Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209748596> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3209748596 abstract "Frequently Asked Questions (FAQ) are a form of semi-structured data that provides users with commonly requested information and enables several natural language processing tasks. Given the plethora of such question-answer pairs on the Web, there is an opportunity to automatically build large FAQ collections for any domain, such as COVID-19 or Plastic Surgery. These collections can be used by several information-seeking portals and applications, such as AI chatbots. Automatically identifying and extracting such high-utility question-answer pairs is a challenging endeavor, which has been tackled by little research work. For a question-answer pair to be useful to a broad audience, it must (i) provide general information -- not be specific to the Web site or Web page where it is hosted -- and (ii) must be self-contained -- not have references to other entities in the page or missing terms (ellipses) that render the question-answer pair ambiguous. Although identifying general, self-contained questions may seem like a straightforward binary classification problem, the limited availability of training data for this task and the countless domains make building machine learning models challenging. Existing efforts in extracting FAQs from the Web typically focus on FAQ retrieval without much regard to the utility of the extracted FAQ. We propose QuAX: a framework for extracting high-utility (i.e., general and self-contained) domain-specific FAQ lists from the Web. QuAX receives a set of keywords from a user, and works in a pipelined fashion to find relevant web pages and extract general and self-contained questions-answer pairs. We experimentally show how QuAX generates high-utility FAQ collections with little and domain-agnostic training data, and how the individual stages of the pipeline improve on the corresponding state-of-the-art." @default.
- W3209748596 created "2021-11-08" @default.
- W3209748596 creator A5029121532 @default.
- W3209748596 creator A5045236138 @default.
- W3209748596 creator A5089254754 @default.
- W3209748596 date "2021-10-26" @default.
- W3209748596 modified "2023-10-13" @default.
- W3209748596 title "QuAX" @default.
- W3209748596 cites W2115186633 @default.
- W3209748596 cites W2122354955 @default.
- W3209748596 cites W2124814993 @default.
- W3209748596 cites W2146537661 @default.
- W3209748596 cites W2169863116 @default.
- W3209748596 cites W2512626121 @default.
- W3209748596 cites W2517194566 @default.
- W3209748596 cites W2604700393 @default.
- W3209748596 cites W2793336985 @default.
- W3209748596 cites W2805975048 @default.
- W3209748596 cites W2889157686 @default.
- W3209748596 cites W2899828811 @default.
- W3209748596 cites W2899992227 @default.
- W3209748596 cites W2911857455 @default.
- W3209748596 cites W2945465473 @default.
- W3209748596 cites W2949671220 @default.
- W3209748596 cites W2956105129 @default.
- W3209748596 cites W2997894965 @default.
- W3209748596 cites W3000983017 @default.
- W3209748596 cites W3023597667 @default.
- W3209748596 cites W3034937228 @default.
- W3209748596 cites W3099309639 @default.
- W3209748596 cites W3102971065 @default.
- W3209748596 cites W3146259567 @default.
- W3209748596 cites W3149154678 @default.
- W3209748596 cites W1981444063 @default.
- W3209748596 doi "https://doi.org/10.1145/3459637.3482289" @default.
- W3209748596 hasPublicationYear "2021" @default.
- W3209748596 type Work @default.
- W3209748596 sameAs 3209748596 @default.
- W3209748596 citedByCount "0" @default.
- W3209748596 crossrefType "proceedings-article" @default.
- W3209748596 hasAuthorship W3209748596A5029121532 @default.
- W3209748596 hasAuthorship W3209748596A5045236138 @default.
- W3209748596 hasAuthorship W3209748596A5089254754 @default.
- W3209748596 hasBestOaLocation W32097485961 @default.
- W3209748596 hasConcept C120665830 @default.
- W3209748596 hasConcept C121332964 @default.
- W3209748596 hasConcept C134306372 @default.
- W3209748596 hasConcept C136764020 @default.
- W3209748596 hasConcept C162324750 @default.
- W3209748596 hasConcept C177264268 @default.
- W3209748596 hasConcept C187736073 @default.
- W3209748596 hasConcept C192209626 @default.
- W3209748596 hasConcept C199360897 @default.
- W3209748596 hasConcept C21959979 @default.
- W3209748596 hasConcept C23123220 @default.
- W3209748596 hasConcept C2780451532 @default.
- W3209748596 hasConcept C3018615553 @default.
- W3209748596 hasConcept C33923547 @default.
- W3209748596 hasConcept C36503486 @default.
- W3209748596 hasConcept C41008148 @default.
- W3209748596 hasConcept C44291984 @default.
- W3209748596 hasConcept C509550671 @default.
- W3209748596 hasConcept C71924100 @default.
- W3209748596 hasConceptScore W3209748596C120665830 @default.
- W3209748596 hasConceptScore W3209748596C121332964 @default.
- W3209748596 hasConceptScore W3209748596C134306372 @default.
- W3209748596 hasConceptScore W3209748596C136764020 @default.
- W3209748596 hasConceptScore W3209748596C162324750 @default.
- W3209748596 hasConceptScore W3209748596C177264268 @default.
- W3209748596 hasConceptScore W3209748596C187736073 @default.
- W3209748596 hasConceptScore W3209748596C192209626 @default.
- W3209748596 hasConceptScore W3209748596C199360897 @default.
- W3209748596 hasConceptScore W3209748596C21959979 @default.
- W3209748596 hasConceptScore W3209748596C23123220 @default.
- W3209748596 hasConceptScore W3209748596C2780451532 @default.
- W3209748596 hasConceptScore W3209748596C3018615553 @default.
- W3209748596 hasConceptScore W3209748596C33923547 @default.
- W3209748596 hasConceptScore W3209748596C36503486 @default.
- W3209748596 hasConceptScore W3209748596C41008148 @default.
- W3209748596 hasConceptScore W3209748596C44291984 @default.
- W3209748596 hasConceptScore W3209748596C509550671 @default.
- W3209748596 hasConceptScore W3209748596C71924100 @default.
- W3209748596 hasLocation W32097485961 @default.
- W3209748596 hasOpenAccess W3209748596 @default.
- W3209748596 hasPrimaryLocation W32097485961 @default.
- W3209748596 hasRelatedWork W11039624 @default.
- W3209748596 hasRelatedWork W12649326 @default.
- W3209748596 hasRelatedWork W15548 @default.
- W3209748596 hasRelatedWork W3614407 @default.
- W3209748596 hasRelatedWork W4135815 @default.
- W3209748596 hasRelatedWork W4496226 @default.
- W3209748596 hasRelatedWork W6865571 @default.
- W3209748596 hasRelatedWork W8067167 @default.
- W3209748596 hasRelatedWork W9224363 @default.
- W3209748596 hasRelatedWork W11962574 @default.
- W3209748596 isParatext "false" @default.
- W3209748596 isRetracted "false" @default.
- W3209748596 magId "3209748596" @default.
- W3209748596 workType "article" @default.