79,700 Hits in 5.3 sec

User Intent Prediction in Information-seeking Conversations

Chen Qu, Liu Yang, W. Bruce Croft, Yongfeng Zhang, Johanne R. Trippas, Minghui Qiu
2019 Proceedings of the 2019 Conference on Human Information Interaction and Retrieval - CHIIR '19  
In this paper, we investigate two aspects of user intent prediction in an information-seeking setting.  ...  Due to the limited communication bandwidth in conversational search, it is important for conversational assistants to accurately detect and predict user intent in information-seeking conversations.  ...  ACKNOWLEDGMENTS This work was supported in part by the Center for Intelligent Information Retrieval and in part by NSF IIS-1715095.  ... 
doi:10.1145/3295750.3298924 dblp:conf/chiir/Qu0CZTQ19 fatcat:mtgyzfi3drd7vkuje4s5y4oczy

Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Dataset [article]

Gustavo Penha, Alexandru Balan, Claudia Hauff
2019 arXiv   pre-print
We provide baseline results for the conversation response ranking and user intent prediction tasks.  ...  Conversational search is an approach to information retrieval (IR), where users engage in a dialogue with an agent in order to satisfy their information needs.  ...  User Intent Prediction The setup of the user intent prediction task is as follows: predict the user intents for each utterance in a given conversation.  ... 
arXiv:1912.04639v1 fatcat:ywrcnweumzhdxh46de64r4vs74

Analyzing and Characterizing User Intent in Information-seeking Conversations

Chen Qu, Liu Yang, W. Bruce Croft, Johanne R. Trippas, Yongfeng Zhang, Minghui Qiu
2018 The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18  
With MSDialog, we find some highly recurring patterns in user intent during an information-seeking process. They could be useful for designing conversational search systems.  ...  In this paper, we introduce a new dataset designed for this purpose and use it to analyze information-seeking conversations by user intent distribution, co-occurrence, and flow patterns.  ...  ACKNOWLEDGMENTS This work was supported in part by the Center for Intelligent Information Retrieval and in part by NSF grant #IIS-1419693 and NSF grant #IIS-1715095.  ... 
doi:10.1145/3209978.3210124 dblp:conf/sigir/QuYCTZQ18 fatcat:ieei3aoawfa3fdyicugowfpnka

IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems [article]

Liu Yang, Minghui Qiu, Chen Qu, Cen Chen, Jiafeng Guo, Yongfeng Zhang, W. Bruce Croft, Haiqing Chen
2020 arXiv   pre-print
In this paper, we analyze user intent patterns in information-seeking conversations and propose an intent-aware neural response ranking model "IART", which refers to "Intent-Aware Ranking with Transformers  ...  Understanding user intent such as clarification questions, potential answers and user feedback in information-seeking conversations is critical for retrieving good responses.  ...  However, much less attention has been paid on the user intent in conversations and how to leverage user intent for response ranking in information-seeking conversations.  ... 
arXiv:2002.00571v1 fatcat:e7e54ph3rnbv7hzlvo7i6svaby

User Intent Inference for Web Search and Conversational Agents [article]

Ali Ahmadvand
2020 arXiv   pre-print
User intent understanding is a crucial step in designing both conversational agents and search engines.  ...  To address the first topic, I proposed novel models to incorporate entity information and conversation-context clues to predict both topic and intent of the user's utterances.  ...  To this end, we proposed a hierarchical architecture for the user intent classification, where in the first layer, the intent of the users in purchasing a product or seeking information (product vs informational  ... 
arXiv:2005.13808v2 fatcat:hxwuux6d45bfdd46nqwqy4aiki

BERT for Conversational Question Answering Systems Using Semantic Similarity Estimation

Abdulaziz Al-Besher, Kailash Kumar, M. Sangeetha, Tinashe Butsa
2022 Computers Materials & Continua  
This model shows the ability to use the limited information in user queries for best context inferences based on Closed-Domain-based CS and Bidirectional Encoder Representations from Transformers for textual  ...  While receiving a question in a new conversational search, the model determines the question that refers to more past CS.  ...  of the user for intent prediction.  ... 
doi:10.32604/cmc.2022.021033 fatcat:wm34anpztzhm5k7q4di2jsxkyi

Supporting Complex Information-Seeking Tasks with Implicit Constraints [article]

Ali Ahmadvand, Negar Arabzadeh, Julia Kiseleva, Patricio Figueroa Sanz, Xin Deng, Sujay Jauhar, Michael Gamon, Eugene Agichtein, Ned Friend, Aniruddha
2022 arXiv   pre-print
This advancement provides the final user more flexibility and precision in expressing their intent through the search process.  ...  In such scenarios, the user requests can be issued at once in the form of a complex and long query, unlike conversational and exploratory search models that require short utterances or queries where they  ...  The proposed interactive user intent modeling for sup- porting complex information seeking tasks.  ... 
arXiv:2205.00584v1 fatcat:waapsu6kjfgolbvhny36kqffsa

Wizard of Search Engine: Access to Information Through Conversations with Search Engines [article]

Pengjie Ren, Zhongkun Liu, Xiaomeng Song, Hongtao Tian, Zhumin Chen, Zhaochun Ren, Maarten de Rijke
2021 arXiv   pre-print
Conversational information seeking (CIS) is playing an increasingly important role in connecting people to information.  ...  In this work, we make efforts to facilitate research on CIS from three aspects. (1) We formulate a pipeline for CIS with six sub-tasks: intent detection (ID), keyphrase extraction (KE), action prediction  ...  Conversational information seeking (CIS) has emerged as a new paradigm for interactions with search engines [3, 11, 47] .  ... 
arXiv:2105.08301v1 fatcat:3vbsrlphrvdx3otnrn65o2a5ki

Direct Answer Threshold Optimization in Dialogue Systems

Marco Peixeiro, Nada Naji, Eric Charton
2021 Proceedings of the Canadian Conference on Artificial Intelligence  
This is especially true in an information seeking task where prompt, correct answers with minimal back-and-forth are desirable.  ...  To determine whether a direct answer is to be given or not, a threshold is applied to the to the confidence level of the predicted intent; in the case where the confidence is higher than the threshold,  ...  We plan on making the datasets available publicly in the medium term. In the meantime, the datasets can be provided upon request by contacting one of the authors.  ... 
doi:10.21428/594757db.ae6ae665 fatcat:hcmqdslylzf6rcykotruqsup5e

Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questions [article]

Kaustubh D. Dhole
2020 arXiv   pre-print
Seeking clarification from the user to classify user intents not only helps understand the user intent effectively, but also reduces the roboticity of the conversation and makes the interaction considerably  ...  Task oriented Dialogue Systems generally employ intent detection systems in order to map user queries to a set of pre-defined intents.  ...  Aliannejadi et al. (2019) proposed a clarification dataset to improve open-domain information-seeking conversations.  ... 
arXiv:2008.07559v1 fatcat:nk5rrvutsvgbjprd5cm6fa2fee

3.10 Ranking People Ranking People

Markus Bernhard Strohmaier
2020 Dagstuhl Reports  
4 Working groups Defining Conversational Search  ...  Conversational information seeking (CIS) has been recognized as a major emerging research area in information retrieval.  ...  This makes it challenging for search engines to predict possible intents, only one of which may pertain to the current user.  ... 
doi:10.18154/rwth-conv-243302 fatcat:cn5d6n3worff7epk45iaxcfwr4

Spoken Conversational Search

Johanne R. Trippas
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
We will also investigate an information seeking model for audio and language models.  ...  approach to determining user information needs, presenting results and enabling search reformulations.  ...  H. 5 .1 [Multimedia Information Systems]; H.3.3 [Information Search and Retrieval]; H.5.2 [User Interfaces] Conversational Search; Interactive Information Retrieval; Search Result Summarisation; Spoken  ... 
doi:10.1145/2766462.2767850 dblp:conf/sigir/Trippas15 fatcat:pqbedvjl3vezpexio6qvnsexn4

Building a Chatbot for the Department of ECE using Flask

G V Pradeep Kumar
2021 International Journal for Research in Applied Science and Engineering Technology  
Implementation is done in Python using some of its software libraries.  ...  The heart of ChatBot technology lies in Natural Language Processing or NLP.  ...  an effort to seek out common spelling mistakes or typographical errors that might the user intent to convey.  ... 
doi:10.22214/ijraset.2021.34865 fatcat:ule4apebxvccjkkicurta3qiey

"What can I cook with these ingredients?" – Understanding cooking-related information needs in conversational search [article]

Alexander Frummet, David Elsweiler, Bernd Ludwig
2021 arXiv   pre-print
In a second contribution we perform classification experiments to determine the feasibility of predicting the type of information need a user has during a dialogue using the turn provided.  ...  As conversational search becomes more pervasive, it becomes increasingly important to understand the user's underlying information needs when they converse with such systems in diverse domains.  ...  In addition to predicting user intents, there have been efforts to improve information need prediction. For example, Aliannejadi et al.  ... 
arXiv:2112.04788v2 fatcat:rmlqopqk3jfapainkp3ag7hh34

Facts or friends?

F. Maxwell Harper, Daniel Moy, Joseph A. Konstan
2009 Proceedings of the 27th international conference on Human factors in computing systems - CHI 09  
might successfully engage users in discussion, but probably will not yield a useful web page for users searching for information about evolution.  ...  For example, a conversational question such as "do you believe in evolution?"  ...  In this paper, we seek to deepen our understanding of the differences between conversational questions and informational questions.  ... 
doi:10.1145/1518701.1518819 dblp:conf/chi/HarperMK09 fatcat:wlienkkm4zbatlde4pjxijllnq
« Previous Showing results 1 — 15 out of 79,700 results