Keyphrase provides highly-summative information that can be effectively used for understanding, organizing and retrieving text content. Though previous studies have provided many workable solutions for automated keyphrase extraction, they commonly divided the to-be-summarized content into multiple text chunks, then ranked and selected the most meaningful ones. These approaches could neither identify keyphrases that do not appear in the text, nor capture the real semantic meaning behind the text. We propose a generative model for keyphrase prediction with an encoder-decoder framework, which can effectively overcome the above drawbacks. We name it as deep keyphrase generation since it attempts to capture the deep semantic meaning of the content with a deep learning method. Empirical analysis on six datasets demonstrates that our proposed model not only achieves a significant performance boost on extracting keyphrases that appear in the source text, but also can generate absent keyphrases based on the semantic meaning of the text. Code and dataset are available at https://github.com/memray/seq2seq-keyphrase.

Learning to Rank, a central problem in information retrieval, is a class of machine learning algorithms that formulate ranking as an optimization task. The objective is to learn a function that produces an ordering of a set of documents in such a way that the utility of the entire ordered list is maximized. Learning-to-rank methods do so by learning a function that computes a score for each document in the set. A ranked list is then compiled by sorting documents according to their scores. While such a deterministic mapping of scores to permutations makes sense during inference where stability of ranked lists is required, we argue that its greedy nature during training leads to less robust models. This is particularly problematic when the loss function under optimization-in agreement with ranking metrics-largely penalizes incorrect rankings and does not take into account the distribution of raw scores. In this work, we present a stochastic framework where, instead of a deterministic derivation of permutations from raw scores, permutations are sampled from a distribution defined by raw scores. Our proposed sampling method is differentiable and works well with gradient descent optimizers. We analytically study our proposed method and demonstrate when and why it leads to model robustness. We also show empirically, through experiments on publicly available learning-to-rank datasets, that the application of our proposed method to a class of ranking loss functions leads to significant model quality improvements.

Investigations of search processes that involve complex interactions, such as collaborative search processes, are important research topics. Previous approaches of directly applying individual search process models into collaborative settings have proven to be problematic. In this paper, we proposed an innovative approach to model collaborative search processes using Hidden Markov Model (HMM), which is an automatic technique for analyzing temporal sequential data. Obtained through a user study, the data used in this paper consist of two different tasks in both collaborative exploratory Web search and individual exploratory Web search conditions. Our results showed that the identified hidden patterns of search process through HMM are compatible with previous well-known models. In addition, HMM generates detailed information on the transitions of hidden patterns in search processes, which demonstrated to be useful for analyzing task differences, and for determining the correlation of search process with search performance. The findings can be used for evaluating collaborative search systems as well as providing guidance for the system design. Author KeywordsCollaborative information behavior; exploratory search; Hidden Markov Model; information seeking process.

Mobile devices enable people to look for information at the moment when their information needs are triggered. While experiencing complex information needs that require multiple search sessions, users may utilize desktop computers to fulfill information needs started on mobile devices. Under the context of mobileto-desktop web search, this article analyzes users' behavioral patterns and compares them to the patterns in desktop-to-desktop web search. Then, we examine several approaches of using Mobile Touch Interactions (MTIs) to infer relevant content so that such content can be used for supporting subsequent search queries on desktop computers. The experimental data used in this article was collected through a user study involving 24 participants and six properly designed cross-device web search tasks. Our experimental results show that (1) users' mobile-to-desktop search behaviors do significantly differ from desktop-to-desktop search behaviors in terms of information exploration, sense-making and repeated behaviors. (2) MTIs can be employed to predict the relevance of click-through documents, but applying document-level relevant content based on the predicted relevance does not improve search performance. (3) MTIs can also be used to identify the relevant text chunks at a fine-grained subdocument level. Such relevant information can achieve better search performance than the document-level relevant content. In addition, such subdocument relevant information can be combined with document-level relevance to further improve the search performance. However, the effectiveness of these methods relies on the sufficiency of click-through documents. (4) MTIs can also be obtained from the Search Engine Results Pages (SERPs). The subdocument feedbacks inferred from this set of MTIs even outperform the MTI-based subdocument feedback from the click-through documents. ACM Reference Format:Shuguang Han, Zhen Yue, and Daqing He. 2015. Understanding and supporting cross-device web search for exploratory tasks with mobile touch interactions.

Collaboration in the information seeking and retrieval environment is common, particularly when the search task is complex and exploratory. Multiple factors such as contextual features and task type can affect users' query behavior. This paper presents a study investigating the effects of collaboration and task types on users' query behavior. The study involves two conditions: collaborative search and individual search, and the two search tasks: the recall‐oriented information‐gathering and the utility‐based decision‐making. We analyze users' query behavior in three dimensions: basic query features (e.g. the number of queries), query reformulation patterns (e.g. New, Specification, Generalization and Reconstruction) and query performance. The findings of this study reveal that queries are more diverse in collaborative search and recall‐oriented tasks. Users employed New and Specialization more often as query reformulation types in collaborative search while people in individual search use Reconstruction more often. Besides, the successful query rate is higher in individual search and recall‐oriented tasks.