Sökning: "Deep structured semantic model"

Hittade 2 uppsatser innehållade orden Deep structured semantic model.

1. 1. There’s a Microwave in the Hallway

   Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

   Författare :Yasmeen Emampoor; [2022-04-20]
   Nyckelord :embodied question answering; visual question answering; multi-modality; information fusion;

   Sammanfattning : Embodied Question Answering (EQA) is a task in which an agent situated in virtual environment navigates from its current position to an object (Navigation), and then answer a question about it (Visual Question Answering, VQA), for example “What color is the table in the table in the kitchen?” This project examines how an agent modelled as a deep neural network uses semantic information from its language model and visual information to answer questions in the second task. This is important since due to the regular nature of the task and the dataset it could be that the model is answering questions purely based on general semantic information from its language model (tables are frequently brown) and not relying on the visual scene, a phenomenon that is commonly known as hallucinating. LÄS MER

3. 2. Transfer Learning in Deep Structured Semantic Models for Information Retrieval

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Sahand Zarrinkoub; [2020]
   Nyckelord :Deep learning; Deep structured semantic model; information retrieval; machine learning; natural langugange processing; neural information retrieval; Djupinlärning; informationssökning; maskininlärning; språkteknologi; neurala sökmotorer;

   Sammanfattning : Recent approaches to IR include neural networks that generate query and document vector representations. The representations are used as the basis for document retrieval and are able to encode semantic features if trained on large datasets, an ability that sets them apart from classical IR approaches such as TF-IDF. LÄS MER