Paper Group ANR 292
Iterative Dual Domain Adaptation for Neural Machine Translation. Learning Semantic Vector Representations of Source Code via a Siamese Neural Network. Policy Targeting under Network Interference. Phase-based Minimalist Parsing and complexity in non-local dependencies. Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Networ …
Iterative Dual Domain Adaptation for Neural Machine Translation
| Title | Iterative Dual Domain Adaptation for Neural Machine Translation |
| Authors | Jiali Zeng, Yang Liu, Jinsong Su, Yubin Ge, Yaojie Lu, Yongjing Yin, Jiebo Luo |
| Abstract | Previous studies on the domain adaptation for neural machine translation (NMT) mainly focus on the one-pass transferring out-of-domain translation knowledge to in-domain NMT model. In this paper, we argue that such a strategy fails to fully extract the domain-shared translation knowledge, and repeatedly utilizing corpora of different domains can lead to better distillation of domain-shared translation knowledge. To this end, we propose an iterative dual domain adaptation framework for NMT. Specifically, we first pre-train in-domain and out-of-domain NMT models using their own training corpora respectively, and then iteratively perform bidirectional translation knowledge transfer (from in-domain to out-of-domain and then vice versa) based on knowledge distillation until the in-domain NMT model convergences. Furthermore, we extend the proposed framework to the scenario of multiple out-of-domain training corpora, where the above-mentioned transfer is performed sequentially between the in-domain and each out-of-domain NMT models in the ascending order of their domain similarities. Empirical results on Chinese-English and English-German translation tasks demonstrate the effectiveness of our framework. |
| Tasks | Domain Adaptation, Machine Translation, Transfer Learning |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07239v1 |
| https://arxiv.org/pdf/1912.07239v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-dual-domain-adaptation-for-neural-1 |
| Repo | |
| Framework | |
Learning Semantic Vector Representations of Source Code via a Siamese Neural Network
| Title | Learning Semantic Vector Representations of Source Code via a Siamese Neural Network |
| Authors | David Wehr, Halley Fede, Eleanor Pence, Bo Zhang, Guilherme Ferreira, John Walczyk, Joseph Hughes |
| Abstract | The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code. In this work, we explore the use of a Siamese recurrent neural network model on Python source code to create vectors which capture the semantics of code. We evaluate the quality of embeddings by identifying which problem from a programming competition the code solves. Our model significantly outperforms a bag-of-tokens embedding, providing promising results for improving code embeddings that can be used in future software engineering tasks. |
| Tasks | |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11968v1 |
| http://arxiv.org/pdf/1904.11968v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-semantic-vector-representations-of |
| Repo | |
| Framework | |
Policy Targeting under Network Interference
| Title | Policy Targeting under Network Interference |
| Authors | Davide Viviano |
| Abstract | This paper discusses the problem of estimating individualized treatment allocation rules under network interference. I propose a method with several attractive features for applications: the method (i) exploits heterogeneity in treatment and spillover effects to construct targeting rules; (ii) it does not rely on the correct specification of a particular structural model; (iii) it accommodates arbitrary constraints on the policy function and capacity constraints on the number of treated units, and (iv) it can also be implemented when network information is not accessible to policy-makers. I establish a set of guarantees on the utilitarian regret, i.e., the difference between the average social welfare attained by the estimated policy function and the maximum attainable welfare, in the presence of network interference. The proposed method achieves the min-max regret-optimal rate in scenarios of practical and theoretical interest. I provide a mixed-integer linear program formulation under interference which can be solved using off-the-shelf algorithms. I discuss the empirical performance in simulations and illustrate the advantages of the method for targeting information on social networks. |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10258v5 |
| https://arxiv.org/pdf/1906.10258v5.pdf | |
| PWC | https://paperswithcode.com/paper/policy-targeting-under-network-interference |
| Repo | |
| Framework | |
Phase-based Minimalist Parsing and complexity in non-local dependencies
| Title | Phase-based Minimalist Parsing and complexity in non-local dependencies |
| Authors | Cristiano Chesi |
| Abstract | A cognitively plausible parsing algorithm should perform like the human parser in critical contexts. Here I propose an adaptation of Earley’s parsing algorithm, suitable for Phase-based Minimalist Grammars (PMG, Chesi 2012), that is able to predict complexity effects in performance. Focusing on self-paced reading experiments of object clefts sentences (Warren & Gibson 2005) I will associate to parsing a complexity metric based on cued features to be retrieved at the verb segment (Feature Retrieval & Encoding Cost, FREC). FREC is crucially based on the usage of memory predicted by the discussed parsing algorithm and it correctly fits with the reading time revealed. |
| Tasks | |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00908v1 |
| https://arxiv.org/pdf/1906.00908v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600908 |
| Repo | |
| Framework | |
Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Network
| Title | Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Network |
| Authors | Rui Cao, Qian Zhang, Jiasong Zhu, Qing Li, Qingquan Li, Bozhi Liu, Guoping Qiu |
| Abstract | With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data. In this letter, we present a novel content-based remote sensing image retrieval method based on Triplet deep metric learning convolutional neural network (CNN). By constructing a Triplet network with metric learning objective function, we extract the representative features of the images in a semantic space in which images from the same class are close to each other while those from different classes are far apart. In such a semantic space, simple metric measures such as Euclidean distance can be used directly to compare the similarity of images and effectively retrieve images of the same class. We also investigate a supervised and an unsupervised learning methods for reducing the dimensionality of the learned semantic features. We present comprehensive experimental results on two publicly available remote sensing image retrieval datasets and show that our method significantly outperforms state-of-the-art. |
| Tasks | Image Retrieval, Metric Learning |
| Published | 2019-02-15 |
| URL | http://arxiv.org/abs/1902.05818v1 |
| http://arxiv.org/pdf/1902.05818v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-remote-sensing-image-retrieval-with |
| Repo | |
| Framework | |
CAIL2019-SCM: A Dataset of Similar Case Matching in Legal Domain
| Title | CAIL2019-SCM: A Dataset of Similar Case Matching in Legal Domain |
| Authors | Chaojun Xiao, Haoxi Zhong, Zhipeng Guo, Cunchao Tu, Zhiyuan Liu, Maosong Sun, Tianyang Zhang, Xianpei Han, Zhen Hu, Heng Wang, Jianfeng Xu |
| Abstract | In this paper, we introduce CAIL2019-SCM, Chinese AI and Law 2019 Similar Case Matching dataset. CAIL2019-SCM contains 8,964 triplets of cases published by the Supreme People’s Court of China. CAIL2019-SCM focuses on detecting similar cases, and the participants are required to check which two cases are more similar in the triplets. There are 711 teams who participated in this year’s competition, and the best team has reached a score of 71.88. We have also implemented several baselines to help researchers better understand this task. The dataset and more details can be found from https://github.com/china-ai-law-challenge/CAIL2019/tree/master/scm. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08962v3 |
| https://arxiv.org/pdf/1911.08962v3.pdf | |
| PWC | https://paperswithcode.com/paper/cail2019-scm-a-dataset-of-similar-case |
| Repo | |
| Framework | |
Data Complexity and Rewritability of Ontology-Mediated Queries in Metric Temporal Logic under the Event-Based Semantics (Full Version)
| Title | Data Complexity and Rewritability of Ontology-Mediated Queries in Metric Temporal Logic under the Event-Based Semantics (Full Version) |
| Authors | Vladislav Ryzhikov, Przemyslaw Andrzej Walega, Michael Zakharyaschev |
| Abstract | We investigate the data complexity of answering queries mediated by metric temporal logic ontologies under the event-based semantics assuming that data instances are finite timed words timestamped with binary fractions. We identify classes of ontology-mediated queries answering which can be done in AC0, NC1, L, NL, P, and coNP for data complexity, provide their rewritings to first-order logic and its extensions with primitive recursion, transitive closure or datalog, and establish lower complexity bounds. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12990v2 |
| https://arxiv.org/pdf/1905.12990v2.pdf | |
| PWC | https://paperswithcode.com/paper/data-complexity-and-rewritability-of-ontology |
| Repo | |
| Framework | |
Towards Run Time Estimation of the Gaussian Chemistry Code for SEAGrid Science Gateway
| Title | Towards Run Time Estimation of the Gaussian Chemistry Code for SEAGrid Science Gateway |
| Authors | Angel Beltre, Shehtab Zaman, Kenneth Chiu, Sudhakar Pamidighantam, Xingye Qiao, Madhusudhan Govindaraju |
| Abstract | Accurate estimation of the run time of computational codes has a number of significant advantages for scientific computing. It is required information for optimal resource allocation, improving turnaround times and utilization of science gateways. Furthermore, it allows users to better plan and schedule their research, streamlining workflows and improving the overall productivity of cyberinfrastructure. Predicting run time is challenging, however. The inputs to scientific codes can be complex and high dimensional. Their relationship to the run time may be highly non-linear, and, in the most general case is completely arbitrary and thus unpredictable (i.e., simply a random mapping from inputs to run time). Most codes are not so arbitrary, however, and there has been significant prior research on predicting the run time of applications and workloads. Such predictions are generally application-specific, however. In this paper, we focus on the Gaussian computational chemistry code. We characterize a data set of runs from the SEAGrid science gateway with a number of different studies. We also explore a number of different potential regression methods and present promising future directions. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.04286v1 |
| https://arxiv.org/pdf/1906.04286v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-run-time-estimation-of-the-gaussian |
| Repo | |
| Framework | |
Sparse Depth Enhanced Direct Thermal-infrared SLAM Beyond the Visible Spectrum
| Title | Sparse Depth Enhanced Direct Thermal-infrared SLAM Beyond the Visible Spectrum |
| Authors | Young-Sik Shin, Ayoung Kim |
| Abstract | In this paper, we propose a thermal-infrared simultaneous localization and mapping (SLAM) system enhanced by sparse depth measurements from Light Detection and Ranging (LiDAR). Thermal-infrared cameras are relatively robust against fog, smoke, and dynamic lighting conditions compared to RGB cameras operating under the visible spectrum. Due to the advantages of thermal-infrared cameras, exploiting them for motion estimation and mapping is highly appealing. However, operating a thermal-infrared camera directly in existing vision-based methods is difficult because of the modality difference. This paper proposes a method to use sparse depth measurement for 6-DOF motion estimation by directly tracking under 14- bit raw measurement of the thermal camera. In addition, we perform a refinement to improve the local accuracy and include a loop closure to maintain global consistency. The experimental results demonstrate that the system is not only robust under various lighting conditions such as day and night, but also overcomes the scale problem of monocular cameras. The video is available at https://youtu.be/oO7lT3uAzLc. |
| Tasks | Motion Estimation, Simultaneous Localization and Mapping |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10892v1 |
| http://arxiv.org/pdf/1902.10892v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-depth-enhanced-direct-thermal-infrared |
| Repo | |
| Framework | |
Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks
| Title | Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks |
| Authors | Omer Berat Sezer, Ahmet Murat Ozbayoglu |
| Abstract | Even though computational intelligence techniques have been extensively utilized in financial trading systems, almost all developed models use the time series data for price prediction or identifying buy-sell points. However, in this study we decided to use 2-D stock bar chart images directly without introducing any additional time series associated with the underlying stock. We propose a novel algorithmic trading model CNN-BI (Convolutional Neural Network with Bar Images) using a 2-D Convolutional Neural Network. We generated 2-D images of sliding windows of 30-day bar charts for Dow 30 stocks and trained a deep Convolutional Neural Network (CNN) model for our algorithmic trading model. We tested our model separately between 2007-2012 and 2012-2017 for representing different market conditions. The results indicate that the model was able to outperform Buy and Hold strategy, especially in trendless or bear markets. Since this is a preliminary study and probably one of the first attempts using such an unconventional approach, there is always potential for improvement. Overall, the results are promising and the model might be integrated as part of an ensemble trading model combined with different strategies. |
| Tasks | Time Series |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.04610v1 |
| http://arxiv.org/pdf/1903.04610v1.pdf | |
| PWC | https://paperswithcode.com/paper/financial-trading-model-with-stock-bar-chart |
| Repo | |
| Framework | |
Variational Smoothing in Recurrent Neural Network Language Models
| Title | Variational Smoothing in Recurrent Neural Network Language Models |
| Authors | Lingpeng Kong, Gabor Melis, Wang Ling, Lei Yu, Dani Yogatama |
| Abstract | We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017). We show that each variant of data noising is an instance of Bayesian recurrent neural networks with a particular variational distribution (i.e., a mixture of Gaussians whose weights depend on statistics derived from the corpus such as the unigram distribution). We use this insight to propose a more principled method to apply at prediction time and propose natural extensions to data noising under the variational framework. In particular, we propose variational smoothing with tied input and output embedding matrices and an element-wise variational smoothing method. We empirically verify our analysis on two benchmark language modeling datasets and demonstrate performance improvements over existing data noising methods. |
| Tasks | Language Modelling |
| Published | 2019-01-27 |
| URL | http://arxiv.org/abs/1901.09296v1 |
| http://arxiv.org/pdf/1901.09296v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-smoothing-in-recurrent-neural |
| Repo | |
| Framework | |
Extracting Incentives from Black-Box Decisions
| Title | Extracting Incentives from Black-Box Decisions |
| Authors | Yonadav Shavit, William S. Moses |
| Abstract | An algorithmic decision-maker incentivizes people to act in certain ways to receive better decisions. These incentives can dramatically influence subjects’ behaviors and lives, and it is important that both decision-makers and decision-recipients have clarity on which actions are incentivized by the chosen model. While for linear functions, the changes a subject is incentivized to make may be clear, we prove that for many non-linear functions (e.g. neural networks, random forests), classical methods for interpreting the behavior of models (e.g. input gradients) provide poor advice to individuals on which actions they should take. In this work, we propose a mathematical framework for understanding algorithmic incentives as the challenge of solving a Markov Decision Process, where the state includes the set of input features, and the reward is a function of the model’s output. We can then leverage the many toolkits for solving MDPs (e.g. tree-based planning, reinforcement learning) to identify the optimal actions each individual is incentivized to take to improve their decision under a given model. We demonstrate the utility of our method by estimating the maximally-incentivized actions in two real-world settings: a recidivism risk predictor we train using ProPublica’s COMPAS dataset, and an online credit scoring tool published by the Fair Isaac Corporation (FICO). |
| Tasks | |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.05664v1 |
| https://arxiv.org/pdf/1910.05664v1.pdf | |
| PWC | https://paperswithcode.com/paper/extracting-incentives-from-black-box |
| Repo | |
| Framework | |
Two-step Constructive Approaches for Dungeon Generation
| Title | Two-step Constructive Approaches for Dungeon Generation |
| Authors | Michael Cerny Green, Ahmed Khalifa, Athoug Alsoughayer, Divyesh Surana, Antonios Liapis, Julian Togelius |
| Abstract | This paper presents a two-step generative approach for creating dungeons in the rogue-like puzzle game MiniDungeons 2. Generation is split into two steps, initially producing the architectural layout of the level as its walls and floor tiles, and then furnishing it with game objects representing the player’s start and goal position, challenges and rewards. Three layout creators and three furnishers are introduced in this paper, which can be combined in different ways in the two-step generative process for producing diverse dungeons levels. Layout creators generate the floors and walls of a level, while furnishers populate it with monsters, traps, and treasures. We test the generated levels on several expressivity measures, and in simulations with procedural persona agents. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04660v1 |
| https://arxiv.org/pdf/1906.04660v1.pdf | |
| PWC | https://paperswithcode.com/paper/two-step-constructive-approaches-for-dungeon |
| Repo | |
| Framework | |
Modeling Theory of Mind in Multi-Agent Games Using Adaptive Feedback Control
| Title | Modeling Theory of Mind in Multi-Agent Games Using Adaptive Feedback Control |
| Authors | Ismael T. Freire, Xerxes D. Arsiwalla, Jordi-Ysard Puigbò, Paul Verschure |
| Abstract | A major challenge in cognitive science and AI has been to understand how autonomous agents might acquire and predict behavioral and mental states of other agents in the course of complex social interactions. How does such an agent model the goals, beliefs, and actions of other agents it interacts with? What are the computational principles to model a Theory of Mind (ToM)? Deep learning approaches to address these questions fall short of a better understanding of the problem. In part, this is due to the black-box nature of deep networks, wherein computational mechanisms of ToM are not readily revealed. Here, we consider alternative hypotheses seeking to model how the brain might realize a ToM. In particular, we propose embodied and situated agent models based on distributed adaptive control theory to predict actions of other agents in five different game theoretic tasks (Harmony Game, Hawk-Dove, Stag-Hunt, Prisoner’s Dilemma and Battle of the Exes). Our multi-layer control models implement top-down predictions from adaptive to reactive layers of control and bottom-up error feedback from reactive to adaptive layers. We test cooperative and competitive strategies among seven different agent models (cooperative, greedy, tit-for-tat, reinforcement-based, rational, predictive and other’s-model agents). We show that, compared to pure reinforcement-based strategies, probabilistic learning agents modeled on rational, predictive and other’s-model phenotypes perform better in game-theoretic metrics across tasks. Our autonomous multi-agent models capture systems-level processes underlying a ToM and highlight architectural principles of ToM from a control-theoretic perspective. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.13225v1 |
| https://arxiv.org/pdf/1905.13225v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-theory-of-mind-in-multi-agent-games |
| Repo | |
| Framework | |
Body-worn triaxial accelerometer coherence and reliability related to static posturography in unilateral vestibular failure
| Title | Body-worn triaxial accelerometer coherence and reliability related to static posturography in unilateral vestibular failure |
| Authors | M. Alessandrini, A. Micarelli, A. Viziano, I. Pavone, G. Costantini, D. Casali, F. Paolizzo, G. Saggio |
| Abstract | Due to the fact that no study to date has shown the experimental validity of ACC-based measures of body sway with respect to posturography for subjects with vestibular deficits, the aim of the present study was: i) to develop and validate a practical tool that can allow clinicians to measure postural sway derangements in an otoneurological setting by ACC, and ii) to provide reliable, sensitive and accurate automatic analysis of sway that could help in discriminating unilateral vestibular failure (UVF) patients. Thus, a group of 13 patients (seven females, 6 males; mean age 48.6 +/- 6.4 years) affected for at least 6 months by UVF and 13 matched healthy subjects were instructed to maintain an upright position during a static forceplate-based posturography (FBP) acquisition while wearing a Movit sensor (by Captiks) with 3-D accelerometers mounted on the posterior trunk near the body centre of mass. Pearson product moment correlation demonstrated a high level of correspondence of four time-domain and three frequency-domain measures extracted by ACC and FBP testing; in addition, t-test demonstrated that two ACC-based time- and frequency-domain parameters were reliable measures in discriminating UVF subjects. These aspects, overall, should further highlight the attention of clinicians and researchers to this kind of sway recording technique in the field of otoneurological disorders by considering the possibility to enrich the amount of quantitative and qualitative information useful for discrimination, diagnosis and treatment of UVF. In conclusion, we believe the present ACC-based measurement of sway offers a patient-friendly, reliable, inexpensive and efficient alternative recording technique that is useful - together with clinical balance and mobility tests - in various circumstances, as well as in outcome studies involving diagnosis, follow-up and rehabilitation of UVF patients. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.11166v2 |
| https://arxiv.org/pdf/1907.11166v2.pdf | |
| PWC | https://paperswithcode.com/paper/body-worn-triaxial-accelerometer-coherence |
| Repo | |
| Framework | |
