scholarly journals Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance

2021 ◽  
Author(s):  
Jingtao Zhan ◽  
Jiaxin Mao ◽  
Yiqun Liu ◽  
Jiafeng Guo ◽  
Min Zhang ◽  
...  
Keyword(s):  
Retrieval Performance ◽  
Product Quantization

scholarly journals Adversarial Attack on Deep Product Quantization Network for Image Retrieval

2020 ◽  
Vol 34 (07) ◽  
pp. 10786-10793 ◽  
Author(s):  
Yan Feng ◽  
Bin Chen ◽  
Tao Dai ◽  
Shu-Tao Xia
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Visual Features ◽  
Retrieval Performance ◽  
Retrieval Models ◽  
Product Quantization ◽  
Security Issues ◽  
Retrieval Systems ◽  
Adversarial Examples ◽  
Adversarial Attack

Deep product quantization network (DPQN) has recently received much attention in fast image retrieval tasks due to its efficiency of encoding high-dimensional visual features especially when dealing with large-scale datasets. Recent studies show that deep neural networks (DNNs) are vulnerable to input with small and maliciously designed perturbations (a.k.a., adversarial examples). This phenomenon raises the concern of security issues for DPQN in the testing/deploying stage as well. However, little effort has been devoted to investigating how adversarial examples affect DPQN. To this end, we propose product quantization adversarial generation (PQ-AG), a simple yet effective method to generate adversarial examples for product quantization based retrieval systems. PQ-AG aims to generate imperceptible adversarial perturbations for query images to form adversarial queries, whose nearest neighbors from a targeted product quantizaiton model are not semantically related to those from the original queries. Extensive experiments show that our PQ-AQ successfully creates adversarial examples to mislead targeted product quantization retrieval models. Besides, we found that our PQ-AG significantly degrades retrieval performance in both white-box and black-box settings.

Semantic Search on Unstructured Data

2010 ◽  
Vol 6 (2) ◽  
pp. 17-35 ◽  
Author(s):  
Alex Kohn ◽  
François Bry ◽  
Alexander Manta
Keyword(s):  
Retrieval System ◽  
Pharmaceutical Research ◽  
Information Retrieval System ◽  
Semantic Search ◽  
Unstructured Data ◽  
Search Performance ◽  
Adaptive Search ◽  
Retrieval Performance ◽  
Enterprise Search ◽  
Existing Data

Studies agree that searchers are often not satisfied with the performance of current enterprise search engines. As a consequence, more scientists worldwide are actively investigating new avenues for searching to improve retrieval performance. This paper contributes to YASA (Your Adaptive Search Agent), a fully implemented and thoroughly evaluated ontology-based information retrieval system for the enterprise. A salient particularity of YASA is that large parts of the ontology are automatically filled with facts by recycling and transforming existing data. YASA offers context-based personalization, faceted navigation, as well as semantic search capabilities. YASA has been deployed and evaluated in the pharmaceutical research department of Roche, Penzberg, and results show that already semantically simple ontologies suffice to considerably improve search performance.

scholarly journals Technological troubleshooting based on sentence embedding with deep transformers

2021 ◽  
Author(s):  
Antonio L. Alfeo ◽  
Mario G. C. A. Cimino ◽  
Gigliola Vaglini
Keyword(s):  
Technical Assistance ◽  
State Of The Art ◽  
Semantic Context ◽  
Retrieval Performance ◽  
Private Company ◽  
Textual Data ◽  
Context Knowledge ◽  
Development And Management ◽  
Preparation Module ◽  
Semantic Textual Similarity

AbstractIn nowadays manufacturing, each technical assistance operation is digitally tracked. This results in a huge amount of textual data that can be exploited as a knowledge base to improve these operations. For instance, an ongoing problem can be addressed by retrieving potential solutions among the ones used to cope with similar problems during past operations. To be effective, most of the approaches for semantic textual similarity need to be supported by a structured semantic context (e.g. industry-specific ontology), resulting in high development and management costs. We overcome this limitation with a textual similarity approach featuring three functional modules. The data preparation module provides punctuation and stop-words removal, and word lemmatization. The pre-processed sentences undergo the sentence embedding module, based on Sentence-BERT (Bidirectional Encoder Representations from Transformers) and aimed at transforming the sentences into fixed-length vectors. Their cosine similarity is processed by the scoring module to match the expected similarity between the two original sentences. Finally, this similarity measure is employed to retrieve the most suitable recorded solutions for the ongoing problem. The effectiveness of the proposed approach is tested (i) against a state-of-the-art competitor and two well-known textual similarity approaches, and (ii) with two case studies, i.e. private company technical assistance reports and a benchmark dataset for semantic textual similarity. With respect to the state-of-the-art, the proposed approach results in comparable retrieval performance and significantly lower management cost: 30-min questionnaires are sufficient to obtain the semantic context knowledge to be injected into our textual search engine.

Sign in / Sign up

Export Citation Format

Share Document