Matches in ScholarlyData for { ?s ?p ?o. }
- item-4 type ListItem.
- item-4 hasContent enrico-motta.
- item-4 previous item-3.
- 238 creator filip-ilievski.
- 238 creator laurens-rietveld.
- 238 creator marieke-van-erp.
- 238 creator stefan-schlobach.
- 238 creator wouter-beek.
- 238 type InProceedings.
- 238 label "LOTUS: Adaptive Text Search for Big Linked Data".
- 238 sameAs 238.
- 238 abstract "Finding relevant resources on the Semantic Web today is a dirty job: there is no centralized lookup service and the support for natural language lookup is limited. In this paper, we present LOTUS: Linked Open Text UnleaShed, a natural language entry point to a massive subset of today's Linked Open Data Cloud. While a wide array of matching and ranking algorithms have been studied, there is no ultimate combination of matching and ranking that will work for every use case. LOTUS recognizes the case-dependent nature of resource retrieval by allowing users to choose from a wide palette of well-known matching and ranking algorithms. LOTUS is an adaptive toolkit that allows user to easily construct the form of resource retrieval that suits her use case best. In this paper, we explain the LOTUS approach, its implementation and the functionality it provides. We also demonstrate the ease with which LOTUS allows Linked Data to be queried at an unprecedented scale in different concrete and domain-specific scenarios. Finally we demonstrate the scalability of LOTUS with respect to the LOD Laundromat data, the biggest collection of easily accessible Linked Data currently available.".
- 238 hasAuthorList authorList.
- 238 isPartOf proceedings.
- 238 title "LOTUS: Adaptive Text Search for Big Linked Data".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent filip-ilievski.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent wouter-beek.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent marieke-van-erp.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent laurens-rietveld.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent stefan-schlobach.
- item-5 previous item-4.
- 241 creator adarsh-alex.
- 241 creator amit-sheth.
- 241 creator krishnaprasad-thirunarayan.
- 241 creator pablo-mendes.
- 241 creator sujan-perera.
- 241 type InProceedings.
- 241 label "Implicit Entity Linking in Tweets".
- 241 sameAs 241.
- 241 abstract "Over the years, Twitter has become one of the largest communication platforms providing key data to various applications such as brand monitoring, trend detection, among others. Natural language understanding from tweets is particularly difficult due to prevalent short length and unconventional grammar. Entity linking associates text to knowledge bases in order to provide unambiguous references and additional context to help with understanding. State-of-the-art techniques have focused on linking explicitly mentioned entities on tweets with reasonable success. However, we argue that in addition to explicit mentions -- i.e. `You guys have no idea how wet the movie Gravity makes me' -- entities (movie Gravity) can also be mentioned implicitly -- i.e. `This new space movie is crazy. you must watch it!'. This paper introduces the problem of implicit entity linking in tweets. We propose an approach that models the entities by exploiting their factual and contextual knowledge. We demonstrate how to use these models to perform implicit entity linking on a ground truth dataset with 400 tweets from two domains, namely, movie and book. Specifically, we show: 1) the value of performing implicit entity linking along with explicit entity linking task, and the importance of exploiting contextual knowledge of an entity in linking their implicit mentions on tweets.".
- 241 hasAuthorList authorList.
- 241 isPartOf proceedings.
- 241 title "Implicit Entity Linking in Tweets".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent sujan-perera.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent pablo-mendes.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent adarsh-alex.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent amit-sheth.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent krishnaprasad-thirunarayan.
- item-5 previous item-4.
- 243 creator adam-barker.
- 243 creator ewan-klein.
- 243 creator paolo-pareti.
- 243 type InProceedings.
- 243 label "Linking Data, Services, and Human Know-How".
- 243 sameAs 243.
- 243 abstract "An increasing number of everyday tasks involve a mixture of human actions and machine computation. This paper presents the first framework that allows non-programmer users to create and execute workflows where each task can be completed by a human or a machine. In this framework, humans and machines interact through a shared knowledge base which is both human and machine understandable. This knowledge base is based on the PROHOW Linked Data vocabulary that can represent human instructions and link them to machine functionalities. Our hypothesis is that non-programmer users can describe how to achieve certain tasks at a level of abstraction which is both human and machine understandable. This paper presents the PROHOW vocabulary and describes its usage within the proposed framework. We substantiate our claim with a concrete implementation of our framework and by experimental evidence.".
- 243 hasAuthorList authorList.
- 243 isPartOf proceedings.
- 243 title "Linking Data, Services, and Human Know-How".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent paolo-pareti.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent ewan-klein.