Matches in SemOpenAlex for { <https://semopenalex.org/work/W2116796754> ?p ?o ?g. }
- W2116796754 abstract "Retrieving information from archived meetings is a new domain of information retrieval that has received increasing attention in the past few years. Search in spontaneous spoken conversations has been recognized as more difficult than text-based document retrieval because meeting discussions contain two levels of information: the content itself, i.e. what topics are discussed, but also the argumentation process, i.e. what conflicts are resolved and what decisions are made. To capture the richness of information in meetings, current research focuses on recording meetings in Smart-Rooms, transcribing meeting discussion into text and annotating discussion with semantic higher-level structures to allow for efficient access to the data. However, it is not yet clear what type of user interface is best suited for searching and browsing such archived, annotated meetings. Content-based retrieval with keyword search is too naive and does not take into account the semantic annotations on the data. The objective of this thesis is to assess the feasibility and usefulness of a natural language interface to meeting archives that allows users to ask complex questions about meetings and retrieve episodes of meeting discussions based on semantic annotations. The particular issues that we address are: the need of argumentative annotation to answer questions about meetings; the linguistic and domain-specific natural language understanding techniques required to interpret such questions; and the use of visual overviews of meeting annotations to guide users in formulating questions. To meet the outlined objectives, we have annotated meetings with argumentative structure and built a prototype of a natural language understanding engine that interprets questions based on those annotations. Further, we have performed two sets of user experiments to study what questions users ask when faced with a natural language interface to annotated meeting archives. For this, we used a simulation method called Wizard of Oz, to enable users to express questions in their own terms without being influenced by limitations in speech recognition technology. Our experimental results show that technically it is feasible to annotate meetings and implement a deep-linguistic NLU engine for questions about meetings, but in practice users do not consistently take advantage of these features. Instead they often search for keywords in meetings. When visual overviews of the available annotations are provided, users refer to those annotations in their questions, but the complexity of questions remains simple. Users search with a breadth-first approach, asking questions in sequence instead of a single complex question. We conclude that natural language interfaces to meeting archives are useful, but that more experimental work is needed to find ways to incent users to take advantage of the expressive power of natural language when asking questions about meetings." @default.
- W2116796754 created "2016-06-24" @default.
- W2116796754 creator A5058600660 @default.
- W2116796754 date "2009-01-01" @default.
- W2116796754 modified "2023-09-23" @default.
- W2116796754 title "Answering questions about archived, annotated meetings" @default.
- W2116796754 cites W100538900 @default.
- W2116796754 cites W1230512944 @default.
- W2116796754 cites W135396087 @default.
- W2116796754 cites W143713808 @default.
- W2116796754 cites W1503312748 @default.
- W2116796754 cites W1504698761 @default.
- W2116796754 cites W1515572669 @default.
- W2116796754 cites W1528193223 @default.
- W2116796754 cites W1532070457 @default.
- W2116796754 cites W1541573696 @default.
- W2116796754 cites W1549026077 @default.
- W2116796754 cites W1550326081 @default.
- W2116796754 cites W1550490297 @default.
- W2116796754 cites W1550961984 @default.
- W2116796754 cites W1552775590 @default.
- W2116796754 cites W1558643924 @default.
- W2116796754 cites W1561314976 @default.
- W2116796754 cites W1563702609 @default.
- W2116796754 cites W1571207926 @default.
- W2116796754 cites W1571763272 @default.
- W2116796754 cites W1576632330 @default.
- W2116796754 cites W1580906282 @default.
- W2116796754 cites W158297150 @default.
- W2116796754 cites W1585696536 @default.
- W2116796754 cites W1606044624 @default.
- W2116796754 cites W1634290079 @default.
- W2116796754 cites W171957037 @default.
- W2116796754 cites W177050029 @default.
- W2116796754 cites W1807805269 @default.
- W2116796754 cites W1823390538 @default.
- W2116796754 cites W1861206810 @default.
- W2116796754 cites W1936920915 @default.
- W2116796754 cites W1965521964 @default.
- W2116796754 cites W1972051027 @default.
- W2116796754 cites W1975871650 @default.
- W2116796754 cites W1976770038 @default.
- W2116796754 cites W1982678125 @default.
- W2116796754 cites W1985289501 @default.
- W2116796754 cites W1985340780 @default.
- W2116796754 cites W1985955841 @default.
- W2116796754 cites W1989182840 @default.
- W2116796754 cites W1990070937 @default.
- W2116796754 cites W1992601293 @default.
- W2116796754 cites W1992700935 @default.
- W2116796754 cites W1993651423 @default.
- W2116796754 cites W2002616384 @default.
- W2116796754 cites W2004322557 @default.
- W2116796754 cites W2008742021 @default.
- W2116796754 cites W2013013717 @default.
- W2116796754 cites W2013489329 @default.
- W2116796754 cites W2024557736 @default.
- W2116796754 cites W2028065606 @default.
- W2116796754 cites W203241404 @default.
- W2116796754 cites W2038721957 @default.
- W2116796754 cites W2040326218 @default.
- W2116796754 cites W2041939855 @default.
- W2116796754 cites W2042159198 @default.
- W2116796754 cites W2042654006 @default.
- W2116796754 cites W2043549431 @default.
- W2116796754 cites W2050492193 @default.
- W2116796754 cites W2051167396 @default.
- W2116796754 cites W2051251368 @default.
- W2116796754 cites W2054503539 @default.
- W2116796754 cites W2056818712 @default.
- W2116796754 cites W2058169200 @default.
- W2116796754 cites W2059320277 @default.
- W2116796754 cites W2067399745 @default.
- W2116796754 cites W2070078620 @default.
- W2116796754 cites W2084742446 @default.
- W2116796754 cites W2090106457 @default.
- W2116796754 cites W2091546239 @default.
- W2116796754 cites W2091894984 @default.
- W2116796754 cites W2092795326 @default.
- W2116796754 cites W2098217544 @default.
- W2116796754 cites W2098772089 @default.
- W2116796754 cites W2099587687 @default.
- W2116796754 cites W2101382042 @default.
- W2116796754 cites W2102518549 @default.
- W2116796754 cites W2103721161 @default.
- W2116796754 cites W2104038318 @default.
- W2116796754 cites W2105508197 @default.
- W2116796754 cites W2105989239 @default.
- W2116796754 cites W2106121453 @default.
- W2116796754 cites W2106918957 @default.
- W2116796754 cites W2112136322 @default.
- W2116796754 cites W2112383723 @default.
- W2116796754 cites W2113007466 @default.
- W2116796754 cites W2117092977 @default.
- W2116796754 cites W2117448986 @default.
- W2116796754 cites W2117488952 @default.
- W2116796754 cites W2121350579 @default.
- W2116796754 cites W2122254380 @default.
- W2116796754 cites W2128970689 @default.
- W2116796754 cites W2129116492 @default.