Point Of Interest (POI) categorization is to group POIs into several categories and make them easy-to-use in geospatial applications. Previous studies mainly used geospatial features, such as check-in sequences and satellite images, to group POIs into pre-defined rough categories. However, each POI has its own "atmosphere" beyond its geospatial features, which represents what kinds of people tend to visit it and how they spend their time there. This subtle atmosphere is important for users to decide whether to visit the POI, so considering it may be critical when providing commercial services, such as a property search service. In this paper, we propose a new POI categorization method that can capture the POI atmosphere by using user behavior on a web search engine. Our key observation is that the next queries of a search query about a POI tend to contain the user's purpose for visiting it. We harness this observation to train a neural encoder that maps POIs to continuous vectors (called embeddings) via next-query prediction with a deep structured semantic model (DSSM). Experimental results indicate that our method performs well for POI atmosphere categorization of parks as a case study. We believe that our method complements the existing POI categorization methods.

Ranking comments on an online news service is a practically important task for the service provider, and thus there have been many studies on this task.However, most of them considered users' positive feedback, such as "Like"-button clicks, as a quality measure.In this paper, we address directly evaluating the quality of comments on the basis of "constructiveness," separately from user feedback.To this end, we create a new dataset including 100K+ Japanese comments with constructiveness scores (C-scores).Our experiments clarify (a) C-scores are not always related to users' positive feedback and (b) the performance of pairwise ranking models tends to be more enhanced by the variation in comments than that in articles.

The writing process consists of several stages such as drafting, revising, editing, and proofreading. Studies on writing assistance, such as grammatical error correction (GEC), have mainly focused on sentence editing and proofreading, where surface-level issues such as typographical errors, spelling errors, or grammatical errors should be corrected. We broaden this focus to include the earlier revising stage, where sentences require adjustment to the information included or major rewriting and propose Sentence-level Revision (SentRev) as a new writing assistance task. Well-performing systems in this task can help inexperienced authors by producing fluent, complete sentences given their rough, incomplete drafts. We build a new freely available crowdsourced evaluation dataset consisting of incomplete sentences authored by non-native writers paired with their final versions extracted from published academic papers for developing and evaluating SentRev models. We also establish baseline performance on SentRev using our newly built evaluation dataset.

User-generated content such as the questions on community question answering (CQA) forums does not always come with appropriate headlines, in contrast to the news articles used in various headline generation tasks. In such cases, we cannot use paired supervised data, e.g., pairs of articles and headlines, to learn a headline generation model. To overcome this problem, we propose an extractive headline generation method based on learning to rank for CQA that extracts the most informative substring from each question as its headline. Experimental results show that our method outperforms several baselines, including a prefix-based method, which is widely used in real services.

Ensemble methods, which combine multiple models at decoding time, are now widely known to be effective for text-generation tasks.However, they generally increase computational costs, and thus, there have been many studies on compressing or distilling ensemble models.In this paper, we propose an alternative, simple but effective unsupervised ensemble method, post-ensemble, that combines multiple models by selecting a majority-like output in post-processing.We theoretically prove that our method is closely related to kernel density estimation based on the von Mises-Fisher kernel.Experimental results on a newsheadline-generation task show that the proposed method performs better than the current ensemble methods.

This paper explores an incremental training strategy for the skip-gram model with negative sampling (SGNS) from both empirical and theoretical perspectives.Existing methods of neural word embeddings, including SGNS, are multi-pass algorithms and thus cannot perform incremental model update.To address this problem, we present a simple incremental extension of SGNS and provide a thorough theoretical analysis to demonstrate its validity.Empirical experiments demonstrated the correctness of the theoretical analysis as well as the practical usefulness of the incremental algorithm.

We discuss an approximate similarity search for word embeddings, which is an operation to approximately find embeddings close to a given vector.We compared several metric-based search algorithms with hash-, tree-, and graphbased indexing from different aspects.Our experimental results showed that a graph-based indexing exhibits robust performance and additionally provided useful information, e.g., vector normalization achieves an efficient search with cosine similarity.

We investigate the statistical efficiency of a nonparametric Gaussian process method for a nonlinear tensor estimation problem. Low-rank tensor estimation has been used as a method to learn higher order relations among several data sources in a wide range of applications, such as multi-task learning, recommendation systems, and spatiotemporal analysis. We consider a general setting where a common linear tensor learning is extended to a nonlinear learning problem in reproducing kernel Hilbert space and propose a nonparametric Bayesian method based on the Gaussian process method. We prove its statistical convergence rate without assuming any strong convexity, such as restricted strong convexity. Remarkably, it is shown that our convergence rate achieves the minimax optimal rate. We apply our proposed method to multi-task learning and show that our method significantly outperforms existing methods through numerical experiments on real-world data sets.

We investigate the statistical performance and computational efficiency of the alternating minimization procedure for nonparametric tensor learning. Tensor modeling has been widely used for capturing the higher order relations between multimodal data sources. In addition to a linear model, a nonlinear tensor model has been received much attention recently because of its high flexibility. We consider an alternating minimization procedure for a general nonlinear model where the true function consists of components in a reproducing kernel Hilbert space (RKHS). In this paper, we show that the alternating minimization method achieves linear convergence as an optimization algorithm and that the generalization error of the resultant estimator yields the minimax optimality. We apply our algorithm to some multitask learning problems and show that the method actually shows favorable performances.

This paper proposes a novel method for transductive classification on heterogeneous information networks composed of multiple types of vertices. Such networks naturally represent many real-world Web data such as DBLP data (author, paper, and conference). Given a network where some vertices are labeled, the classifier aims to predict labels for the remaining vertices by propagating the labels to the entire network. In the label propagation process, many studies reduce the importance of edges connecting to a high-degree vertex. The assumption is unsatisfactory when reliability of a label of a vertex cannot be implied from its degree. On the basis of our intuition that edges bridging across communities are less trustworthy, we adapt edge betweenness to imply the importance of edges. Since directly applying the conventional edge betweenness is inefficient on heterogeneous networks, we propose two additional refinements. First, the centrality utilizes the fact that networks contain multiple types of vertices. Second, the centrality ignores flows originating from endpoints of considering edges. The experimental results on real-world datasets show our proposed method is more effective than a state-of-the-art method, GNetMine. On average, our method yields 92.79 ± 1.25% accuracy on a DBLP network even if only 1.92% of vertices are labeled. Our simple weighting scheme results in more than 5 percentage points increase in accuracy compared with GNetMine.

In this study, we consider a summarization method using the document level similarity based on embeddings, or distributed representations of words, where we assume that an embedding of each word can represent its "meaning."We formalize our task as the problem of maximizing a submodular function defined by the negative summation of the nearest neighbors' distances on embedding distributions, each of which represents a set of word embeddings in a document.We proved the submodularity of our objective function and that our problem is asymptotically related to the KL-divergence between the probability density functions that correspond to a document and its summary in a continuous space.An experiment using a real dataset demonstrated that our method performed better than the existing method based on sentence-level similarity.

In this study, we examine the effects of using a game for encouraging the use of a spoken dialogue system.As a case study, we developed a word-chain game, called Shiritori in Japanese, and released the game as a module in a Japanese Android/iOS app, Onsei-Assist, which is a Siri-like personal assistant based on a spoken dialogue technology.We analyzed the log after the release and confirmed that the game can increase the number of user utterances.Furthermore, we discovered a positive side effect, in which users who have played the game tend to begin using non-game modules.This suggests that just adding a game module to the system can improve user engagement with an assistant agent.

This paper studies the idea of removing low-frequency words from a corpus, which is a common practice to reduce computational costs, from a theoretical standpoint. Based on the assumption that a corpus follows Zipf’s law, we derive tradeoff formulae of the perplexity of k-gram models and topic models with respect to the size of the reduced vocabulary. In addition, we show an approximate behavior of each formula under certain conditions. We verify the correctness of our theory on synthetic corpora and examine the gap between theory and practice on real corpora.