Retrieval models for question and answer archives

By Xiaobing Xue, Jiwoon Jeon, W. Bruce Croft. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2008

396 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/942cfcdcdde2c90c0650c43c54cb4b8cb572373f

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

Citations in the corpus

IRIS: a Chat-oriented Dialogue System based on the Vector Space Model (2012, background): “Different from example-based question answering systems (Vicedo, 2002; Xue et al. , 2008), IRIS uses a dual search strategy.”
Latent Semantic Tensor Indexing for Community-based Question Answering (2013, methodology): “We compare our method with two baseline methods: Okapi BM25 and LSI and two state-of-the-art methods: (Jeon et al., 2005b)(Xue et al., 2008).”
Entity based Q&A Retrieval (2012, methodology): “Following (Xue et al., 2008) we pool the question and answers from D to create a master parallel corpus P = ( q 1 , a 1 ) , .., ( q n , a n ) ∪ ( a 1 , q 1 ) , ., ( a n , q n ) .”
Convolutional Neural Tensor Network Architecture for Community-Based Question Answering (2015, methodology): “We use the mean average precision (MAP) and P @10 to evaluate the effectiveness of each method, which are widely used in question retrieval [Jeon et al., 2005; Xue et al., 2008; Zhou et al., 2011].”
Convolutional Neural Network Architectures for Matching Natural Language Sentences (2014, background): “Matching two potentially heterogenous language objects is central to many natural language applications [28, 2].”
Answer Interaction in Non-factoid Question Answering Systems (2019, background): “Substantial work has been done in factoid QA [9, 22, 34, 37, 38], community QA [10, 24, 24, 25, 32, 33], and non-factoid QA [5, 11, 18, 35].”
Clickthrough-based translation models for web search: from word models to phrase models (2010, methodology): “This problem has also been studied in [36, 20, 24, 21].”
Learning Continuous Word Embedding with Metadata for Question Retrieval in Community Question Answering (2015, methodology): “Xue et al. (2008) proposed a word-based translation language model for question retrieval.”
Estimation of statistical translation models based on mutual information for ad hoc information retrieval (2010, methodology): “As a result, translation language models have been successfully applied to diﬀerent tasks such as cross-lingual information retrieval [12, 20, 39], question answering [40], sentence retrieval [19], and tracking information ﬂow [18].”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “Differently from the features derived from translation-based language models [183], which extract knowledge from q/a pairs, topic models use the distribution of words over the entire collection.”
Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System (2019, background): “This task is formalized as a text matching problem (Xue et al., 2008).”
FAQ-based Question Answering via Word Alignment (2015, methodology): “Another method treated this task as a statistical machine translation problem, and employed a parallel question set to learn word-to-word or phrase-to-phrase translation probabilities (Berger and Lafferty, 1999; Jeon et al., 2005; Lee et al., 2008; Xue et al., 2008; Bernhard and Gurevych, 2009; Zhou”
Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQs (2020, background): “tuation such as the currrent COVID-19 pandemic. The problem of matching general unanswered questions with semantically similar answered questions has been well-studied in the contextofonlineuserforums[7,9,11,27],communityQA[8,16,29] and question answer archives [15, 16]. Typical approaches either as”
An Information Retrieval Approach to Short Text Conversation (2014, methodology): “To alleviate the lexical gap problem, we employ the state-of-the-art translation-based language model (TransLM) (Xue et al., 2008) with a small modiﬁcation for retrieval-based STC.”
Text Matching as Image Recognition (2016, background): “Matching two texts is central to many natural language applications, such as machine translation (Brown et al. 1993), question and answering (Xue, Jeon, and Croft 2008), paraphrase identiﬁcation (Socher et al. 2011) and document retrieval (Li and Xu 2014).”