Analysis in terms of Model, Data and User-Centric Approach [article]

Jungseob Lee, Midan Shim, Suhyune Son, Yujin Kim, Chanjun Park, Heuiseok Lim
<span title="2022-01-10">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
From a user perspective, we identify nine types of problems of BlenderBot 2.0, and their causes are thoroughly investigated.  ...  verifying the accuracy of internet-based information.  ...  ., 2018) , Wizard of Wikipedia (WoW) , and Empathetic Dialogues (ED) datasets (Rashkin et al., 2018) to provide engaging conversation topics, utilize knowledge, and empathize.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.03239v1">arXiv:2201.03239v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jzrqzos3tbbk7efbjhdwxaosey">fatcat:jzrqzos3tbbk7efbjhdwxaosey</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220123205250/https://arxiv.org/pdf/2201.03239v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5f/a2/5fa273f7db53ef98d3789b26a8f2dcf3b71fe005.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.03239v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions [article]

Stephen Roller, Y-Lan Boureau, Jason Weston, Antoine Bordes, Emily Dinan, Angela Fan, David Gunning, Da Ju, Margaret Li, Spencer Poff, Pratik Ringshia, Kurt Shuster (+4 others)
<span title="2020-07-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping  ...  We end with a discussion of our experience and learnings, and our recommendations to the community.  ...  Figure 2 : 2 Using Knowledge: the Wizard of Wikipedia task Figure 3 : 3 Controlling specificity in generative models affects user engagingness evaluations (See et al., 2019) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.12442v2">arXiv:2006.12442v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/stxhx77lgrbs5mdhcpyo4fak7m">fatcat:stxhx77lgrbs5mdhcpyo4fak7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200721023903/https://arxiv.org/pdf/2006.12442v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.12442v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An Exploratory Study on a Reinforcement Learning Prototype for Multimodal Image Retrieval Using a Conversational Search Interface

Abhishek Kaushik, Billy Jacob, Pankaj Velavan
<span title="2022-02-28">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/shgfodzaxnef3ku2wx2bpwfmwe" style="color: black;">Knowledge</a> </i> &nbsp;
In the realm of information, conversational search is a relatively new trend.  ...  The result of this usability experiment proved that most of the users found the system to be very usable and helpful for their image search.  ...  Acknowledgments: The authors would like to thank Sargam Yadav for proofreading and providing suggestions for the improvement of the article.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/knowledge2010007">doi:10.3390/knowledge2010007</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m3fblpckufbnhp7w2snomjw4d4">fatcat:m3fblpckufbnhp7w2snomjw4d4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220430043427/https://mdpi-res.com/d_attachment/knowledge/knowledge-02-00007/article_deploy/knowledge-02-00007-v2.pdf?version=1646273419" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5e/2f/5e2f06537a42d96d447aed67d5803e7bb98d9fe4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/knowledge2010007"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation [article]

Hao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang, Xiaoyan Zhu
<span title="2020-04-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with knowledge annotations.  ...  In this paper, we propose a Chinese multi-domain knowledge-driven conversation dataset, KdConv, which grounds the topics in multi-turn conversations to knowledge graphs.  ...  Acknowledgments This work was jointly supported by the NSFC projects (Key project with No. 61936010 and regular project with No. 61876096), and the National Key R&D Program of China (Grant No. 2018YFC0830200  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.04100v1">arXiv:2004.04100v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g6tqgjrhunc7pnsdvhsxxx5iuq">fatcat:g6tqgjrhunc7pnsdvhsxxx5iuq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200415195200/https://arxiv.org/pdf/2004.04100v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.04100v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 439 results