Hongbo Deng

Identifying and labeling search tasks via query-based hawkes processes

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.

Ranking Relevance in Yahoo Search

Search engines play a crucial role in our daily lives. Relevance is the core problem of a commercial search engine. It has attracted thousands of researchers from both academia and industry and has been studied for decades. Relevance in a modern search engine has gone far beyond text matching, and now involves tremendous challenges. The semantic gap between queries and URLs is the main barrier for improving base relevance. Clicks help provide hints to improve relevance, but unfortunately for most tail queries, the click information is too sparse, noisy, or missing entirely. For comprehensive relevance, the recency and location sensitivity of results is also critical. In this paper, we give an overview of the solutions for relevance in the Yahoo search engine. We introduce three key techniques for base relevance -- ranking functions, semantic matching features and query rewriting. We also describe solutions for recency sensitive relevance and location sensitive relevance. This work builds upon 20 years of existing efforts on Yahoo search, summarizes the most recent advances and provides a series of practical relevance solutions. The performance reported is based on Yahoos commercial search engine, where tens of billions of urls are indexed and served by the ranking system.

Uncertainty Reduction for Knowledge Discovery and Information Extraction on the World Wide Web

In this paper, we give an overview of knowledge discovery (KD) and information extraction (IE) techniques on the World Wide Web (WWW). We intend to answer the following questions: What kind of additional uncertainty challenges are introduced by the WWW setting to basic KD and IE techniques? What are the fundamental techniques that can be used to reduce such uncertainty and achieve reasonable KD and IE performance on the WWW? What is the impact of each novel method? What types of interactions can be conducted between these techniques and information networks to make them benefit from each other? In what way can we utilize the results in more interesting applications? What are the remaining challenges and what are the possible ways to address these challenges? We hope this can provide a road map to advance KD and IE on the WWW to a higher level of performance, portability and utilization.

Analysis and refinement of cross-lingual entity linking

In this paper we propose two novel approaches to enhance cross-lingual entity linking (CLEL). One is based on cross-lingual information networks, aligned based on monolingual information extraction, and the other uses topic modeling to ensure global consistency. We enhance a strong baseline system derived from a combination of state-of-the-art machine translation and monolingual entity linking to achieve 11.2% improvement in B-Cubed+ F-measure. Our system achieved highly competitive results in the NIST Text Analysis Conference (TAC) Knowledge Base Population (KBP2011) evaluation. We also provide detailed qualitative and quantitative analysis on the contributions of each approach and the remaining challenges.

Exploring and inferring user-user pseudo-friendship for sentiment analysis with heterogeneous networks

With the development of social media and social networks, user-generated content, such as forums, blogs and comments, are not only getting richer, but also ubiquitously interconnected with many other objects and entities, forming a heterogeneous information network between them. Sentiment analysis on such kinds of data can no longer ignore the information network, since it carries a lot of rich and valuable information, explicitly or implicitly, where some of them can be observed while others are not. However, most existing methods may heavily rely on the observed user-user friendship or similarity between objects, and can only handle a subgraph associated with a single topic. None of them takes into account the hidden and implicit dissimilarity, opposite opinions, and foe relationship. In this paper, we propose a novel information network-based framework which can infer hidden similarity and dissimilarity between users by exploring similar and opposite opinions, so as to improve post-level and user-level sentiment classification at the same time. More specifically, we develop a new meta path-based measure for inferring pseudo-friendship as well as dissimilarity between users, and propose a semi-supervised refining model by encoding similarity and dissimilarity from both user-level and post-level relations. We extensively evaluate the proposed approach and compare with several state-of-the-art techniques on two real-world forum datasets. Experimental results show that our proposed model with 10.5% labeled samples can achieve better performance than a traditional supervised model trained on 61.7% data samples.

Query Understanding for Search on All Devices at WSDM 2016

It is our great pleasure to welcome you to the QRUMS 2016, the workshop on Query Understanding for Search on All Devices, held as part of the WSDM 2016 conference in San Francisco, USA. Theme and Purpose of the workshop: Query understanding has become a crucial component for today’s search engines. It is important to improve query understanding as query formulation is the way through which users express their search intent to a search engine. With the ubiquitousness of mobile devices, it is even more important to better understand user intent as typing on mobile is hard and time consuming. This workshop focuses on query understanding for mobile search with a motivation of reducing user efforts in formulating queries and getting their expected search results quickly. One of the most important problem in query understanding is Query auto-completion (QAC). QAC is the first service through which users interact with a search engine to input their search intent. QAC has to provide and update their suggestion lists based on each new character typed by the user in the search box. Returned suggestion lists are ranked based on different relevance models, such as most popular completion (based on historical frequency counts from query logs) [1], time-based (giving more weight to breaking news or recent popular queries) [10, 12, 11], location-based [9], context-sensitive (based on user’s context) [1, 5], personalized (based on user’s profile) [9], click modeling (based on user’s past clicks) [6], user-QAC interactions [8, 4], adaptive query auto-completion [13]. QAC becomes even more important as the focus shifts from desktop search to mobile search. On mobile, due to small typing keyboard, it is even more important to exploit all user and its context information available on mobile to provide the user better search suggestions. On query understanding and QAC: there is also a need of personalized and context models, especially for name queries. For example, a user may talk to his smart phone, “forward an email to Bill”. This implicitly triggers the query understanding engine to map “Bill” to a specific person in