Search

Domain transfer is a prevalent challenge in modern neural Information Retrieval (IR). To overcome this problem, previous research has utilized domain-specific manual annotations and synthetic data produced by consistency filtering to finetune a general ranker and produce a domain-specific ranker. However, training such consistency filters are computationally expensive, which significantly reduces the model efficiency. In addition, consistency filtering often struggles to identify retrieval intentions and recognize query and corpus distributions in a target domain. In this study, we evaluate a more efficient solution: replacing the consistency filter with either direct pseudo-labeling, pseudo-relevance feedback, or unsupervised keyword generation methods for achieving consistent filtering-free unsupervised dense retrieval. Our extensive experimental evaluations demonstrate that, on average, TextRank-based pseudo relevance feedback outperforms other methods. Furthermore, we analyzed the training and inference efficiency of the proposed paradigm. The results indicate that filtering-free unsupervised learning can continuously improve training and inference efficiency while maintaining retrieval performance. In some cases, it can even improve performance based on particular datasets.

Big data mining is well known to be an important task for data science, because it can provide useful observations and new knowledge hidden in given large datasets. Proximity-based data analysis is particularly utilized in many real-life applications. In such analysis, the distances to k nearest neighbors are usually employed, thus its main bottleneck is derived from data retrieval. Much efforts have been made to improve the efficiency of these analyses. However, they still incur large costs, because they essentially need many data accesses. To avoid this issue, we propose a machine-learning technique that quickly and accurately estimates the k-NN distances (i.e., distances to the k nearest neighbors) of a given query. We train a fully connected neural network model and utilize pivots to achieve accurate estimation. Our model is designed to have useful advantages: it infers distances to the k-NNs at a time, its inference time is O(1) (no data accesses are incurred), but it keeps high accuracy. Our experimental results and case studies on real datasets demonstrate the efficiency and effectiveness of our solution., Comment: Accepted to SIGSPATIAL2022 (as short paper)

Influenza, an infectious disease, causes many deaths worldwide. Predicting influenza victims during epidemics is an important task for clinical, hospital, and community outbreak preparation. On-line user-generated contents (UGC), primarily in the form of social media posts or search query logs, are generally used for prediction for reaction to sudden and unusual outbreaks. However, most studies rely only on the UGC as their resource and do not use various UGCs. Our study aims to solve these questions about Influenza prediction: Which model is the best? What combination of multiple UGCs works well? What is the nature of each UGC? We adapt some models, LASSO Regression, Huber Regression, Support Vector Machine regression with Linear kernel (SVR) and Random Forest, to test the influenza volume prediction in Japan during 2015 - 2018. For that, we use on-line five data resources: (1) past flu patients, (2) SNS (Twitter), (3) search engines (Yahoo! Japan), (4) shopping services (Yahoo! Shopping), and (5) Q&A services (Yahoo! Chiebukuro) as resources of each model. We then validate respective resources contributions using the best model, Huber Regression, with all resources except one resource. Finally, we use Bayesian change point method for ascertaining whether the trend of time series on any resources is reflected in the trend of flu patient count or not. Our experiments show Huber Regression model based on various data resources produces the most accurate results. Then, from the change point analysis, we get the result that search query logs and social media posts for three years represents these resources as a good predictor. Conclusions: We show that Huber Regression based on various data resources is strong for outliers and is suitable for the flu prediction. Additionally, we indicate the characteristics of each resource for the flu prediction., Comment: 18pages, 3 figures

[Background] Two clusters of coronavirus disease 2019 (COVID-19) were confirmed in Hokkaido, Japan in February 2020. To capture the clusters, this study employs Web search query logs and user location information from smartphones. [Material and Methods] First, we anonymously identified smartphone users who used a Web search engine (Yahoo! JAPAN Search) for the COVID-19 or its symptoms via its companion application for smartphones (Yahoo Japan App). We regard these searchers as Web searchers who are suspicious of their own COVID-19 infection (WSSCI). Second, we extracted the location of the WSSCI via the smartphone application. The spatio-temporal distribution of the number of WSSCI are compared with the actual location of the known two clusters. [Result and Discussion] Before the early stage of the cluster development, we could confirm several WSSCI, which demonstrated the basic feasibility of our WSSCI-based approach. However, it is accurate only in the early stage, and it was biased after the public announcement of the cluster development. For the case where the other cluster-related resources, such as fine-grained population statistics, are not available, the proposed metric would be helpful to catch the hint of emerging clusters.

We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). We call our method BanditRank as it treats ranking as a contextual bandit problem. In the domain of learning to rank for IR, current deep learning models are trained on objective functions different from the measures they are evaluated on. Since most evaluation measures are discrete quantities, they cannot be leveraged by directly using gradient descent algorithms without an approximation. BanditRank bridges this gap by directly optimizing a task-specific measure, such as mean average precision (MAP), using gradient descent. Specifically, a contextual bandit whose action is to rank input documents is trained using a policy gradient algorithm to directly maximize the reward. The reward can be a single measure, such as MAP, or a combination of several measures. The notion of ranking is also inherent in BanditRank, similar to the current \textit{listwise} approaches. To evaluate the effectiveness of BanditRank, we conducted a series of experiments on datasets related to three different tasks, i.e., web search, community, and factoid question answering. We found that it performs better than state-of-the-art methods when applied on the question answering datasets. On the web search dataset, we found that BanditRank performed better than four strong listwise baselines including LambdaMART, AdaRank, ListNet and Coordinate Ascent., Comment: 9 pages

Question categorization and expert retrieval methods have been crucial for information organization and accessibility in community question & answering (CQA) platforms. Research in this area, however, has dealt with only the text modality. With the increasing multimodal nature of web content, we focus on extending these methods for CQA questions accompanied by images. Specifically, we leverage the success of representation learning for text and images in the visual question answering (VQA) domain, and adapt the underlying concept and architecture for automated category classification and expert retrieval on image-based questions posted on Yahoo! Chiebukuro, the Japanese counterpart of Yahoo! Answers. To the best of our knowledge, this is the first work to tackle the multimodality challenge in CQA, and to adapt VQA models for tasks on a more ecologically valid source of visual questions. Our analysis of the differences between visual QA and community QA data drives our proposal of novel augmentations of an attention method tailored for CQA, and use of auxiliary tasks for learning better grounding features. Our final model markedly outperforms the text-only and VQA model baselines for both tasks of classification and expert retrieval on real-world multimodal CQA data., Comment: Submitted for review at CIKM 2019

The BM25 ranking function is one of the most well known query relevance document scoring functions and many variations of it are proposed. The BM25F function is one of its adaptations designed for modeling documents with multiple fields. The Expanded Span method extends a BM25-like function by taking into considerations of the proximity between term occurrences. In this note, we combine these two variations into one scoring method in view of proximity-based scoring of documents with multiple fields., Comment: 2 pages

Logs of the interactions with a search engine show that users often reformulate their queries. Examining these reformulations shows that recommendations that precise the focus of a query are helpful, like those based on expansions of the original queries. But it also shows that queries that express some topical shift with respect to the original query can help user access more rapidly the information they need. We propose a method to identify from the query logs of past users queries that either focus or shift the initial query topic. This method combines various click-based, topic-based and session based ranking strategies and uses supervised learning in order to maximize the semantic similarities between the query and the recommendations, while at the same diversifying them. We evaluate our method using the query/click logs of a Japanese web search engine and we show that the combination of the three methods proposed is significantly better than any of them taken individually., Comment: 2nd International Workshop on Usage Analysis and the Web of Data (USEWOD2012) in the 21st International World Wide Web Conference (WWW2012), Lyon, France, April 17th, 2012