Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userQuery Term Weighting based on Query Performance Prediction
155
0
0.0
(
0
)
Added by
Haggai Roitman
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Authors
Haggai Roitman
Ask ChatGPT about the research
No Arabic abstract
This work presents a general query term weighting approach based on query performance prediction (QPP). To this end, a given term is weighed according to its predicted effect on query performance. Such an effect is assumed to be manifested in the responses made by the underlying retrieval method for the original query and its (simple) variants in the form of a single-term expanded query. Focusing on search re-ranking as the underlying application, the effectiveness of the proposed term weighting approach is demonstrated using several state-of-the-art QPP methods evaluated over TREC corpora.
rate research
Read More
Geographic location search engines allow users to constrain and order search results in an intuitive manner by focusing a query on a particular geographic region. Geographic search technology, also called location search, has recently received significant interest from major search engine companies. Academic research in this area has focused primarily on techniques for extracting geographic knowledge from the web. In this paper, we study the problem of efficient query processing in scalable geographic search engines. Query processing is a major bottleneck in standard web search engines, and the main reason for the thousands of machines used by the major engines. Geographic search engine query processing is different in that it requires a combination of text and spatial data processing techniques. We propose several algorithms for efficient query processing in geographic search engines, integrate them into an existing web search query processor, and evaluate them on large sets of real data and query traces.
The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark---and can be considered to be an efficient (but slightly less effective) alternative to BERT-based ranking models. In this work, we extend the TK architecture to the full retrieval setting by incorporating the query term independence assumption. Furthermore, to reduce the memory complexity of the Transformer layers with respect to the input sequence length, we propose a new Conformer layer. We show that the Conformers GPU memory requirement scales linearly with input sequence length, making it a more viable option when ranking long documents. Finally, we demonstrate that incorporating explicit term matching signal into the model can be particularly useful in the full retrieval setting. We present preliminary results from our work in this paper.
The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark -- and can be considered to be an efficient (but slightly less effective) alternative to other Transformer-based architectures that employ (i) large-scale pretraining (high training cost), (ii) joint encoding of query and document (high inference cost), and (iii) larger number of Transformer layers (both high training and high inference costs). Since, a variant of the TK model -- called TKL -- has been developed that incorporates local self-attention to efficiently process longer input sequences in the context of document ranking. In this work, we propose a novel Conformer layer as an alternative approach to scale TK to longer input sequences. Furthermore, we incorporate query term independence and explicit term matching to extend the model to the full retrieval setting. We benchmark our models under the strictly blind evaluation setting of the TREC 2020 Deep Learning track and find that our proposed architecture changes lead to improved retrieval quality over TKL. Our best model also outperforms all non-neural runs (trad) and two-thirds of the pretrained Transformer-based runs (nnlm) on NDCG@10.
NoSQL systems are more and more deployed as back-end infrastructure for large-scale distributed online platforms like Google, Amazon or Facebook. Their applicability results from the fact that most services of online platforms access the stored data objects via their primary key. However, NoSQL systems do not efficiently support services referring more than one data object, e.g. the term-based search for data objects. To address this issue we propose our architecture based on an inverted index on top of a NoSQL system. For queries comprising more than one term, distributed indices yield a limited performance in large distributed systems. We propose two extensions to cope with this challenge. Firstly, we store index entries not only for single term but also for a selected set of term combinations depending on their popularity derived from a query history. Secondly, we additionally cache popular keys on gateway nodes, which are a common concept in real-world systems, acting as interface for services when accessing data objects in the back end. Our results show that we can significantly reduces the bandwidth consumption for processing queries, with an acceptable, marginal increase in the load of the gateway nodes.
Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However, term-based matching algorithms often miss relevant passages that have no lexical overlap with the query and cannot be finetuned to downstream datasets. In this work, we consider the embedding-based two-tower architecture as our neural retrieval model. Since labeled data can be scarce and because neural retrieval models require vast amounts of data to train, we propose a novel method for generating synthetic training data for retrieval. Our system produces remarkable results, significantly outperforming BM25 on 5 out of 6 datasets tested, by an average of 2.45 points for Recall@1. In some cases, our model trained on synthetic data can even outperform the same model trained on real data
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
