Searcharxiv⌕ Search

arXiv subjects

An Yan

Publications and source records attributed to An Yan.

43 records · Page 3Linked to original sources

Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation

One of the most challenging topics in Natural Language Processing (NLP) is visually-grounded language understanding and reasoning. Outdoor vision-and-language navigation (VLN) is such a task where an agent follows natural language instructions and navigates a real-life urban environment. Due to the lack of human-annotated instructions that illustrate intricate urban scenes, outdoor VLN remains a challenging task to solve. This paper introduces a Multimodal Text Style Transfer (MTST) learning approach and leverages external multimodal resources to mitigate data scarcity in outdoor navigation tasks. We first enrich the navigation data by transferring the style of the instructions generated by Google Maps API, then pre-train the navigator with the augmented external outdoor navigation dataset. Experimental results show that our MTST learning approach is model-agnostic, and our MTST approach significantly outperforms the baseline models on the outdoor VLN task, improving task completion rate by 8.7% relatively on the test set.

cs.CL↗

L2C: Describing Visual Differences Needs Semantic Understanding of Individuals

Recent advances in language and vision push forward the research of captioning a single image to describing visual differences between image pairs. Suppose there are two images, I_1 and I_2, and the task is to generate a description W_{1,2} comparing them, existing methods directly model { I_1, I_2 } -> W_{1,2} mapping without the semantic understanding of individuals. In this paper, we introduce a Learning-to-Compare (L2C) model, which learns to understand the semantic structures of these two images and compare them while learning to describe each one. We demonstrate that L2C benefits from a comparison between explicit semantic representations and single-image captions, and generalizes better on the new testing image pairs. It outperforms the baseline on both automatic evaluation and human evaluation for the Birds-to-Words dataset.

cs.CV↗

Cross-Lingual Vision-Language Navigation

Commanding a robot to navigate with natural language instructions is a long-term goal for grounded language understanding and robotics. But the dominant language is English, according to previous studies on vision-language navigation (VLN). To go beyond English and serve people speaking different languages, we collect a bilingual Room-to-Room (BL-R2R) dataset, extending the original benchmark with new Chinese instructions. Based on this newly introduced dataset, we study how an agent can be trained on existing English instructions but navigate effectively with another language under a zero-shot learning scenario. Without any training data of the target language, our model shows competitive results even compared to a model with full access to the target language training data. Moreover, we investigate the transferring ability of our model when given a certain amount of target language training data.

cs.CL↗

CosRec: 2D Convolutional Neural Networks for Sequential Recommendation

Sequential patterns play an important role in building modern recommender systems. To this end, several recommender systems have been built on top of Markov Chains and Recurrent Models (among others). Although these sequential models have proven successful at a range of tasks, they still struggle to uncover complex relationships nested in user purchase histories. In this paper, we argue that modeling pairwise relationships directly leads to an efficient representation of sequential features and captures complex item correlations. Specifically, we propose a 2D convolutional network for sequential recommendation (CosRec). It encodes a sequence of items into a three-way tensor; learns local features using 2D convolutional filters; and aggregates high-order interactions in a feedforward manner. Quantitative results on two public datasets show that our method outperforms both conventional methods and recent sequence-based approaches, achieving state-of-the-art performance on various evaluation metrics.

cs.IR↗

FairST: Equitable Spatial and Temporal Demand Prediction for New Mobility Systems

Emerging transportation modes, including car-sharing, bike-sharing, and ride-hailing, are transforming urban mobility but have been shown to reinforce socioeconomic inequities. Spatiotemporal demand prediction models for these new mobility regimes must therefore consider fairness as a first-class design requirement. We present FairST, a fairness-aware model for predicting demand for new mobility systems. Our approach utilizes 1D, 2D and 3D convolutions to integrate various urban features and learn the spatial-temporal dynamics of a mobility system, but we include fairness metrics as a form of regularization to make the predictions more equitable across demographic groups. We propose two novel spatiotemporal fairness metrics, a region-based fairness gap (RFG) and an individual-based fairness gap (IFG). Both quantify equity in a spatiotemporal context, but vary by whether demographics are labeled at the region level (RFG) or whether population distribution information is available (IFG). Experimental results on real bike share and ride share datasets demonstrate the effectiveness of the proposed model: FairST not only reduces the fairness gap by more than 80%, but can surprisingly achieve better accuracy than state-of-the-art yet fairness-oblivious methods including LSTMs, ConvLSTMs, and 3D CNN.

cs.CY↗

Mining Open Government Data Used in Scientific Research

In the following paper, we describe results from mining citations, mentions, and links to open government data (OGD) in peer-reviewed literature. We inductively develop a method for categorizing how OGD are used by different research communities, and provide descriptive statistics about the publication years, publication outlets, and OGD sources. Our results demonstrate that, 1. The use of OGD in research is steadily increasing from 2009 to 2016; 2. Researchers use OGD from 96 different open government data portals, with data.gov.uk and data.gov being the most frequent sources; and, 3.Contrary to previous findings, we provide evidence suggesting that OGD from developing nations, notably India and Kenya, are being frequently used to fuel scientific discoveries. The findings of this paper contribute to ongoing research agendas aimed at tracking the impact of open government data initiatives, and provides an initial description of how open government data are valuable to diverse scientific research communities.

cs.CY↗

Predicting Abandonment in Online Coding Tutorials

Learners regularly abandon online coding tutorials when they get bored or frustrated, but there are few techniques for anticipating this abandonment to intervene. In this paper, we examine the feasibility of predicting abandonment with machine-learned classifiers. Using interaction logs from an online programming game, we extracted a collection of features that are potentially related to learner abandonment and engagement, then developed classifiers for each level. Across the first five levels of the game, our classifiers successfully predicted 61% to 76% of learners who did not complete the next level, achieving an average AUC of 0.68. In these classifiers, features negatively associated with abandonment included account activation and help-seeking behaviors, whereas features positively associated with abandonment included features indicating difficulty and disengagement. These findings highlight the feasibility of providing timely intervention to learners likely to quit.

cs.LG↗