Filters








3,569 Hits in 3.7 sec

Recognizing Question Entailment for Medical Question Answering

Asma Ben Abacha, Dina Demner-Fushman
2017 AMIA Annual Symposium Proceedings  
In this paper, we propose a new approach for the detection of similar questions based on Recognizing Question Entailment (RQE).  ...  Our final goal is to automatically provide an existing answer if FAQ similar to a consumer health question exists.  ...  We presented an automatic method for the construction of training corpora for RQE and a semi-automatic method for the construction of a test corpus for medical questions.  ... 
pmid:28269825 pmcid:PMC5333286 fatcat:de4e5eavvrffhk3fcwz452zp5e

An FAQ Search Method Using a Document Classifier Trained With Automatically Generated Training Data
自動生成した学習データを用いた文書分類器に基づく FAQ 検索システム

Takuya Makino, Tomoya Noro, Tomoya Iwakura
2017 Journal of Natural Language Processing  
We propose an Frequently Asked Question (FAQ) search method that uses a document classifier for classifying a natural language query to a corresponding FAQ.  ...  To tackle this problem, our method generates training data automatically from FAQs and corresponding histories and trains the document classifier with them.  ...  FAQ 0 β Ranking SVM(Joachims 2002) (Sculley 2009) K 300 ExtractFeatureVector Base features tfidf FAQ+query faq-scorer • Base features -cos-q, cos-a: cos-q FAQ cos-a FAQ FAQ  ... 
doi:10.5715/jnlp.24.117 fatcat:ce6omcm5zzgfbd5nxwtigfonqy

orgFAQ: A New Dataset and Analysis on Organizational FAQs and User Questions [article]

Guy Lev, Michal Shmueli-Scheuer, Achiya Jerbi, David Konopnicki
2020 arXiv   pre-print
On the other hand, the content of FAQs is affected by user questions by definition. In order to promote research in this field, several FAQ datasets exist.  ...  Thus, we release orgFAQ, a new dataset composed of 6988 user questions and 1579 corresponding FAQs that were extracted from organizations' FAQ webpages in the Jobs domain.  ...  Table 5 : 5 Mean ROUGE F 1 scores of our FAQ- Generator vs. a baseline method which randomly se- lects one of the input user questions.  ... 
arXiv:2009.01460v1 fatcat:ca6irsstybd3bkk7pntztcczce

A Mobile-Based Question-Answering and Early Warning System for Assisting Diabetes Management

Wenxiu Xie, Ruoyao Ding, Jun Yan, Yingying Qu
2018 Wireless Communications and Mobile Computing  
Results show that two essential methods in the system outperform baseline methods on both aspects.  ...  This study is to develop a mobile-based diabetes question-answering (Q&A) and early warning system named Dia-AID, assisting diabetes patients and populations at high risk.  ...  Acknowledgments The work was substantially supported by a grant from the National Natural Science Foundation of China (no.  ... 
doi:10.1155/2018/9163160 fatcat:e4hruin4jbg3de5usqqvhvi27i

UNDIKSHA VIRTUAL ASSISTANT (SHAVIRA): INTEGRATION FREQUENCY ASKED QUESTION WITH RASA FRAMEWORK

I Ketut Resika Arthana, Luh Joni Erawati Dewi, Ketut Agus Seputra, Ni Wayan Marti
2021 JST (Jurnal Sains dan Teknologi)  
Shavira is a knowledge management system (KMS) as Frequency Asked Question (FAQ) system to facilitate users to get an answer about their questions.  ...  We used Rasa Framework as a chatbot engine in Shavira. Rasa Framework is an open-source virtual assistant engine based on artificial intelligence.  ...  The method to search for answers by the chatbot utilizing machine learning technology to perform a sophisticated retrieval process, where responses are generated based on analysis from web searches (Cahn  ... 
doi:10.23887/jst-undiksha.v10i2.39863 fatcat:ee2r3oc535hfxbz7slwyjynyyq

Towards More Robust Natural Language Understanding [article]

Xinliang Frederick Zhang
2022 arXiv   pre-print
Besides proposing more advanced model architectures, constructing more reliable and trustworthy datasets also plays a huge role in improving NLU systems, without which it would be impossible to train a  ...  doesn't know a priori of users' inputs.  ...  predict potential question phrases set {Y T } on {A T } 6: Use QPP-enhanced QG to generate diverse questions {Q T } based on {(A T , Y T )} 7: Train a QA model on synthetic target data {(P T , A T , Q  ... 
arXiv:2112.02992v2 fatcat:5pbszflxkbdibanpcvaqfzv67a

Development of an automatic customer service system on the internet

Judy C.R. Tseng, Gwo-Jen Hwang
2007 Electronic Commerce Research and Applications  
from the frequently asked question (FAQ) database.  ...  Most existing network-based customer services heavily rely on manpower in replying e-mails or on-line requests from customers, which not only increases the service cost, but also delay the time for responding  ...  To cope with these problems, this study proposes a new system, automatic customer service system (ACSS), which can automatically reply the requests from customers by invoking a knowledge base containing  ... 
doi:10.1016/j.elerap.2006.04.009 fatcat:smf7tc6ytjfg3di6jogppq2zsu

Effective FAQ Retrieval and Question Matching With Unsupervised Knowledge Injection [article]

Wen-Ting Tseng, Tien-Hong Lo, Yung-Chang Hsu, Berlin Chen
2020 arXiv   pre-print
We evaluate variants of our approach on a publicly-available Chinese FAQ dataset, and further apply and contextualize it to a large-scale question-matching task, which aims to search questions from a QA  ...  distilled from a generic (open domain) knowledge base, into a contextual language model for inferring the q-A relevance.  ...  Instead of using the unsupervised Okapi BM25 method, we in this paper employ a supervised neural method for this purpose, which encompasses a single layer neural network stacked on top of a pre-trained  ... 
arXiv:2010.14049v1 fatcat:be3tvdo7inellfevcll3j4odlq

FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance [article]

Wataru Sakata, Tomohide Shibata, Ribeka Tanaka, Sadao Kurohashi
2019 arXiv   pre-print
Frequently Asked Question (FAQ) retrieval is an important task where the objective is to retrieve an appropriate Question-Answer (QA) pair from a database based on a user's query.  ...  Since the number of QA pairs in FAQ page is not enough to train a model, we cope with this issue by leveraging FAQ sets that are similar to the one in question.  ...  In general, information retrieval evaluation based on the pooling method has inherently a biased problem.  ... 
arXiv:1905.02851v2 fatcat:gckz62oaijdwngaccoumx4wwqq

Retrieving answers from frequently asked questions pages on the web

Valentin Jijkoun, Maarten de Rijke
2005 Proceedings of the 14th ACM international conference on Information and knowledge management - CIKM '05  
from a web search engine log.  ...  The task involves three steps: (1) fetching FAQ pages from the web; (2) automatic extraction of question/answer (Q/A) pairs from the collected pages; and (3) answering users' questions by retrieving appropriate  ...  We use fielded search, based on a mixture model to which indexed questions, answers, and full FAQ pages contribute, optionally together with phrasal search and stemming.  ... 
doi:10.1145/1099554.1099571 dblp:conf/cikm/JijkounR05 fatcat:m7sxwqdvvrgy5mccr56egg4mne

A Machine-Translation Method for Normalization of SMS [chapter]

Darnes Vilariño, David Pinto, Beatriz Beltrán, Saul León, Esteban Castillo, Mireya Tovar
2012 Lecture Notes in Computer Science  
Normalization of SMS is a very important task that must be addressed by the computational community because of the tremendous growth of services based on mobile devices, which make use of this kind of  ...  There exist many limitations on the automatic treatment of SMS texts derived from the particular writing style used.  ...  In this paper we aim, as a study case, to face the problem of searching answers of FAQs (Frequently Asked Questions) when one SMS is used as query for the information retrieval system.  ... 
doi:10.1007/978-3-642-31149-9_30 fatcat:sm5dy7p3wzgqdozuvvl5oycj7u

Automated Self-learning Chatbot Initially Build as a FAQs Database Information Retrieval System: Multi-level and Intelligent Universal Virtual Front-office Implementing Neural Network

Alessandro Massaro, Vincenzo Maritati, Angelo Galiano
2018 Informatica (Ljubljana, Tiskana izd.)  
The method proposed in this paper is based on dynamical information system capable toimplement a universal multi-level virtual front-office made by FAQs and chatbot self-learning systems.We describe statistics  ...  for their specific tasks, limiting the possibility to transform directly their methods in a general knowledge extraction approach.  ...  these questions with similar ones but based on different keywords.  ... 
doi:10.31449/inf.v42i4.2173 fatcat:7fd4lgx4mbfgppke4ftl3nqmwm

Towards a Next-Generation Search Engine [chapter]

Qiang Yang, Hai-Feng Wang, Ji-Rong Wen, Gao Zhang, Ye Lu, Kai-Fu Lee, Hong-Jiang Zhang
2000 Lecture Notes in Computer Science  
In this paper, we describe the system architecture of a next-generation search engine that we have built with a goal to provide accurate search result on frequently asked concepts.  ...  Search based on simple keywords returns many irrelevant documents that can easily swamp the user.  ...  In Brilliant™ search engine, this confidence level is built based on statistical training.  ... 
doi:10.1007/3-540-44533-1_5 fatcat:kalceka55ncitdx7c3e3mpgnwi

Who asked what: integrating crowdsourced FAQs into API documentation

Cong Chen, Kang Zhang
2014 Companion Proceedings of the 36th International Conference on Software Engineering - ICSE Companion 2014  
Developers often rely on Web search to retrieve additional programming help.  ...  We propose to connect these two types of documentation by capturing developers' Web browsing behavior in the context of document reading and integrating crowdsourced frequently asked questions (FAQs) into  ...  The relevance of the page to her question was inferred automatically based on her interactions (e.g., dwell time and cursor movement) with the page [7] .  ... 
doi:10.1145/2591062.2591128 dblp:conf/icse/ChenZ14 fatcat:secxv7crpjfqpgoutppikxdub4

MFAQ: a Multilingual FAQ Dataset [article]

Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann, Walter Daelemans
2021 arXiv   pre-print
Our experiments reveal that a multilingual model based on XLM-RoBERTa achieves the best results, except for English.  ...  Lower resources languages seem to learn from one another as a multilingual model achieves a higher MRR than language-specific ones.  ...  FAQs are also useful to automatically answer the most frequent questions on different communication channels: email, chatbot, or search bar.  ... 
arXiv:2109.12870v2 fatcat:okrggnbm4zepvnrw3uqsd2oroi
« Previous Showing results 1 — 15 out of 3,569 results