Question Answering from Frequently Asked Question Files: Experiences with the FAQ FINDER System

By Robin D. Burke, Kristian J. Hammond, Vladimir A. Kulyukin, S. Lytinen, Noriko Tomuro, Scott Schoenberg. 1997

Subfields: Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “This mode of searching, which dates back to the late 1990s [Burke et al., 1997], is known as community question answering (CQA) [Srba and Bielikova, 2016].”
Maximum Entropy Markov Models for Information Extraction and Segmentation (2000, methodology): “In the case of FAQs, at least one such system, a question-answering system, has been described in the literature ( Burke, Hammond, Kulyukin, Lytinen, & Tomuro, 1997 ).”
Building a question answering test collection (2000, methodology): “The FAQ Finder system used files containing question and answer pairs as developed for human readers of Usenet news groups to answer user's questions [4].”
A question-entailment approach to question answering (2019, background): “One of the earliest question answering systems based on finding similar questions and re-using the existing answers was FAQ FINDER [9].”
Redefining the learning companion: the past, present, and future of educational agents (2003, background): “Furthermore, the system may collect and reuse instruction portfolios of these peers or teachers, integrating human and machine intelligence (Ackerman, 1998; Heinrich & Maurer, 2000; Burke, Hammond, Kulyukin, Lytinen, Tomuro, & Schoenberg, 1997 ).”
FAQ-based Question Answering via Word Alignment (2015, methodology): “Frequently Asked Questions (FAQ) based QA is an economical and practical solution for general QA (Burke et al., 1997).”
Open-domain textual question answering techniques (2003, methodology): “In TREC-8, the 200 questions originated from the FAQFinder (Burke et al. 1997) and from the questions generated by TREC participants or the NIST staﬀ.”
Convolutional Neural Tensor Network Architecture for Community-Based Question Answering (2015, background): “The early works can be traced back to finding similar questions in Frequently Asked Questions (FAQ) archives, such as the FAQ finder [Burke et al., 1997], which usually used statistical and semantic similarity measures to rank FAQs.”
Retrieval models for question and answer archives (2008, methodology): “For example, FAQ Finder [14] used the conventional vector space model to calculate the statistical similarities between questions and WordNet to help calculate the semantical similarities.”
Finding the right facts in the crowd: factoid question answering over social media (2008, unknown): “This area of QA can be traced to the research on answering questions using Usenet Frequently Asked Questions (FAQ) archives [7, 19, 17, 20].”
A framework to predict the quality of answers with non-textual features (2006, background): “FAQ retrieval research [3, 19, 13, 21, 9] has focused on finding similar questions from FAQ collections.”
Latent Semantic Tensor Indexing for Community-based Question Answering (2013, background): “The early works on question retrieval can be traced back to ﬁnding similar questions in Frequently Asked Questions (FAQ) archives, such as the FAQ ﬁnder (Burke et al., 1997), which usually used statistical and semantic similarity measures to rank FAQs.”
Finding similar questions in large question and answer archives (2005, methodology): “Previous research [5] implied that similarities between questions are much more important than the similarity between questions and answers in FAQ retrieval tasks.”
Semantic Matching in Search (2014, background): “These include collaborative filtering [101, 1, 2, 102, 45, 149, 9, 44], image annotation [83, 76, 159], paraphrasing and textual entailment [62, 54, 139, 203, 55, 85, 165, 35], question answering [37, 126, 21, 205, 178, 130], cross-language information retrieval [64, 141, 140], short text conversati”