Recommender systems have become ubiquitous in our digital lives, from recommending products on e-commerce websites to suggesting movies and music on streaming platforms. Existing recommendation datasets, such as Amazon Product Reviews and MovieLens, greatly facilitated the research and development of recommender systems in their respective domains. While the number of mobile users and applications (aka apps) has increased exponentially over the past decade, research in mobile app recommender systems has been significantly constrained, primarily due to the lack of high-quality benchmark datasets, as opposed to recommendations for products, movies, and news. To facilitate research for app recommendation systems, we introduce a large-scale dataset, called MobileRec. We constructed MobileRec from users' activity on the Google play store. MobileRec contains 19.3 million user interactions (i.e., user reviews on apps) with over 10K unique apps across 48 categories. MobileRec records the sequential activity of a total of 0.7 million distinct users. Each of these users has interacted with no fewer than five distinct apps, which stands in contrast to previous datasets on mobile apps that recorded only a single interaction per user. Furthermore, MobileRec presents users' ratings as well as sentiments on installed apps, and each app contains rich metadata such as app name, category, description, and overall rating, among others. We demonstrate that MobileRec can serve as an excellent testbed for app recommendation through a comparative study of several state-of-the-art recommendation approaches. The MobileRec dataset is available at https://huggingface.co/datasets/recmeapp/mobilerec.

Slot filling is one of the critical tasks in modern conversational systems. The majority of existing literature employs supervised learning methods, which require labeled training data for each new domain. Zero-shot learning and weak supervision approaches, among others, have shown promise as alternatives to manual labeling. Nonetheless, these learning paradigms are significantly inferior to supervised learning approaches in terms of performance. To minimize this performance gap and demonstrate the possibility of open-domain slot filling, we propose a Self-supervised Co-training framework, called , that requires zero in-domain manually labeled training examples and works in three phases. Phase one acquires two sets of complementary pseudo labels automatically. Phase two leverages the power of the pre-trained language model BERT, by adapting it for the slot filling task using these sets of pseudo labels. In phase three, we introduce a self-supervised co-training mechanism, where both models automatically select high-confidence soft labels to further improve the performance of the other in an iterative fashion. Our thorough evaluations show that outperforms state-of-the-art models by 45.57% and 37.56% on SGD and MultiWoZ datasets, respectively. Moreover, our proposed framework achieves comparable performance when compared to state-of-the-art fully supervised models.

Mobile app stores produce a tremendous amount of data in the form of user reviews, which is a huge source of user requirements and sentiments; such reviews allow app developers to proactively address issues in their apps. However, only a small number of reviews capture common issues and sentiments which creates a need for automatically identifying prominent reviews. Unfortunately, most existing work in text ranking and popularity prediction focuses on social contexts where other signals are available, which renders such works ineffective in the context of app reviews. In this work, we propose a new framework, PPrior, that enables proactive prioritization of app issues through identifying prominent reviews (ones predicted to receive a large number of votes in a given time window). Predicting highly-voted reviews is challenging given that, unlike social posts, social network features of users are not available. Moreover, there is an issue of class imbalance, since a large number of user reviews receive little to no votes. PPrior employs a pre-trained T5 model and works in three phases. Phase one adapts the pre-trained T5 model to the user reviews data in a self-supervised fashion. In phase two, we leverage contrastive training to learn a generic and task-independent representation of user reviews. Phase three uses radius neighbors classifier t o m ake t he final predictions. This phase also uses FAISS index for scalability and efficient search. To conduct extensive experiments, we acquired a large dataset of over 2.1 million user reviews from Google Play. Our experimental results demonstrate the effectiveness of the proposed framework when compared against several state-of-the-art approaches. Moreover, the accuracy of PPrior in predicting prominent reviews is comparable to that of experienced app developers.

Task-oriented dialog systems enable users to accomplish tasks using natural language. State-of-the-art systems respond to users in the same way regardless of their personalities, although personalizing dialogues can lead to higher levels of adoption and better user experiences. Building personalized dialog systems is an important, yet challenging endeavor, and only a handful of works took on the challenge. Most existing works rely on supervised learning approaches and require laborious and expensive labeled training data for each user profile. Additionally, collecting and labeling data for each user profile is virtually impossible. In this work, we propose a novel framework, P-ToD, to personalize task-oriented dialog systems capable of adapting to a wide range of user profiles in an unsupervised fashion using a zero-shot generalizable reward function. P-ToD uses a pre-trained GPT-2 as a backbone model and works in three phases. Phase one performs task-specific training. Phase two kicks off unsupervised personalization by leveraging the proximal policy optimization algorithm that performs policy gradients guided by the zero-shot generalizable reward function. Our novel reward function can quantify the quality of the generated responses even for unseen profiles. The optional final phase fine-tunes the personalized model using a few labeled training examples. We conduct extensive experimental analysis using the personalized bAbI dialogue benchmark for five tasks and up to 180 diverse user profiles. The experimental results demonstrate that P-ToD, even when it had access to zero labeled examples, outperforms state-of-the-art supervised personalization models and achieves competitive performance on BLEU and ROUGE metrics when compared to a strong fully-supervised GPT-2 baseline.

This paper introduces the open-source Beast system for scalable exploratory data science on big spatio-temporal data. Beast is based on well-established research and has been released to assist the research community with analyzing big spatio-temporal data. Beast provides a set of extensible components that naturally integrate with Spark to build exploratory data science pipelines. Beast can install in less than a minute on an existing Spark cluster and provides a wide array of features including loading vector and raster data represented in standard file formats, synthetic data generation for benchmarking, load-balanced spatial partitioning, data summarization, interactive visualization, and more. Beast builds on several research projects; its goal is to make all this research widely available to researchers in one integrative and coherent system.

Identifying user intents from natural language utterances is a crucial step in conversational systems that has been extensively studied as a supervised classification problem. However, in practice, new intents emerge after deploying an intent detection model. Thus, these models should seamlessly adapt and classify utterances with both seen and unseen intents -- unseen intents emerge after deployment and they do not have training data. The few existing models that target this setting rely heavily on the training data of seen intents and consequently overfit to these intents, resulting in a bias to misclassify utterances with unseen intents into seen ones. We propose RIDE: an intent detection model that leverages commonsense knowledge in an unsupervised fashion to overcome the issue of training data scarcity. RIDE computes robust and generalizable relationship meta-features that capture deep semantic relationships between utterances and intent labels; these features are computed by considering how the concepts in an utterance are linked to those in an intent label via commonsense knowledge. Our extensive experimental analysis on three widely-used intent detection benchmarks shows that relationship meta-features significantly improve the detection of both seen and unseen intents and that RIDE outperforms the state-of-the-art models.

Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems. Supervised approaches have proven effective at tackling this challenge, but they need a significant amount of labeled training data in a given domain. However, new domains (i.e., unseen in training) may emerge after deployment. Thus, it is imperative that these models seamlessly adapt and fill slots from both seen and unseen domains – unseen domains contain unseen slot types with no training data, and even seen slots in unseen domains are typically presented in different contexts. This setting is commonly referred to as zero-shot slot filling. Little work has focused on this setting, with limited experimental evaluation. Existing models that mainly rely on context-independent embedding-based similarity measures fail to detect slot values in unseen domains or do so only partially. We propose a new zero-shot slot filling neural model, , which works in three steps. Step one acquires domain-oblivious, context-aware representations of utterance words by exploiting (a) linguistic features such as part-of-speech tags; (b) named entity recognition cues; and (c) contextual embeddings from pre-trained language models. Step two fine-tunes these rich representations and produces slot-independent tags for each word. Step three exploits generalizable context-aware utterance-slot similarity features at the word level, uses slot-independent tags, and contextualizes them to produce slot-specific predictions for each word. Our thorough evaluation on four diverse public datasets demonstrates that our approach consistently outperforms state-of-the-art models by 17.52%, 22.15%, 17.42%, and 17.95% on average for unseen domains on SNIPS, ATIS, MultiWOZ, and SGD datasets, respectively.

Hundreds of thousands of mobile app users post their reviews online. Responding to user reviews promptly and satisfactorily improves application ratings, which is key to application popularity and success. The proliferation of such reviews makes it virtually impossible for developers to keep up with responding manually. To address this challenge, recent work has shown the possibility of automatic response generation by training a seq2seq model with a large collection of review-response pairs. However, because the training review-response pairs are aggregated from many different apps, it remains challenging for such models to generate app-specific responses, which, on the other hand, are often desirable as appwes have different features and concerns. Solving the challenge by simply building an app-specific generative model per app (i.e., training the model with review-response pairs of a single app) may be insufficient because individual apps have limited review-response pairs, and such pairs typically lack the relevant information needed to respond to a new review.To enable app-specific response generation, this work proposes AARSYNTH: an app-aware response synthesis system. The key idea behind AARSYNTH is to augment the seq2seq model with information specific to a given app. Given a new user review, AARSYNTH first retrieves the top-K most relevant app reviews and the most relevant snippet from the app description. The retrieved information and the new user review are then fed into a fused machine learning model that integrates the seq2seq model with a machine reading comprehension model. The latter helps digest the retrieved reviews and app description. Finally, the fused model generates a response that is customized to the given app. We evaluated AARSYNTH using a large corpus of reviews and responses from Google Play. The results show that AARSYNTH outperforms the state-of-the-art system by 22.2% on BLEU-4 score. Furthermore, our human study shows that AARSYNTH produces a statistically significant improvement in response quality compared to the state-of-the-art system.

Paraphrasing is expressing the meaning of an input sentence in different wording while maintaining fluency (i.e., grammatical and syntactical correctness). Most existing work on paraphrasing use supervised models that are limited to specific domains (e.g., image captions). Such models can neither be straightforwardly transferred to other domains nor generalize well, and creating labeled training data for new domains is expensive and laborious. The need for paraphrasing across different domains and the scarcity of labeled training data in many such domains call for exploring unsupervised paraphrase generation methods. We propose Progressive Unsupervised Paraphrasing (PUP): a novel unsupervised paraphrase generation method based on deep reinforcement learning (DRL). PUP uses a variational autoencoder (trained using a non-parallel corpus) to generate a seed paraphrase that warm-starts the DRL model. Then, PUP progressively tunes the seed paraphrase guided by our novel reward function which combines semantic adequacy, language fluency, and expression diversity measures to quantify the quality of the generated paraphrases in each iteration without needing parallel sentences. Our extensive experimental evaluation shows that PUP outperforms unsupervised state-of-the-art paraphrasing techniques in terms of both automatic metrics and user studies on four real datasets. We also show that PUP outperforms domain-adapted supervised algorithms on several datasets. Our evaluation also shows that PUP achieves a great trade-off between semantic similarity and diversity of expression.

Selectivity estimation is one of the common research problems for big spatial data, where the objective is to quickly estimate the number of records in a given query range. Euler histogram has been used to answer the selectivity estimation queries for objects with extents such as rectangles in constant time. However, it is only accurate when the query range is aligned with the histogram grid lines. In this paper, we improve the Euler histogram to accurately answer arbitrary queries, i.e., even if they do not align with the histogram grid lines. The improved histogram, called Euler++, has the same space and time complexity as the regular Euler histogram and provides a better accuracy for objects with extents. We use both real and synthetic datasets for extensive experiments, and show that the proposed technique, Euler++, consistently outperforms the existing ones, while still providing answer in constant time.

The increasing amount of spatial data calls for new scalable query processing techniques. One of the techniques that are getting attention is data synopsis , which summarizes the data using samples or histograms and computes an approximate answer based on the synopsis. This general technique is used in selectivity estimation, clustering, partitioning, load balancing, and visualization, among others. This paper experimentally studies four spatial data synopsis techniques for three common data analysis problems, namely, selectivity estimation, k-means clustering, and spatial partitioning. We run an extensive experimental evaluation on both real and synthetic datasets of up to 2.7 billion records to study the trade-offs between the synopsis methods and their applicability in big spatial data analysis. For each of the three problems, we compare with baseline techniques that operate on the whole dataset and evaluate the synopsis generation time, the time for computing an approximate answer on the synopsis, and the accuracy of the result. We present our observations about when each synopsis technique performs best.