Toward a Formal Theory of Information Structure

Hobbs, Jerry R.; Mulkar-Mehta, Rutu

doi:10.1007/978-3-642-34997-3_6

Cited by 1 publication

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For joint parsing of video and text, Hobbs and Mulkar-Mehta [38] described a preliminary framework that interprets the combination of video and text from news broadcasts, which is the work most closely related to ours. Compared with their work, our system extracts information directly from the raw data of video and text, and relies on a probabilistic generative model to handle uncertainty; besides, we have done comprehensive experiments to evaluate our system.…”

Section: Parsing Based Approachesmentioning

confidence: 99%

Joint Video and Text Parsing for Understanding Events and Answering Queries

Meng

Lee

et al. 2014

IEEE MultiMedia

View full text Add to dashboard Cite

We propose a framework for parsing video and text jointly for understanding events and answering user queries. Our framework produces a parse graph that represents the compositional structures of spatial information (objects and scenes), temporal information (actions and events) and causal information (causalities between events and fluents) in the video and text. The knowledge representation of our framework is based on a spatial-temporal-causal And-Or graph (S/T/C-AOG), which jointly models possible hierarchical compositions of objects, scenes and events as well as their interactions and mutual contexts, and specifies the prior probabilistic distribution of the parse graphs. We present a probabilistic generative model for joint parsing that captures the relations between the input video/text, their corresponding parse graphs and the joint parse graph. Based on the probabilistic model, we propose a joint parsing system consisting of three modules: video parsing, text parsing and joint inference. Video parsing and text parsing produce two parse graphs from the input video and text respectively. The joint inference module produces a joint parse graph by performing matching, deduction and revision on the video and text parse graphs. The proposed framework has the following objectives: Firstly, we aim at deep semantic parsing of video and text that goes beyond the traditional bag-of-words approaches; Secondly, we perform parsing and reasoning across the spatial, temporal and causal dimensions based on the joint S/T/C-AOG representation; Thirdly, we show that deep joint parsing facilitates subsequent applications such as generating narrative text descriptions and answering queries in the forms of who, what, when, where and why. We empirically evaluated our system based on comparison against groundtruth as well as accuracy of query answering and obtained satisfactory results.

show abstract

Section: Parsing Based Approachesmentioning

confidence: 99%