Recommending tasks based on search queries and missions

We present a novel, hybrid approach for clustering text databases. We use a genetic algorithm to generate and evolve a set of single word search queries in Apache Lucene format. Clusters are formed as the set of documents matching a search query. The queries are optimized to maximize the number of documents returned and to minimize the overlap between clusters (documents returned by more than one query in a set). Optionally, the number of clusters can be specified in advance, which will normally result in an improvement in performance. Not all documents in a collection are returned by any of the search queries in a set, so once the search query evolution is completed a second stage is performed whereby a KNN algorithm is applied to assign all unassigned documents to their nearest cluster. We describe the method and compare effectiveness with other well-known existing systems on 8 different text datasets. We note that search query format has the qualitative benefits of being interpretable and providing an explanation of cluster construction.

Reciprocal Recommender Systems (RRSs) which aim to satisfy the preferences of both service providers and seekers simultaneously has attracted significant research interest in recent years. Existing studies on RRSs mainly focus on modeling the bilateral interactions between the users on both sides to capture the user preferences. However, due to the presence of exposure bias, modeling user preferences solely based on bilateral interactions often lacks precision. Additionally, in RRSs, users may exhibit varying preferences when acting in different roles, and how to effectively model users from multiple perspectives remains a substantial problem. To solve the above challenges, in this paper, we propose a novel MultI-view Reciprocal Recommender system for Online Recruitment (MIRROR). Specifically, we first propose to model the users from three different views, respectively search, active, and passive views, and we further design several Transformer-based sequential models to capture the user representation corresponding to each view. Then, we propose to divide the bilateral matching process into three stages, respectively apply, reply, and match, and a multi-stage output layer is designed based on the above multi-view modeling results. To train our MIRROR model, we first design a multi-task learning loss based on the multi-stage output results. Moreover, to bridge the semantic gap between search queries and user behaviors, we additionally design a supplementary task for next-query prediction. Finally, we conduct both offline experiments on five real-world datasets and online A/B tests, and the experiment results clearly validate the effectiveness of our MIRROR model compared with several state-of-the-art baseline methods.

We consider a search task as a set of queries that serve the same user information need. Analyzing search tasks from user query streams plays an important role in building a set of modern tools to improve search engine performance. In this paper, we propose a probabilistic method for identifying and labeling search tasks based on the following intuitive observations: queries that are issued temporally close by users in many sequences of queries are likely to belong to the same search task, meanwhile, different users having the same information needs tend to submit topically coherent search queries. To capture the above intuitions, we directly model query temporal patterns using a special class of point processes called Hawkes processes, and combine topic models with Hawkes processes for simultaneously identifying and labeling search tasks. Essentially, Hawkes processes utilize their self-exciting properties to identify search tasks if influence exists among a sequence of queries for individual users, while the topic model exploits query co-occurrence across different users to discover the latent information needed for labeling search tasks. More importantly, there is mutual reinforcement between Hawkes processes and the topic model in the unified model that enhances the performance of both. We evaluate our method based on both synthetic data and real-world query log data. In addition, we also apply our model to query clustering and search task identification. By comparing with state-of-the-art methods, the results demonstrate that the improvement in our proposed approach is consistent and promising.

ObjectiveThis study aimed to develop a robust framework for breast cancer diagnosis by integrating advanced segmentation and classification approaches. Transformer-based and U-Net segmentation models were combined with radiomic feature extraction and machine learning classifiers to improve segmentation precision and classification accuracy in mammographic images.Materials and MethodsA multi-center dataset of 8000 mammograms (4200 normal, 3800 abnormal) was used. Segmentation was performed using Transformer-based and U-Net models, evaluated through Dice Coefficient (DSC), Intersection over Union (IoU), Hausdorff Distance (HD95), and Pixel-Wise Accuracy. Radiomic features were extracted from segmented masks, with Recursive Feature Elimination (RFE) and Analysis of Variance (ANOVA) employed to select significant features. Classifiers including Logistic Regression, XGBoost, CatBoost, and a Stacking Ensemble model were applied to classify tumors into benign or malignant. Classification performance was assessed using accuracy, sensitivity, F1 score, and AUC-ROC. SHAP analysis validated feature importance, and Q-value heatmaps evaluated statistical significance.ResultsThe Transformer-based model achieved superior segmentation results with DSC (0.94 ± 0.01 training, 0.92 ± 0.02 test), IoU (0.91 ± 0.01 training, 0.89 ± 0.02 test), HD95 (3.0 ± 0.3 mm training, 3.3 ± 0.4 mm test), and Pixel-Wise Accuracy (0.96 ± 0.01 training, 0.94 ± 0.02 test), consistently outperforming U-Net across all metrics. For classification, Transformer-segmented features with the Stacking Ensemble achieved the highest test results: 93% accuracy, 92% sensitivity, 93% F1 score, and 95% AUC. U-Net-segmented features achieved lower metrics, with the best test accuracy at 84%. SHAP analysis confirmed the importance of features like Gray-Level Non-Uniformity and Zone Entropy.ConclusionThis study demonstrates the superiority of Transformer-based segmentation integrated with radiomic feature selection and robust classification models. The framework provides a precise and interpretable solution for breast cancer diagnosis, with potential for scalability to 3D imaging and multimodal datasets.

The ad hoc table retrieval task is concerned with satisfying a query with a ranked list of tables. While there are strong baselines in the literature that exploit learning to rank and semantic matching techniques, there are still a set of hard queries that are difficult for these baseline methods to address. We find that such hard queries are those whose constituting tokens (i.e., terms or entities) are not fully or partially observed in the relevant tables. We focus on proposing a latent factor model to address such hard queries. Our proposed model factorizes the token-table co-occurrence matrix into two low dimensional latent factor matrices that can be used for measuring table and query similarity even if no shared tokens exist between them. We find that the variation of our proposed model that considers keywords provides statistically significant improvement over three strong baselines in terms of NDCG and ERR.

Framework for tasks suggestion on web search based on unsupervised learning techniques

Personalized data access has become one of the core challenges for intelligent information access, especially for nonmainstream long-tail content, as can be found in digital libraries. One of the main reasons that personalization remains a difficult task is the lack of standardized test corpora. In this paper we provide a comprehensive analysis of feature requirements for personalization together with a data collection tool for generating user models and collecting data for personalization of search and recommender system optimization in the long-tail. Based on the feature analysis, we provide a feature-rich publicly available data set, covering web content consumption and creation tasks. Our data set contains user models for eight users, including performed tasks, relevant topics for each task, relevance ratings, and relations between focus text and search queries. Altogether, the data set consists of 217 tasks, 4562 queries and over 15.000 ratings. On this data we perform automatic query prediction from web page content, achieving an accuracy of 89% using term identity, capitalization and part-of-speech tags as features. The results of the feature analysis can serve as guideline for feature collection for long-tail content personalization, and the provided data set as a gold standard for learning and evaluation of user models as well as for optimizing recommender or search engines for long-tail domains.

Understanding the biology underpinning the natural regeneration of plant species in order to make plans for effective reforestation is a complex task. This can be aided by providing access to databases that contain long-term and wide-scale geographical information on species distribution, habitat, and reproduction. Although there exists widely-used biodiversity databases that contain structured information on species and their occurrences, such as the Global Biodiversity Information Facility (GBIF) and the Atlas of Living Australia (ALA), the bulk of knowledge about biodiversity still remains embedded in textual documents. Unstructured information can be made more accessible and useful for large-scale studies if there are tools and services that automatically extract meaningful information from text and store it in structured formats, e.g., open biodiversity databases, ready to be consumed for analysis (Thessen et al. 2022). We aim to enrich biodiversity occurrence databases with information on species reproductive condition and habitat, derived from text. In previous work, we developed unsupervised approaches to extract related habitats and their locations, and related reproductive condition and temporal expressions (Gabud and Batista-Navarro 2018). We built a new unsupervised hybrid approach for relation extraction (RE), which is a combination of classical rule-based pattern-matching methods and transformer-based language models that framed our RE task as a natural language inference (NLI) task. Using our hybrid approach for RE, we were able to extract related biodiversity entities from text even without a large training dataset. In this work, we implement an information extraction (IE) pipeline comprised of a named entity recognition (NER) tool and our hybrid relation extraction (RE) tool. The NER tool is a transformer-based language model that was pretrained on scientific text and then fine-tuned using COPIOUS (Conserving Philippine Biodiversity by Understanding big data; Nguyen et al. 2019), a gold standard corpus containing named entities relevant to species occurrence. We applied the NER tool to automatically annotate geographical location, temporal expression and habitat information contained within sentences. A dictionary-based approach is then used to identify mentions of reproductive conditions in text (e.g., phrases such as "fruited heavily" and "mass flowering"). We then use our hybrid RE tool to extract reproductive condition - temporal expression and habitat - geographical location entity pairs. We test our IE pipeline on the forestry compendium available in the CABI Digital Library (Centre for Agricultural and Biosciences International), and show that our work enables the enrichment of descriptive information on reproductive and habitat conditions of species. This work is a step towards enhancing a biodiversity database with the inclusion of habitat and reproductive condition information extracted from text.

Stance detection aims at identifying people's stand-point towards a given target. New targets are constantly appearing on social media, making previous annotated data unusable by stance detection models relying on classical supervised machine learning. Thus, cross-target stance detection which uses labeled data from source targets to learn a model that can be adapted to the destination new target, has become a prevailing research direction. However, previous methods rely on manually chosen similar source-destination target pairs and lack generalization to unseen targets with no explicit relation to known ones. To this end, we investigate the problem from a domain adaptation perspective and further propose a novel Unified Target-aware Domain Adaptation method (UTDA) that leverages knowledge transfer capability of transformer-based language model. The proposed method can effectively extract critical target-shared features for detecting stance by feature disentanglement and automatically learn to identify target relations. UTDA can easily be applied to a new unseen target since it does not rely on any pre-defined target pairs. Experimental results on two benchmark stance datasets demonstrate that our method achieves better performance than strong baselines.

Despite their important role in online information search, search query suggestions have not been researched as much as most other aspects of search engines. Although reasons for this are multi-faceted, the sparseness of context and the limited data basis of up to ten suggestions per search query pose the most significant problem in identifying bias in search query suggestions. The most proven method to reduce sparseness and improve the validity of bias identification of search query suggestions so far is to consider suggestions from subsequent searches over time for the same query. This work presents a new, alternative approach to search query bias identification that includes less high-level suggestions to deepen the data basis of bias analyses. We employ recursive algorithm interrogation techniques and create suggestion trees that enable access to more subliminal search query suggestions. Based on these suggestions, we investigate topical group bias in person-related searches in the political domain.

Document corpora are key components of information retrieval test collections. However, for certain tasks, such as evaluating the effectiveness of a new retrieval technique or estimating the parameters of a learning to rank model, a corpus alone is not enough. For these tasks, queries and relevance judgments associated with the corpus are also necessary. However, researchers often find themselves in scenarios where they only have access to a corpus, in which case evaluation and learning to rank become challenging. Document corpora are relatively straightforward to gather. On the other hand, obtaining queries and relevance judgments for a given corpus is costly. In production environments, it may be possible to obtain low-cost relevance information using query and click logs. However, in more constrained research environments these options are not available, and relevance judgments are usually provided by humans. To reduce the cost of this potentially expensive process, researchers have developed low-cost evaluation strategies, including minimal test collections [2] and crowdsourcing [1]. Despite the usefulness of these strategies, the resulting relevance judgments cannot easily be “ported” to a new or different corpus. To overcome these issues, we propose a new method to reduce manual annotation costs by transferring relevance judgments across corpora. Assuming that a set of queries and relevance judgments have been manually constructed for a source document corpus Ds, our goal is to automatically construct a test collection for a target document corpus Dt by projecting the existing test collection from Ds onto Dt. The goal of projecting test collections is not to produce manual quality test collections. In fact, it is assumed that projected test collections will contain noisy relevance judgments (i.e., ones which humans are unlikely to agree with). The important question, however, is whether these noisy projected judgments are useful for training ranking models in the target corpus.

Agenda 2030 of Sustainable Development Goals (SDGs) 9 and 11 recognizes tourism as one of the central industries to global development to tackle global challenges. With the transformation of information and communication technologies (ICT), e-tourism has evolved globally to establish commercial relationships using the Internet for offering tourism-related products, including giving personalised suggestions. The contextual suggestion has emerged as a modified recommendation system that is integrated with information-retrieval techniques within large databases to provide tourists with a list of suggestions based on contexts, such as location, time of day, or day of the week (weekdays or weekends). This study surveyed literature in the field of contextual suggestion and recommendation systems with a focus on e-tourism. The concerns linked with approaches used in contextual suggestion and recommendation systems are highlighted in this systematic review, while motivations, recommendations, and practical implications in e-tourism are also discussed in this paper. A query search using the keywords “contextual suggestion system”, “recommendation system”, and “tourism” identified 143 relevant articles published from 2012 to 2020. Four major repositories are considered for searching, namely, (i) Science Direct, (ii) Scopus, (iii) IEEE, and (iv) Web of Science. This review was carried out under the protocols of four phases, namely, (i) query searching in major article repositories, (ii) removal of duplicates, (iii) scan of title and abstract, and (iv) complete reading of articles. To identify the gaps in current research, a taxonomy analysis was exemplified into categories and subcategories. The main categories were highlighted as (i) review articles, (ii) model/framework, and (iii) applications. Critical analysis was carried out on the basis of the available literature on the limitations of approaches used in contextual suggestion and recommendation systems. In conclusion, the approaches used are mainly based on content-based filtering, collaborative filtering, preference-based product ranking, and language modelling. The evaluation measures for the contextual suggestion system include precision, normalized discounted cumulative, and mean reciprocal rank, while test collections comprise Internet resources. Given that the tourism industry contributed to the environmental and social-economic development, contextual suggestion and recommendation systems have presented themselves to be relevant in integrating and achieving SDG 9 and SDG 11 in many ways such as web-based e-services by the government sector and smart gadgets based on reliable and real-time data and information for city planners as well as law enforcement personnel in a sustainable city.

Chapter 20 - Query Suggestion with Large Scale Data

This paper targets to a novel but practical recommendation problem named exact-K recommendation. It is different from traditional top-K recommendation, as it focuses more on (constrained) combinatorial optimization which will optimize to recommend a whole set of K items called card, rather than ranking optimization which assumes that better items should be put into top positions. Thus we take the first step to give a formal problem definition, and innovatively reduce it to Maximum Clique Optimization based on graph. To tackle this specific combinatorial optimization problem which is NP-hard, we propose Graph Attention Networks (GAttN) with a Multi-head Self-attention encoder and a decoder with attention mechanism. It can end-to-end learn the joint distribution of the K items and generate an optimal card rather than rank individual items by prediction scores. Then we propose Reinforcement Learning from Demonstrations (RLfD) which combines the advantages in behavior cloning and reinforcement learning, making it sufficient-and-efficient to train the model. Extensive experiments on three datasets demonstrate the effectiveness of our proposed GAttN with RLfD method, it outperforms several strong baselines with a relative improvement of 7.7% and 4.7% on average in Precision and Hit Ratio respectively, and achieves state-of-the-art (SOTA) performance for the exact-K recommendation problem.

Availability of diagnostic codes in Electronic Health Records (EHRs) is crucial for patient care as well as reimbursement purposes. However, entering them in the EHR is tedious, and some clinical codes may be overlooked. Given an incomplete list of clinical codes, we investigate the performance of ML methods on predicting the complete ones, and assess the added predictive value of including other clinical patient data in this task. We used the MIMIC-III dataset and frame the task of completing the clinical codes as a recommendation problem. We consider various autoencoder approaches plus two strong baselines; item co-occurrence and Singular Value Decomposition (SVD). Inputs are 1) a record’s known clinical codes, 2) the codes plus variables. The co-occurrence-based approach performed slightly better (F1 score = 0.26, Mean Average Precision [MAP] = 0.19) than the SVD (F1 = 0.24, MAP = 0.18). However, the adversarial autoencoder achieved the best performance when using the codes plus variables (F1 = 0.32, MAP = 0.25). Adversarial autoencoders performed best in terms of F1 and were equal to vanilla and denoising autoencoders in term of MAP. Using clinical variables in addition to the incomplete codes list, improves the predictive performance of the models.