Веб-поиск
Related Papers
Clustering Similar Query Sessions Toward Interactive Web Search
A new effective log-based approach for interactive Web search is presented in this paper. The most important feature of the proposed approach is that the suggested terms corresponding to the …...
Probabilistic Inference for Cold Start Knowledge Base Population with Prior World Knowledge
AbstractBuilding knowledge bases (KB) automatically from text corpora is crucial for many applications such as question answering and web search. The problem is very challenging and has been divided into …...
Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities
AbstractBreaking domain names such as openresearch into component words open and research is important for applications like Text-to-Speech synthesis and web search. We link this problem to the classic problem …...
Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder
AbstractDense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output …...
Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives
AbstractIn this paper, we investigate the instability in the standard dense retrieval training, which iterates between model training and hard negative selection using the being-trained model. We show the catastrophic …...
RARR: Researching and Revising What Language Models Say, Using Language Models
AbstractLanguage models (LMs) now excel at many tasks such as question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their …...