FALCON: Boosting Knowledge for Answer Engines

By Sanda M. Harabagiu, Dan I. Moldovan, Marius Pasca, Rada Mihalcea, Mihai Surdeanu, Razvan C. Bunescu, Roxana Girju, Vasile Rus, Paul Morarescu. Text Retrieval Conference, 2000

339 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2f6c079bc68b93e7d0934a0b88c2105a2e39e040

How researchers see this paper

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

Citations in the corpus

Adaptive Document Retrieval for Deep Question Answering (2018, methodology): “On the other hand, QA system incorporate a document retrieval module which selects candidate documents based on a chosen similarity metric, while a subsequent module then processes these in order to extract the answer (e. g. Cao et al., 2011; Harabagiu et al., 2000).”
Open Domain Question Answering via Semantic Enrichment (2015, background): “, [22, 24]), systems like Mulder [26] and AskMSR [7] take a different path by leveraging the crowd knowledge from the Web.”
Open-domain textual question answering techniques (2003, methodology): “This section introduces an alternative answer extraction method based on simple machine learning technique, also exhibited in FALCON (Harabagiu et al. 2000b).”
Learning from On-Line User Feedback in Neural Question Answering on the Web (2019, result): “This is in contrast to QA for knowledge bases, where a key objective involves building up the knowledge base itself [12, 16], as well as continuously updating the underlying decision rules for answering [2].”
BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network (2012, background): “These include, among others, text summarization [82], named entity disambiguation [16], Question Answering [48,66], text categorization [40,130,88], coreference resolution [107,111], sentiment analysis [125, 129] and plagiarism detection [10].”
A Probabilistic Classification Approach for Lexical Textual Entailment (2005, background): “In some QA systems, (Harabagiu et al., 2000; Kwok et al., 2001; Hovy et al., 2001) there is no clear weighting scheme for the lexical expansion, and expanded words are added equally to a Boolean retrieval search of candidate answer texts.”
A survey on question answering technology from an information retrieval perspective (2011, unknown): “[45] presented a WordNet-based taxonomy of classes.”
Learning question classifiers: the role of semantic information (2005, methodology): “This remains true even if external knowledge bases (e.g. WordNet (Fellbaum 1998)) are exploited to partially automate the mapping from word-level information to question classes (Harabagiu et al. 2000; Hermjakob 2001).”
Learning Question Classifiers (2002, methodology): “Performance of the hierarchical classifier Table 2 shows the P 5 precision of the hierarchical classifier when trained on 5,500 examples and tested on the 500 TREC 10 questions.”
BabelNet: Building a Very Large Multilingual Semantic Network (2010, background): “These include, among others, text summarization (Nastase, 2008), Named Entity Recognition (Bunescu and Paşca, 2006), Question Answering (Harabagiu et al., 2000) and text categorization (Gabrilovich and Markovitch, 2006).”
What’s in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams (2016, methodology): “Factoid QA systems use classifiers to identify the types of question and expected answers, which are subsequently used to select specific problem solving routines, and to filter answer candidates (Harabagiu et al., 2000; Li and Roth, 2006; Roberts and Hickl, 2008).”