Paper Group NANR 221
Automated Text Simplification as a Preprocessing Step for Machine Translation into an Under-resourced Language. Leveraging Sublanguage Features for the Semantic Categorization of Clinical Terms. NEURAL MALWARE CONTROL WITH DEEP REINFORCEMENT LEARNING. Learning Auctions with Robust Incentive Guarantees. Temporal Structure Mining for Weakly Supervise …
Automated Text Simplification as a Preprocessing Step for Machine Translation into an Under-resourced Language
| Title | Automated Text Simplification as a Preprocessing Step for Machine Translation into an Under-resourced Language |
| Authors | Sanja {\v{S}}tajner, Maja Popovi{'c} |
| Abstract | In this work, we investigate the possibility of using fully automatic text simplification system on the English source in machine translation (MT) for improving its translation into an under-resourced language. We use the state-of-the-art automatic text simplification (ATS) system for lexically and syntactically simplifying source sentences, which are then translated with two state-of-the-art English-to-Serbian MT systems, the phrase-based MT (PBMT) and the neural MT (NMT). We explore three different scenarios for using the ATS in MT: (1) using the raw output of the ATS; (2) automatically filtering out the sentences with low grammaticality and meaning preservation scores; and (3) performing a minimal manual correction of the ATS output. Our results show improvement in fluency of the translation regardless of the chosen scenario, and difference in success of the three scenarios depending on the MT approach used (PBMT or NMT) with regards to improving translation fluency and post-editing effort. |
| Tasks | Machine Translation, Text Simplification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1131/ |
| https://www.aclweb.org/anthology/R19-1131 | |
| PWC | https://paperswithcode.com/paper/automated-text-simplification-as-a |
| Repo | |
| Framework | |
Leveraging Sublanguage Features for the Semantic Categorization of Clinical Terms
| Title | Leveraging Sublanguage Features for the Semantic Categorization of Clinical Terms |
| Authors | Leonie Gr{"o}n, Ann Bertels, Kris Heylen |
| Abstract | The automatic processing of clinical documents, such as Electronic Health Records (EHRs), could benefit substantially from the enrichment of medical terminologies with terms encountered in clinical practice. To integrate such terms into existing knowledge sources, they must be linked to corresponding concepts. We present a method for the semantic categorization of clinical terms based on their surface form. We find that features based on sublanguage properties can provide valuable cues for the classification of term variants. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5022/ |
| https://www.aclweb.org/anthology/W19-5022 | |
| PWC | https://paperswithcode.com/paper/leveraging-sublanguage-features-for-the |
| Repo | |
| Framework | |
NEURAL MALWARE CONTROL WITH DEEP REINFORCEMENT LEARNING
| Title | NEURAL MALWARE CONTROL WITH DEEP REINFORCEMENT LEARNING |
| Authors | Yu Wang, Jack W. Stokes, Mady Marinescu |
| Abstract | Antimalware products are a key component in detecting malware attacks, and their engines typically execute unknown programs in a sandbox prior to running them on the native operating system. Files cannot be scanned indefinitely so the engine employs heuristics to determine when to halt execution. Previous research has investigated analyzing the sequence of system calls generated during this emulation process to predict if an unknown file is malicious, but these models require the emulation to be stopped after executing a fixed number of events from the beginning of the file. Also, these classifiers are not accurate enough to halt emulation in the middle of the file on their own. In this paper, we propose a novel algorithm which overcomes this limitation and learns the best time to halt the file’s execution based on deep reinforcement learning (DRL). Because the new DRL-based system continues to emulate the unknown file until it can make a confident decision to stop, it prevents attackers from avoiding detection by initiating malicious activity after a fixed number of system calls. Results show that the proposed malware execution control model automatically halts emulation for 91.3% of the files earlier than heuristics employed by the engine. Furthermore, classifying the files at that time improves the true positive rate by 61.5%, at a false positive rate of 1%, compared to a baseline classifier. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJg6nj09F7 |
| https://openreview.net/pdf?id=SJg6nj09F7 | |
| PWC | https://paperswithcode.com/paper/neural-malware-control-with-deep |
| Repo | |
| Framework | |
Learning Auctions with Robust Incentive Guarantees
| Title | Learning Auctions with Robust Incentive Guarantees |
| Authors | Jacob D. Abernethy, Rachel Cummings, Bhuvesh Kumar, Sam Taggart, Jamie H. Morgenstern |
| Abstract | We study the problem of learning Bayesian-optimal revenue-maximizing auctions. The classical approach to maximizing revenue requires a known prior distribution on the demand of the bidders, although recent work has shown how to replace the knowledge of a prior distribution with a polynomial sample. However, in an online setting, when buyers can participate in multiple rounds, standard learning techniques are susceptible to \emph{strategic overfitting}: bidders can improve their long-term wellbeing by manipulating the trajectory of the learning algorithm in earlier rounds. For example, they may be able to strategically adjust their behavior in earlier rounds to achieve lower, more favorable future prices. Such non-truthful behavior can hinder learning and harm revenue. In this paper, we combine tools from differential privacy, mechanism design, and sample complexity to give a repeated auction that (1) learns bidder demand from past data, (2) is approximately revenue-optimal, and (3) strategically robust, as it incentivizes bidders to behave truthfully. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9334-learning-auctions-with-robust-incentive-guarantees |
| http://papers.nips.cc/paper/9334-learning-auctions-with-robust-incentive-guarantees.pdf | |
| PWC | https://paperswithcode.com/paper/learning-auctions-with-robust-incentive |
| Repo | |
| Framework | |
Temporal Structure Mining for Weakly Supervised Action Detection
| Title | Temporal Structure Mining for Weakly Supervised Action Detection |
| Authors | Tan Yu, Zhou Ren, Yuncheng Li, Enxu Yan, Ning Xu, Junsong Yuan |
| Abstract | Different from the fully-supervised action detection problem that is dependent on expensive frame-level annotations, weakly supervised action detection (WSAD) only needs video-level annotations, making it more practical for real-world applications. Existing WSAD methods detect action instances by scoring each video segment (a stack of frames) individually. Most of them fail to model the temporal relations among video segments and cannot effectively characterize action instances possessing latent temporal structure. To alleviate this problem in WSAD, we propose the temporal structure mining (TSM) approach. In TSM, each action instance is modeled as a multi-phase process and phase evolving within an action instance, i.e., the temporal structure, is exploited. Meanwhile, the video background is modeled by a background phase, which separates different action instances in an untrimmed video. In this framework, phase filters are used to calculate the confidence scores of the presence of an action’s phases in each segment. Since in the WSAD task, frame-level annotations are not available and thus phase filters cannot be trained directly. To tackle the challenge, we treat each segment’s phase as a hidden variable. We use segments’ confidence scores from each phase filter to construct a table and determine hidden variables, i.e., phases of segments, by a maximal circulant path discovery along the table. Experiments conducted on three benchmark datasets demonstrate the state-of-the-art performance of the proposed TSM. |
| Tasks | Action Detection, Weakly Supervised Action Localization |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yu_Temporal_Structure_Mining_for_Weakly_Supervised_Action_Detection_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Yu_Temporal_Structure_Mining_for_Weakly_Supervised_Action_Detection_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-structure-mining-for-weakly |
| Repo | |
| Framework | |
Prototypical Examples in Deep Learning: Metrics, Characteristics, and Utility
| Title | Prototypical Examples in Deep Learning: Metrics, Characteristics, and Utility |
| Authors | Nicholas Carlini, Ulfar Erlingsson, Nicolas Papernot |
| Abstract | Machine learning (ML) research has investigated prototypes: examples that are representative of the behavior to be learned. We systematically evaluate five methods for identifying prototypes, both ones previously introduced as well as new ones we propose, finding all of them to provide meaningful but different interpretations. Through a human study, we confirm that all five metrics are well matched to human intuition. Examining cases where the metrics disagree offers an informative perspective on the properties of data and algorithms used in learning, with implications for data-corpus construction, efficiency, adversarial robustness, interpretability, and other ML aspects. In particular, we confirm that the “train on hard” curriculum approach can improve accuracy on many datasets and tasks, but that it is strictly worse when there are many mislabeled or ambiguous examples. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1xyx3R9tQ |
| https://openreview.net/pdf?id=r1xyx3R9tQ | |
| PWC | https://paperswithcode.com/paper/prototypical-examples-in-deep-learning |
| Repo | |
| Framework | |
Suicide Risk Assessment with Multi-level Dual-Context Language and BERT
| Title | Suicide Risk Assessment with Multi-level Dual-Context Language and BERT |
| Authors | Matthew Matero, Akash Idnani, Youngseo Son, Salvatore Giorgi, Huy Vu, Mohammad Zamani, Parth Limbachiya, Sharath Ch Guntuku, ra, H. Andrew Schwartz |
| Abstract | Mental health predictive systems typically model language as if from a single context (e.g. Twitter posts, status updates, or forum posts) and often limited to a single level of analysis (e.g. either the message-level or user-level). Here, we bring these pieces together to explore the use of open-vocabulary (BERT embeddings, topics) and theoretical features (emotional expression lexica, personality) for the task of suicide risk assessment on support forums (the CLPsych-2019 Shared Task). We used dual context based approaches (modeling content from suicide forums separate from other content), built over both traditional ML models as well as a novel dual RNN architecture with user-factor adaptation. We find that while affect from the suicide context distinguishes with no-risk from those with {``}any-risk{''}, personality factors from the non-suicide contexts provide distinction of the levels of risk: low, medium, and high risk. Within the shared task, our dual-context approach (listed as SBU-HLAB in the official results) achieved state-of-the-art performance predicting suicide risk using a combination of suicide-context and non-suicide posts (Task B), achieving an F1 score of 0.50 over hidden test set labels. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3005/ |
| https://www.aclweb.org/anthology/W19-3005 | |
| PWC | https://paperswithcode.com/paper/suicide-risk-assessment-with-multi-level-dual |
| Repo | |
| Framework | |
Augmenting a German Morphological Database by Data-Intense Methods
| Title | Augmenting a German Morphological Database by Data-Intense Methods |
| Authors | Petra Steiner |
| Abstract | This paper deals with the automatic enhancement of a new German morphological database. While there are some databases for flat word segmentation, this is the first available resource which can be directly used for deep parsing of German words. We combine the entries of this morphological database with the morphological tools SMOR and Moremorph and a context-based evaluation method which builds on a large Wikipedia corpus. We describe the state of the art and the essential characteristics of the database and the context method. The approach is tested on an inflight magazine of Lufthansa. We derive over 5,000 new instances of complex words. The coverage for the lemma types reaches up to over 99 percent. The precision of new found complex splits and monomorphemes is between 0.93 and 0.99. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4221/ |
| https://www.aclweb.org/anthology/W19-4221 | |
| PWC | https://paperswithcode.com/paper/augmenting-a-german-morphological-database-by |
| Repo | |
| Framework | |
Seeing Motion in the Dark
| Title | Seeing Motion in the Dark |
| Authors | Chen Chen, Qifeng Chen, Minh N. Do, Vladlen Koltun |
| Abstract | Deep learning has recently been applied with impressive results to extreme low-light imaging. Despite the success of single-image processing, extreme low-light video processing is still intractable due to the difficulty of collecting raw video data with corresponding ground truth. Collecting long-exposure ground truth, as was done for single-image processing, is not feasible for dynamic scenes. In this paper, we present deep processing of very dark raw videos: on the order of one lux of illuminance. To support this line of work, we collect a new dataset of raw low-light videos, in which high-resolution raw data is captured at video rate. At this level of darkness, the signal-to-noise ratio is extremely low (negative if measured in dB) and the traditional image processing pipeline generally breaks down. A new method is presented to address this challenging problem. By carefully designing a learning-based pipeline and introducing a new loss function to encourage temporal stability, we train a siamese network on static raw videos, for which ground truth is available, such that the network generalizes to videos of dynamic scenes at test time. Experimental results demonstrate that the presented approach outperforms state-of-the-art models for burst processing, per-frame processing, and blind temporal consistency. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Seeing_Motion_in_the_Dark_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Seeing_Motion_in_the_Dark_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-motion-in-the-dark |
| Repo | |
| Framework | |
MSCap: Multi-Style Image Captioning With Unpaired Stylized Text
| Title | MSCap: Multi-Style Image Captioning With Unpaired Stylized Text |
| Authors | Longteng Guo, Jing Liu, Peng Yao, Jiangwei Li, Hanqing Lu |
| Abstract | In this paper, we propose an adversarial learning network for the task of multi-style image captioning (MSCap) with a standard factual image caption dataset and a multi-stylized language corpus without paired images. How to learn a single model for multi-stylized image captioning with unpaired data is a challenging and necessary task, whereas rarely studied in previous works. The proposed framework mainly includes four contributive modules following a typical image encoder. First, a style dependent caption generator to output a sentence conditioned on an encoded image and a specified style. Second, a caption discriminator is presented to distinguish the input sentence to be real or not. The discriminator and the generator are trained in an adversarial manner to enable more natural and human-like captions. Third, a style classifier is employed to discriminate the specific style of the input sentence. Besides, a back-translation module is designed to enforce the generated stylized captions are visually grounded, with the intuition of the cycle consistency for factual caption and stylized caption. We enable an end-to-end optimization of the whole model with differentiable softmax approximation. At last, we conduct comprehensive experiments using a combined dataset containing four caption styles to demonstrate the outstanding performance of our proposed method. |
| Tasks | Image Captioning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Guo_MSCap_Multi-Style_Image_Captioning_With_Unpaired_Stylized_Text_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Guo_MSCap_Multi-Style_Image_Captioning_With_Unpaired_Stylized_Text_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mscap-multi-style-image-captioning-with |
| Repo | |
| Framework | |
Proceedings of the Qualities of Literary Machine Translation
| Title | Proceedings of the Qualities of Literary Machine Translation |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7300/ |
| https://www.aclweb.org/anthology/W19-7300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-qualities-of-literary |
| Repo | |
| Framework | |
Asynchronous Deep Interaction Network for Natural Language Inference
| Title | Asynchronous Deep Interaction Network for Natural Language Inference |
| Authors | Di Liang, Fubao Zhang, Qi Zhang, Xuanjing Huang |
| Abstract | Natural language inference aims to predict whether a premise sentence can infer another hypothesis sentence. Existing methods typically have framed the reasoning problem as a semantic matching task. The both sentences are encoded and interacted symmetrically and in parallel. However, in the process of reasoning, the role of the two sentences is obviously different, and the sentence pairs for NLI are asymmetrical corpora. In this paper, we propose an asynchronous deep interaction network (ADIN) to complete the task. ADIN is a neural network structure stacked with multiple inference sub-layers, and each sub-layer consists of two local inference modules in an asymmetrical manner. Different from previous methods, this model deconstructs the reasoning process and implements the asynchronous and multi-step reasoning. Experiment results show that ADIN achieves competitive performance and outperforms strong baselines on three popular benchmarks: SNLI, MultiNLI, and SciTail. |
| Tasks | Natural Language Inference |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1271/ |
| https://www.aclweb.org/anthology/D19-1271 | |
| PWC | https://paperswithcode.com/paper/asynchronous-deep-interaction-network-for |
| Repo | |
| Framework | |
Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading
| Title | Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading |
| Authors | Xingxuan Zhang, Feng Cheng, Shilin Wang |
| Abstract | Current state-of-the-art approaches for lip reading are based on sequence-to-sequence architectures that are designed for natural machine translation and audio speech recognition. Hence, these methods do not fully exploit the characteristics of the lip dynamics, causing two main drawbacks. First, the short-range temporal dependencies, which are critical to the mapping from lip images to visemes, receives no extra attention. Second, local spatial information is discarded in the existing sequence models due to the use of global average pooling (GAP). To well solve these drawbacks, we propose a Temporal Focal block to sufficiently describe short-range dependencies and a Spatio-Temporal Fusion Module (STFM) to maintain the local spatial information and to reduce the feature dimensions as well. From the experiment results, it is demonstrated that our method achieves comparable performance with the state-of-the-art approach using much less training data and much lighter Convolutional Feature Extractor. The training time is reduced by 12 days due to the convolutional structure and the local self-attention mechanism. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Spatio-Temporal_Fusion_Based_Convolutional_Sequence_Learning_for_Lip_Reading_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Spatio-Temporal_Fusion_Based_Convolutional_Sequence_Learning_for_Lip_Reading_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spatio-temporal-fusion-based-convolutional |
| Repo | |
| Framework | |
Reviews Meet Graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive Graph Neural Network
| Title | Reviews Meet Graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive Graph Neural Network |
| Authors | Chuhan Wu, Fangzhao Wu, Tao Qi, Suyu Ge, Yongfeng Huang, Xing Xie |
| Abstract | User and item representation learning is critical for recommendation. Many of existing recommendation methods learn representations of users and items based on their ratings and reviews. However, the user-user and item-item relatedness are usually not considered in these methods, which may be insufficient. In this paper, we propose a neural recommendation approach which can utilize useful information from both review content and user-item graphs. Since reviews and graphs have different characteristics, we propose to use a multi-view learning framework to incorporate them as different views. In the review content-view, we propose to use a hierarchical model to first learn sentence representations from words, then learn review representations from sentences, and finally learn user/item representations from reviews. In addition, we propose to incorporate a three-level attention network into this view to select important words, sentences and reviews for learning informative user and item representations. In the graph-view, we propose a hierarchical graph neural network to jointly model the user-item, user-user and item-item relatedness by capturing the first- and second-order interactions between users and items in the user-item graph. In addition, we apply attention mechanism to model the importance of these interactions to learn informative user and item representations. Extensive experiments on four benchmark datasets validate the effectiveness of our approach. |
| Tasks | MULTI-VIEW LEARNING, Representation Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1494/ |
| https://www.aclweb.org/anthology/D19-1494 | |
| PWC | https://paperswithcode.com/paper/reviews-meet-graphs-enhancing-user-and-item |
| Repo | |
| Framework | |
RETHINKING SELF-DRIVING : MULTI -TASK KNOWLEDGE FOR BETTER GENERALIZATION AND ACCIDENT EXPLANATION ABILITY
| Title | RETHINKING SELF-DRIVING : MULTI -TASK KNOWLEDGE FOR BETTER GENERALIZATION AND ACCIDENT EXPLANATION ABILITY |
| Authors | Zhihao LI, Toshiyuki MOTOYOSHI, Kazuma SASAKI, Tetsuya OGATA, Shigeki SUGANO |
| Abstract | Current end-to-end deep learning driving models have two problems: (1) Poor generalization ability of unobserved driving environment when diversity of train- ing driving dataset is limited (2) Lack of accident explanation ability when driving models don’t work as expected. To tackle these two problems, rooted on the be- lieve that knowledge of associated easy task is benificial for addressing difficult task, we proposed a new driving model which is composed of perception module for see and think and driving module for behave, and trained it with multi-task perception-related basic knowledge and driving knowledge stepwisely. Specifi- cally segmentation map and depth map (pixel level understanding of images) were considered as what & where and how far knowledge for tackling easier driving- related perception problems before generating final control commands for difficult driving task. The results of experiments demonstrated the effectiveness of multi- task perception knowledge for better generalization and accident explanation abil- ity. With our method the average sucess rate of finishing most difficult navigation tasks in untrained city of CoRL test surpassed current benchmark method for 15 percent in trained weather and 20 percent in untrained weathers. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B14rPj0qY7 |
| https://openreview.net/pdf?id=B14rPj0qY7 | |
| PWC | https://paperswithcode.com/paper/rethinking-self-driving-multi-task-knowledge |
| Repo | |
| Framework | |
