Báo cáo khoa học: "Generating Image Descriptions From Computer Vision Detections" pptx

... natural- sounding descriptions from computer vision de- tections. This commonality is our starting point: We aim to design a system capable of producing natural-sounding descriptions from computer vi- sion ... descrip- tions of images from computer vision de- tections. By leveraging syntactically in- formed word co-occurrence statistics, the generator filters and constrains...

Ngày tải lên: 31/03/2014, 21:20

... 310 images from our image set (see Section 4.1) to train the weights. The image descriptions from this data set are used as model summaries. Our training data contains for each image a set of image ... image a set of image descriptions taken from the Virtual- Tourist travel community web-site 4 . From this web-site we took all existing image descriptions about a pa...

Ngày tải lên: 30/03/2014, 21:20

... accompanied with ar- gument mappings taken from FrameNet. 3 Rule Extraction from FrameNet The above prior work identified lexical entailment relations mainly from WordNet, which limits the use of FrameNet ... 2002). LexPar Rules are generated from the publicly available LexPar database. We generated unary rules from each LexPar rule based on a manually constructed mapping from Fram...

Ngày tải lên: 17/03/2014, 00:20

... also identify related songs from the internet, including: other songs from the same al- bum, popular songs of the artist and popular songs of related artists, as obtained from Yahoo Music. c) The ... base form from the original verb or noun, so that YAG can generate grammatical sentences. Figure 5 shows the regenerated review from Fig- ure 1. YAG regenerates as many f-sentences fro...

Ngày tải lên: 20/02/2014, 04:20

... 393–400, Sydney, July 2006. c 2006 Association for Computational Linguistics Learning Event Durations from Event Descriptions Feng Pan, Rutu Mulkar, and Jerry R. Hobbs Information Sciences Institute ... instances), from the TimeBank corpus annotated in TimeML (Pustejovky et al., 2003). The non- WSJ articles (mainly political and disaster news) include both print and broadcast...

Ngày tải lên: 20/02/2014, 12:20

... first, from the ex- tended domain of locality which makes TAG par- ticularly suitable for generation (cf. (Joshi, 1987)) and second, from the monotonicity which differ- entiates descriptions from ... Grammars There is a range of grammar formalisms which depart from Tree Adjoining Grammar (TAG) by taking as basic building blocks tree descriptions rather than trees. D-Tree Grammar (D...

Ngày tải lên: 20/02/2014, 18:20

... our general corpora to produce three different models: GSLCLM from the GSLC corpus, NewsLM from the newspaper corpus and DomNewsLM from the domain adapted newspaper Corpus. 3.1 Interpolating the ... speech recognition grammar compiled from the same GF interpretation grammar. The results show a relative Word Error Rate (WER) reduction of 37% for the SLM derived from the interpretatio...

Ngày tải lên: 22/02/2014, 02:20

... Generating Spatio-Temporal Descriptions in Pollen Forecasts Ross Turner, Somayajulu Sripada and Ehud Reiter Dept of Computing ... written pollen reports which our industrial collab- orator has provided for a local commercial television station. The forecasts were written by two expert mete- orologists, one of whom provided ... Due to the fact that we are modeling the task of automatically p...

Ngày tải lên: 08/03/2014, 21:20

... Natural Lan- guage descriptions of the output of a database enquiry program. The system uses a two level model of semantics. The possibility of alterna- tive descriptions arises from the mapping ... (from now on the term "event" will cover both these), for which it provides some parameter. Thus, the origin of a flight could be described by saying that the plane "...

Ngày tải lên: 09/03/2014, 01:20

... of the objects the speaker is referring to. From the generation perspective, this means that, starting from the set of objects to be described and from the properties known to hold of these objects by ... overspecified descriptions. It has often been observed that human beings produce overspecified i.e., non-minimal descriptions. One might therefore wonder whether generating minimal de...

Ngày tải lên: 17/03/2014, 08:20