Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 4 of 4 for “"Bi-Encoder"”.
-
A Bi-Encoder LSTM Model for Learning Unstructured Dialogs
… Recurrent Neural Network (RNN) and a Dual Encoder (DE) based on Long Short Term Memory (LSTM) model suitable to learn from the Ubuntu Dialog Corpus Version 1 (UDCv1). We use this same architecture but on UDCv2 as a benchmark and introduce a new LSTM based architecture called the Bi-Encoder …
-
Building a Robust Retrieval System with Dense Retrieval Models
… and languages, limiting their broader applicability. As an alternative, dense–sparse fusion and multi-vector bi-encoder retrieval models have been shown to capture both semantic and lexical features, demonstrating superior retrieval robustness. However, these designs introduce increased query …
-
Pretrained Transformers for Efficient and Robust Information Retrieval
… followed by task-aware finetuning, the encoder-only BERT effectively captures the complex semantics of texts and overcomes the limitations of traditional bag-of-words systems like BM25, addressing the lexical mismatch between queries and documents. The successor models based on …
-
Massively Multilingual Vision-Language Understanding
… Their success lies in the alignment of a visual encoder and a Large Language Model (LLM) that were both pretrained on massive datasets. Through this pretraining, the visual encoder learns rich representations of diverse images while the LLM acquires the ability to understand complex instructions …