Neural Embedding-Based Metrics for Pre-retrieval Query Performance Prediction

10.32920/ryerson.14654253 ◽

2021 ◽

Author(s):

Arabzadehghahyazi Negar

Keyword(s):

Performance Prediction ◽

State Of The Art ◽

Learning To Rank ◽

The State ◽

Test Collection ◽

Query Performance ◽

Performance Predictors ◽

Level Statistics ◽

Ablation Study ◽

Individual Specificity

file:///C:/Users/MWF/Downloads/Arabzadehghahyazi, Negar.Pre-retrieval Query Performance Prediction (QPP) methods are oblivious to the performance of the retrieval model as they predict query difficulty prior to observing the set of documents retrieved for the query. Among pre-retrieval query performance predictors, specificity-based metrics investigate how corpus, query and corpus-query level statistics can be used to predict the performance of the query. In this thesis, we explore how neural embeddings can be utilized to define corpus-independent and semantics-aware specificity metrics. Our metrics are based on the intuition that a term that is closely surrounded by other terms in the embedding space is more likely to be specific while a term surrounded by less closely related terms is more likely to be generic. On this basis, we leverage geometric properties between embedded terms to define four groups of metrics: (1) neighborhood-based, (2) graph-based, (3) cluster-based and (4) vector-based metrics. Moreover, we employ learning-to-rank techniques to analyze the importance of individual specificity metrics. To evaluate the proposed metrics, we have curated and publicly share a test collection of term specificity measurements defined based on Wikipedia category hierarchy and DMOZ taxonomy. We report on our extensive experiments on the effectiveness of our metrics through metric comparison, ablation study and comparison against the state-of-the-art baselines. We have shown that our proposed set of pre-retrieval QPP metrics based on the properties of pre-trained neural embeddings are more effective for performance prediction compared to the state-of-the-art methods. We report our findings based on Robust04, ClueWeb09 and Gov2 corpora and their associated TREC topics.

Download Full-text

MeSH-Based Semantic Indexing Approach to Enhance Biomedical Information Retrieval

The Computer Journal ◽

10.1093/comjnl/bxaa073 ◽

2020 ◽

Cited By ~ 1

Author(s):

Hager Kammoun ◽

Imen Gabsi ◽

Ikram Amous

Keyword(s):

Information Retrieval ◽

State Of The Art ◽

Research Paper ◽

The State ◽

Test Collection ◽

Semantic Indexing ◽

Effective Strategy ◽

Biomedical Information Retrieval ◽

Content Representation

Abstract Owing to the tremendous size of electronic biomedical documents, users encounter difficulties in seeking useful biomedical information. An efficient and smart access to the relevant biomedical information has become a fundamental need. In this research paper, we set forward a novel biomedical MeSH-based semantic indexing approach to enhance biomedical information retrieval. The proposed semantic indexing approach attempts to strengthen the content representation of both documents and queries by incorporating unambiguous MeSH concepts as well as the adequate senses of ambiguous MeSH concepts. For this purpose, our proposed approach relies on a disambiguation method to identify the adequate senses of ambiguous MeSH concepts and introduces four representation enrichment strategies so as to identify the best appropriate representatives of the adequate sense in the textual entities representation. To prove its effectiveness, the proposed semantic indexing approach was evaluated by intensive experiments. These experiments were carried out on OHSUMED test collection. The results reveal that our proposal outperforms the state-of-the-art approaches and allow us to highlight the most effective strategy.

Download Full-text

A Recurrent Model for Collective Entity Linking with Adaptive Features

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i01.5367 ◽

2020 ◽

Vol 34 (01) ◽

pp. 329-336

Author(s):

Xiaoling Zhou ◽

Yukai Miao ◽

Wei Wang ◽

Jianbin Qin

Keyword(s):

Machine Learning ◽

Deep Learning ◽

State Of The Art ◽

Learning To Rank ◽

Parameter Tuning ◽

Knowledge Bases ◽

The State ◽

Training Data ◽

Machine Learning Techniques ◽

Free Text

The vast amount of web data enables us to build knowledge bases with unprecedented quality and coverage. Named Entity Disambiguation (NED) is an important task that automatically resolves ambiguous mentions in free text to correct target entries in the knowledge base. Traditional machine learning based methods for NED were outperformed and made obsolete by the state-of-the-art deep learning based models. However, deep learning models are more complex, requiring large amount of training data and lengthy training and parameter tuning time. In this paper, we revisit traditional machine learning techniques and propose a light-weight, tuneable and time-efficient method without using deep learning or deep learning generated features. We propose novel adaptive features that focus on extracting discriminative features to better model similarities between candidate entities and the mention's context. We learn a local ranking model based on traditional and the new adaptive features based on the learning-to-rank framework. While arriving at linking decisions individually via the local model, our method also takes into consideration the correlation between decisions by running multiple recurrent global models, which can be deemed as a learned local search method. Our method attains performances comparable to the state-of-the-art deep learning-based methods on NED benchmark datasets while being significantly faster to train.

Download Full-text

Practical Picture Processing

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100051700 ◽

1974 ◽

Vol 32 ◽

pp. 338-339

Author(s):

T. A. Welton

Keyword(s):

Radiation Damage ◽

Coherence Length ◽

Spatial Information ◽

State Of The Art ◽

Coherent Radiation ◽

The State ◽

Energy Spread ◽

Electron Micrograph ◽

Picture Processing ◽

Molecular Skeleton

Various authors have emphasized the spatial information resident in an electron micrograph taken with adequately coherent radiation. In view of the completion of at least one such instrument, this opportunity is taken to summarize the state of the art of processing such micrographs. We use the usual symbols for the aberration coefficients, and supplement these with £ and 6 for the transverse coherence length and the fractional energy spread respectively. He also assume a weak, biologically interesting sample, with principal interest lying in the molecular skeleton remaining after obvious hydrogen loss and other radiation damage has occurred.

Download Full-text