Multi-aspect query summarization by composite query

Understanding user intent from her sequential search behaviors, i.e. predicting the intent of each user query in a search session, is crucial for modern Web search engines. However, due to the huge number of user behavior variables and coarse level intent labels defined by human editors, it is very difficult to directly model user behavioral dynamics or user intent dynamics in user search sessions. In this paper, we propose a novel Sparse Hidden-Dynamic Conditional Random Fields (SHDCRF) model for user intent learning from their search sessions. Through incorporating the proposed hidden state variables, SHDCRF aims to learn a substructure, i.e. a set of related hidden variables, for each intent label and they are used to model the intermediate dynamics between user intent labels and user behavioral variables. In addition, SHDCRF learns a sparse relation between the hidden variables and intent labels to make the hidden state variables explainable. Extensive experiment results, on real user search sessions from a popular commercial search engine show that the proposed SHDCRF model significantly outperforms in terms of intent prediction results that those classical solutions such as Support Vector Machine (SVM), Conditional Random Field (CRF) and Latnet-Dynamic Conditional Random Field (LDCRF).

Web-based image search engines differ from Web search engines greatly. The intents or goals behind human interactions with image search engines are different. In image search, users mainly search images instead of Web pages or online services. It is essential to know why people search for images because user satisfaction may vary as intent varies. Furthermore, image search engines show results differently. For example, grid-based placement is used in image search instead of the linear result list, so that users can browse result list both vertically and horizontally. Different user intents and system UIs lead to different user behavior. Thus, it is hard to apply standard user behavior models developed for general Web search to image search. To better understand user intent and behavior in image search scenarios, we plan to conduct the lab-based user study, field study and commercial search log analysis. We then propose user behavior models based on the observation from data analysis to improve the performance of Web image search engines.

With the exponential growth of information on the internet, users have been relying on search engines for finding the precise documents. However, user queries are often short. The inherent ambiguity of short queries imposes great challenges for search engines to understand user intent. Query suggestion is one key technique for search engines to augment user queries so that they can better understand user intent. In the past, query suggestions have been relying on either term-frequency--based methods with little semantic understanding of the query, or word-embedding--based methods with little personalization efforts. Here, we present a sequence-to-sequence-model--based query suggestion framework that is capable of modeling structured, personalized features and unstructured query texts naturally. This capability opens up the opportunity to better understand query semantics and user intent at the same time. As the largest professional network, LinkedIn has the advantage of utilizing a rich amount of accurate member profile information to personalize query suggestions. We applied this framework in the LinkedIn production traffic and showed that personalized query suggestions significantly improved member search experience as measured by key business metrics at LinkedIn.

An efficient adaptive document classification and categorization approach is proposed for personal file creation corresponding to user’s specific needs and profile. This kind of approach is needed because the search engines are often too general to offer a precise answer to the user request. As we cannot act directly on the search engines methodology, we propose to rather act on the documents retrieved by classifying and ranking them properly. A classifier combination approach is considered. These classifiers are chosen very complementary in order to treat all the query aspects and to present to the user at the end a readable and comprehensible result. The application performed corresponds to the law articles stemmed from the European Union data base. The law texts are always entangled with cross-references and accompanied by some updating files (for application dates, for new terms and formulations). Our approach found here a real application offering to the specialist (jurist, lawyer, etc. ) a synthetic vision of the law related to the topic requested.

Search engines derive revenue by displaying sponsored results along with organic results in response to user queries. In general, search engines run a per-query, on-line auction amongst interested advertisers to select sponsored results to display. In doing so, they must carefully balance the revenue derived from sponsored results against potential degradation in user experience due to less-relevant results. Hence, major search engines attempt to analyze the relevance of potential sponsored results to the user's query using supervised learning algorithms. Past work has employed a bag-of-words approach using features extracted from both the query and potential sponsored result to train the ranker.We show that using features that capture the advertiser's intent can significantly improve the performance of relevance ranking. In particular, we consider the ad keyword the advertiser submits as part of the auction process as a direct expression of intent. We leverage the search engine itself to interpret the ad keyword by submitting the ad keyword as an independent query and incorporating the results as features when determining the relevance of the advertiser's sponsored result to the user's original query. We achieve 43.2% improvement in precision-recall AUC over the best previously published baseline and 2.7% improvement in the production system of a large search engine.

This paper proposed an autonomous task algorithm based on Behavior Trees (BTs) for robot, which enabled robot to complete tasks autonomously in dynamic environment with understanding user's intention. Different from other advanced robotic systems, we proposed a unified representation model based on BTs. It achieved the process of transformation from abstract intention to robot specific operation and had been applied on robotic component of human-robot interaction and reasoning, task planning, execution. Then, the autonomous task algorithm was designed, which generated a plan according to the user's intention, map it into a BTs model and execute it. The plan could be updated dynamically through the status feedback of execution, iteratively accomplished a series of ordered actions to complete the task. We designed simulations and actual experiments respectively to verify the feasibility and practicality of our methods. The success rate of simulation and actual experiments were both 100%.

This paper introduces interactive query expansion for Thai library automation system. The approach aims to expand original Thai-language user queries to a new set of more meaningful queries in the same language. The purpose is to improve the quality of Thai user query and suggest the user with a new set of more meaningful queries. User satisfaction with retrieved results should be improved. The approach employs the information in MARC 21 bibliographic format (title access field 245) in order to generate a new list of candidate terms. The genetic process is then augmented to select new expanded terms from those candidates. The approach is evaluated on the collection of Thai educational materials such as book, journal and magazine. The performance is measured by the accuracy of new expanded terms. We asked 87 participants whether our generated terms are related to their original query. The experiment shows that users quite agree that our technique is able to generate useful terms for searching their materials in library system.

In this world the Internet has become very casual for searching. Ordinary user appears to use it every time; even they need to search keyword from any query information. Also, people use search engine like Google, Bing when they are willing to search something, wants to use some relevant information or go to their synonyms. But searching for correct result requires more time and less execution speed even they produce multiple choices. So, this process is very confusing for users to decide one correct keyword amid the many results as a search engine show overall results. An agglomerative algorithm which is useful in searching better result by their centroid, hence it executes up to their centroid. Intended for the Bisect K means approach is used which aim to generate exact keyword in less time and reducing computational cost. For these reasons, enhance method called Bisect k means approach is very useful for knowing the best result from requiring query candidate.

In this paper, a two-level deep learning framework is presented to model human information foraging behavior with search engines. A recurrent neural network architecture is designed using LSTM as the base unit to explicitly consider the temporal and spatial dependencies of information scents, the key concept in Information Foraging Theory. The target is to predict several major search behaviors, such as query abandonment, query reformulation, number of clicks, and information gain. The memory capability and the sequence structure of LSTM allow to naturally mimic not only what users are perceiving and performing at the moment but also what they have seen and learned from the past during the search dynamics. The promising results indicate that our information scent models with different input variations were better, compared to the state-of-the art neural click models, at predicting some search behaviors. When incorporating the knowledge from a previous query in the same search session, the prediction of current query abandonment, pagination, and information gain has been improved. Compared to the well known neural click models that model search behaviors under a single search query thread, this study takes a broader view to consider an entire search session which may contain multiple queries. More importantly, our model takes the search result relevance pattern on the Search Engine Results Pages (SERP) as a whole as the information scent input to the deep learning model, instead of considering one search result at each step. The results have insights on the impact of information scents on how people forage for information, which has implications for designing or refining a set of design guidelines for search engines.

Emotion recognition, an important research problem in human-robot interactions, is primarily achieved by extracting human emotions from audio and visual data. State-of-the-art performance is reported by audio-visual sensor fusion algorithms using deep learning models such as CNN, RNN, and LSTM. However, the RNN and LSTM are shown to be limited in handling the long-term dependencies over the entire input sequence. In this work, we propose to improve the performance of audio-visual emotion recognition using a novel transformer-based model, containing three transformer branches, named multimodal transformers. The three transformer branches, in our work, compute the audio self-attention, the video self-attention, and the audio-video cross attention. The self-attention branches identify the most relevant information in the audio and video input, while the cross-attention branch identifies the most relevant audio-video interactive information. The relevant information from these three branches report the best performance in our ablation study. We also propose a novel temporal embedding scheme, termed block embedding, to add the temporal information to the visual feature, derived from the multiple frames in the video. The proposed architecture is validated using the RAVDESS, CREMA-D, and SAVEE audio-visual public datasets. A detailed ablation study and comparative analysis with baseline models is performed. The results show that the proposed multi-modal transformer framework is better than the baseline methods.

Variation in Results of Three Biology‐Focused Search Engines: A Case Study Using North American Tree Species

A predictive model for mobility systems capable of understanding the trajectory a user intends to follow in the environment is proposed. Understanding user intention is paramount for any shared-control navigation strategy between a user and an active robotic agent. Equally important however is being able to go beyond simple sample generation to assign probabilistic meaning to the set of possible future trajectories, so most likely scenarios can be assumed. The framework estimates a distribution over possible intentions, proposing a novel generative model predicated on Normalizing Flows which accounts for past behaviours, as traditionally reported in the literature, but also incorporates visual scene information. As the model permits trajectories to be assigned exact likelihoods, tractable density estimates can be readily exploited to finalize an executable intention. Baseline comparisons with the publicly available and widely used KITTI navigational dataset show significant improvements (up to 11.08%) with respect to traditional metrics such as Average and Final Displacement Errors. A novel metric that stands independent of the number of samples is also proposed as a more fitting comparison for future works.

Investigating senders’ switching intention to smart lockers: An extension of push-pull-mooring model

In this paper, we explore the feature of sharing partial results of multiple queries to reduce the total number of messages incurred. Those queries sharing their partial results are referred to as backbones. Given a set of queries, we shall determine backbones with the purpose of minimizing the total number of messages. Specifically, given a set of queries, we derive a graph, where each vertex represents one query and the corresponding weight edge denotes the number of messages reduced by sharing partial results. Then, we develop a heuristic algorithm SB (standing for Selecting Backbones) to derive a cut in which both backbones and non-backbones are determined. Simulation results show that by sharing partial results, algorithm SB is able to significantly reduce the total number of messages involved.

Wireless sensor networks (WSNs) have been proposed for a large variety of applications. As the number of applications of sensor networks continue to grow, the number of users in sensor networks increases as well. Consequently, it is not uncommon that base station often needs to process multiple queries simultaneously. Furthermore, these queries often need to collect data from some particular sets of sensors such as the sensors in a hot spot.To reduce the communication cost of multiple query processing in WSNs, this paper proposes a new optimization technique based on similarities among multiple queries. Given a set of queries, Q, the proposed scheme constructs a set of shared intermediate views (SIVs) from Q. Each SIV identifies a set of shared data among queries in Q. The SIVs, are processed only once, but reused by at least two queries in Q. The queries in Q, are rewritten into a different set of queries, Q ′. The collected sensor data from Q ′ and SIVs, are aggregated and returned as the processing results for the original set of queries in Q. The simulation results show that the proposed technique can effectively reduce the communication cost of multiple query processing in WSNs.KeywordsSensor NetworkSensor NodeWireless Sensor NetworkData TransmissionQuery ProcessingThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.