Paper Group NANR 161
Clinical Data Classification using Conditional Random Fields and Neural Parsing for Morphologically Rich Languages. Putting the Horse before the Cart: A Generator-Evaluator Framework for Question Generation from Text. Asking Clarification Questions in Knowledge-Based Question Answering. Min-Max Statistical Alignment for Transfer Learning. Counting …
Clinical Data Classification using Conditional Random Fields and Neural Parsing for Morphologically Rich Languages
| Title | Clinical Data Classification using Conditional Random Fields and Neural Parsing for Morphologically Rich Languages |
| Authors | Razieh Ehsani, Tyko Niemi, Gaurav Khullar, Tiina Leivo |
| Abstract | Past prescriptions constitute a central element in patient records. These are often written in an unstructured and brief form. Extracting information from such prescriptions enables the development of automated processes in the medical data mining field. This paper presents a Conditional Random Fields (CRFs) based approach to extract relevant information from prescriptions. We focus on Finnish language prescriptions and make use of Finnish language specific features. Our labeling accuracy is 95{%}, which compares favorably to the current state-of-the-art in English language prescriptions. This, to the best of our knowledge, is the first such work for the Finnish language. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1919/ |
| https://www.aclweb.org/anthology/W19-1919 | |
| PWC | https://paperswithcode.com/paper/clinical-data-classification-using |
| Repo | |
| Framework | |
Putting the Horse before the Cart: A Generator-Evaluator Framework for Question Generation from Text
| Title | Putting the Horse before the Cart: A Generator-Evaluator Framework for Question Generation from Text |
| Authors | Vishwajeet Kumar, Ganesh Ramakrishnan, Yuan-Fang Li |
| Abstract | Automatic question generation (QG) is a useful yet challenging task in NLP. Recent neural network-based approaches represent the state-of-the-art in this task. In this work, we attempt to strengthen them significantly by adopting a holistic and novel generator-evaluator framework that directly optimizes objectives that reward semantics and structure. The \textit{generator} is a sequence-to-sequence model that incorporates the \textit{structure} and \textit{semantics} of the question being generated. The generator predicts an answer in the passage that the question can pivot on. Employing the copy and coverage mechanisms, it also acknowledges other contextually important (and possibly rare) keywords in the passage that the question needs to conform to, while not redundantly repeating words. The \textit{evaluator} model evaluates and assigns a reward to each predicted question based on its conformity to the \textit{structure} of ground-truth questions. We propose two novel QG-specific reward functions for text conformity and answer conformity of the generated question. The evaluator also employs structure-sensitive rewards based on evaluation measures such as BLEU, GLEU, and ROUGE-L, which are suitable for QG. In contrast, most of the previous works only optimize the cross-entropy loss, which can induce inconsistencies between training (objective) and testing (evaluation) measures. Our evaluation shows that our approach significantly outperforms state-of-the-art systems on the widely-used SQuAD benchmark as per both automatic and human evaluation. |
| Tasks | Question Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1076/ |
| https://www.aclweb.org/anthology/K19-1076 | |
| PWC | https://paperswithcode.com/paper/putting-the-horse-before-the-cart-a-generator |
| Repo | |
| Framework | |
Asking Clarification Questions in Knowledge-Based Question Answering
| Title | Asking Clarification Questions in Knowledge-Based Question Answering |
| Authors | Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, Pengcheng Yang, Qi Zeng, Ming Zhou, Xu Sun |
| Abstract | The ability to ask clarification questions is essential for knowledge-based question answering (KBQA) systems, especially for handling ambiguous phenomena. Despite its importance, clarification has not been well explored in current KBQA systems. Further progress requires supervised resources for training and evaluation, and powerful models for clarification-related text understanding and generation. In this paper, we construct a new clarification dataset, CLAQUA, with nearly 40K open-domain examples. The dataset supports three serial tasks: given a question, identify whether clarification is needed; if yes, generate a clarification question; then predict answers base on external user feedback. We provide representative baselines for these tasks and further introduce a coarse-to-fine model for clarification question generation. Experiments show that the proposed model achieves better performance than strong baselines. The further analysis demonstrates that our dataset brings new challenges and there still remain several unsolved problems, like reasonable automatic evaluation metrics for clarification question generation and powerful models for handling entity sparsity. |
| Tasks | Question Answering, Question Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1172/ |
| https://www.aclweb.org/anthology/D19-1172 | |
| PWC | https://paperswithcode.com/paper/asking-clarification-questions-in-knowledge |
| Repo | |
| Framework | |
Min-Max Statistical Alignment for Transfer Learning
| Title | Min-Max Statistical Alignment for Transfer Learning |
| Authors | Samitha Herath, Mehrtash Harandi, Basura Fernando, Richard Nock |
| Abstract | A profound idea in learning invariant features for transfer learning is to align statistical properties of the domains. In practice, this is achieved by minimizing the disparity between the domains, usually measured in terms of their statistical properties. We question the capability of this school of thought and propose to minimize the maximum disparity between domains. Furthermore, we develop an end-to-end learning scheme that enables us to benefit from the proposed min-max strategy in training deep models. We show that the min-max solution can outperform the existing statistical alignment solutions, and can compete with state-of-the-art solutions on two challenging learning tasks, namely, Unsupervised Domain Adaptation (UDA) and Zero-Shot Learning (ZSL). |
| Tasks | Domain Adaptation, Transfer Learning, Unsupervised Domain Adaptation, Zero-Shot Learning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Herath_Min-Max_Statistical_Alignment_for_Transfer_Learning_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Herath_Min-Max_Statistical_Alignment_for_Transfer_Learning_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/min-max-statistical-alignment-for-transfer |
| Repo | |
| Framework | |
Counting the Optimal Solutions in Graphical Models
| Title | Counting the Optimal Solutions in Graphical Models |
| Authors | Radu Marinescu, Rina Dechter |
| Abstract | We introduce #opt, a new inference task for graphical models which calls for counting the number of optimal solutions of the model. We describe a novel variable elimination based approach for solving this task, as well as a depth-first branch and bound algorithm that traverses the AND/OR search space of the model. The key feature of the proposed algorithms is that their complexity is exponential in the induced width of the model only. It does not depend on the actual number of optimal solutions. Our empirical evaluation on various benchmarks demonstrates the effectiveness of the proposed algorithms compared with existing depth-first and best-first search based approaches that enumerate explicitly the optimal solutions. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9379-counting-the-optimal-solutions-in-graphical-models |
| http://papers.nips.cc/paper/9379-counting-the-optimal-solutions-in-graphical-models.pdf | |
| PWC | https://paperswithcode.com/paper/counting-the-optimal-solutions-in-graphical |
| Repo | |
| Framework | |
Depth-Attentional Features for Single-Image Rain Removal
| Title | Depth-Attentional Features for Single-Image Rain Removal |
| Authors | Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Pheng-Ann Heng |
| Abstract | Rain is a common weather phenomenon, where object visibility varies with depth from the camera and objects faraway are visually blocked more by fog than by rain streaks. Existing methods and datasets for rain removal, however, ignore these physical properties, thereby limiting the rain removal efficiency on real photos. In this work, we first analyze the visual effects of rain subject to scene depth and formulate a rain imaging model collectively with rain streaks and fog; by then, we prepare a new dataset called RainCityscapes with rain streaks and fog on real outdoor photos. Furthermore, we design an end-to-end deep neural network, where we train it to learn depth-attentional features via a depth-guided attention mechanism, and regress a residual map to produce the rain-free image output. We performed various experiments to visually and quantitatively compare our method with several state-of-the-art methods to demonstrate its superiority over the others. |
| Tasks | Rain Removal |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Hu_Depth-Attentional_Features_for_Single-Image_Rain_Removal_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Hu_Depth-Attentional_Features_for_Single-Image_Rain_Removal_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/depth-attentional-features-for-single-image |
| Repo | |
| Framework | |
From Image to Text in Sentiment Analysis via Regression and Deep Learning
| Title | From Image to Text in Sentiment Analysis via Regression and Deep Learning |
| Authors | Daniela Onita, Liviu P. Dinu, Adriana Birlutiu |
| Abstract | Images and text represent types of content which are used together for conveying user emotions in online social networks. These contents are usually associated with a sentiment category. In this paper, we investigate an approach for mapping images to text for three types of sentiment categories: positive, neutral and negative. The mapping from images to text is performed using a Kernel Ridge Regression model. We considered two types of image features: i) RGB pixel-values features, and ii) features extracted with a deep learning approach. The experimental evaluation was performed on a Twitter data set containing both text and images and the sentiment associated with these. The experimental results show a difference in performance for different sentiment categories, in particular the mapping that we propose performs better for the positive sentiment category in comparison with the neutral and negative ones. Furthermore, the experimental results show that the more complex deep learning features perform better than the RGB pixel-value features for all sentiment categories and for larger training sets. |
| Tasks | Sentiment Analysis |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1100/ |
| https://www.aclweb.org/anthology/R19-1100 | |
| PWC | https://paperswithcode.com/paper/from-image-to-text-in-sentiment-analysis-via |
| Repo | |
| Framework | |
DM_NLP at SemEval-2018 Task 12: A Pipeline System for Toponym Resolution
| Title | DM_NLP at SemEval-2018 Task 12: A Pipeline System for Toponym Resolution |
| Authors | Xiaobin Wang, Chunping Ma, Huafei Zheng, Chu Liu, Pengjun Xie, Linlin Li, Luo Si |
| Abstract | This paper describes DM-NLP{'}s system for toponym resolution task at Semeval 2019. Our system was developed for toponym detection, disambiguation and end-to-end resolution which is a pipeline of the former two. For toponym detection, we utilized the state-of-the-art sequence labeling model, namely, BiLSTM-CRF model as backbone. A lot of strategies are adopted for further improvement, such as pre-training, model ensemble, model averaging and data augment. For toponym disambiguation, we adopted the widely used searching and ranking framework. For ranking, we proposed several effective features for measuring the consistency between the detected toponym and toponyms in GeoNames. Eventually, our system achieved the best performance among all the submitted results in each sub task. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2156/ |
| https://www.aclweb.org/anthology/S19-2156 | |
| PWC | https://paperswithcode.com/paper/dm_nlp-at-semeval-2018-task-12-a-pipeline |
| Repo | |
| Framework | |
Coda: An End-to-End Neural Program Decompiler
| Title | Coda: An End-to-End Neural Program Decompiler |
| Authors | Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong Tian, Farinaz Koushanfar, Jishen Zhao |
| Abstract | Reverse engineering of binary executables is a critical problem in the computer security domain. On the one hand, malicious parties may recover interpretable source codes from the software products to gain commercial advantages. On the other hand, binary decompilation can be leveraged for code vulnerability analysis and malware detection. However, efficient binary decompilation is challenging. Conventional decompilers have the following major limitations: (i) they are only applicable to specific source-target language pair, hence incurs undesired development cost for new language tasks; (ii) their output high-level code cannot effectively preserve the correct functionality of the input binary; (iii) their output program does not capture the semantics of the input and the reversed program is hard to interpret. To address the above problems, we propose Coda1, the first end-to-end neural-based framework for code decompilation. Coda decomposes the decompilation task into of two key phases: First, Coda employs an instruction type-aware encoder and a tree decoder for generating an abstract syntax tree (AST) with attention feeding during the code sketch generation stage. Second, Coda then updates the code sketch using an iterative error correction machine guided by an ensembled neural error predictor. By finding a good approximate candidate and then fixing it towards perfect, Coda achieves superior with performance compared to baseline approaches. We assess Coda’s performance with extensive experiments on various benchmarks. Evaluation results show that Coda achieves an average of 82% program recovery accuracy on unseen binary samples, where the state-of-the-art decompilers yield 0% accuracy. Furthermore, Coda outperforms the sequence-to-sequence model with attention by a margin of 70% program accuracy. Our work reveals the vulnerability of binary executables and imposes a new threat to the protection of Intellectual Property (IP) for software development. |
| Tasks | Malware Detection |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8628-coda-an-end-to-end-neural-program-decompiler |
| http://papers.nips.cc/paper/8628-coda-an-end-to-end-neural-program-decompiler.pdf | |
| PWC | https://paperswithcode.com/paper/coda-an-end-to-end-neural-program-decompiler |
| Repo | |
| Framework | |
Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
| Title | Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds |
| Authors | Minshuo Chen, Haoming Jiang, Wenjing Liao, Tuo Zhao |
| Abstract | Deep neural networks have revolutionized many real world applications, due to their flexibility in data fitting and accurate predictions for unseen data. A line of research reveals that neural networks can approximate certain classes of functions with an arbitrary accuracy, while the size of the network scales exponentially with respect to the data dimension. Empirical results, however, suggest that networks of moderate size already yield appealing performance. To explain such a gap, a common belief is that many data sets exhibit low dimensional structures, and can be modeled as samples near a low dimensional manifold. In this paper, we prove that neural networks can efficiently approximate functions supported on low dimensional manifolds. The network size scales exponentially in the approximation error, with an exponent depending on the intrinsic dimension of the data and the smoothness of the function. Our result shows that exploiting low dimensional data structures can greatly enhance the efficiency in function approximation by neural networks. We also implement a sub-network that assigns input data to their corresponding local neighborhoods, which may be of independent interest. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9028-efficient-approximation-of-deep-relu-networks-for-functions-on-low-dimensional-manifolds |
| http://papers.nips.cc/paper/9028-efficient-approximation-of-deep-relu-networks-for-functions-on-low-dimensional-manifolds.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-approximation-of-deep-relu-networks-1 |
| Repo | |
| Framework | |
Look Back and Predict Forward in Image Captioning
| Title | Look Back and Predict Forward in Image Captioning |
| Authors | Yu Qin, Jiajun Du, Yonghua Zhang, Hongtao Lu |
| Abstract | Most existing attention-based methods on image captioning focus on the current word and visual information in one time step and generate the next word, without considering the visual and linguistic coherence. We propose Look Back (LB) method to embed visual information from the past and Predict Forward (PF) approach to look into future. LB method introduces attention value from the previous time step into the current attention generation to suit visual coherence of human. PF model predicts the next two words in one time step and jointly employs their probabilities for inference. Then the two approaches are combined together as LBPF to further integrate visual information from the past and linguistic information in the future to improve image captioning performance. All the three methods are applied on a classic base decoder, and show remarkable improvements on MSCOCO dataset with small increments on parameter counts. Our LBPF model achieves BLEU-4 / CIDEr / SPICE scores of 37.4 / 116.4 / 21.2 with cross-entropy loss and 38.3 / 127.6 / 22.0 with CIDEr optimization. Our three proposed methods can be easily applied on most attention-based encoder-decoder models for image captioning. |
| Tasks | Image Captioning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Qin_Look_Back_and_Predict_Forward_in_Image_Captioning_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Qin_Look_Back_and_Predict_Forward_in_Image_Captioning_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/look-back-and-predict-forward-in-image |
| Repo | |
| Framework | |
Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence
| Title | Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence |
| Authors | Amir Zadeh, Michael Chan, Paul Pu Liang, Edmund Tong, Louis-Philippe Morency |
| Abstract | As intelligent systems increasingly blend into our everyday life, artificial social intelligence becomes a prominent area of research. Intelligent systems must be socially intelligent in order to comprehend human intents and maintain a rich level of interaction with humans. Human language offers a unique unconstrained approach to probe through questions and reason through answers about social situations. This unconstrained approach extends previous attempts to model social intelligence through numeric supervision (e.g. sentiment and emotions labels). In this paper, we introduce Social-IQ, a unconstrained benchmark specifically designed to train and evaluate socially intelligent technologies. By providing a rich source of open-ended questions and answers, Social-IQ opens the door to explainable social intelligence. The dataset contains rigorously annotated and validated videos, questions and answers, as well as annotations for the complexity level of each question and answer. Social-IQ contains 1,250 natural in-the-wild social situations, 7,500 questions and 52,500 correct and incorrect answers. Although humans can reason about social situations with very high accuracy (95.08%), existing state-of-the-art computational models struggle on this task. As a result, Social-IQ brings novel challenges that will spark future research in social intelligence modeling, visual reasoning, and multimodal question answering (QA). |
| Tasks | Question Answering, Visual Reasoning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zadeh_Social-IQ_A_Question_Answering_Benchmark_for_Artificial_Social_Intelligence_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zadeh_Social-IQ_A_Question_Answering_Benchmark_for_Artificial_Social_Intelligence_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/social-iq-a-question-answering-benchmark-for |
| Repo | |
| Framework | |
Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media
| Title | Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media |
| Authors | Hansi Hettiarachchi, Tharindu Ranasinghe |
| Abstract | This paper describes a novel research approach to detect type and target of offensive posts in social media using a capsule network. The input to the network was character embeddings combined with emoji embeddings. The approach was evaluated on all three subtasks in Task 6 - SemEval 2019: OffensEval: Identifying and Categorizing Offensive Language in Social Media. The evaluation also showed that even though the capsule networks have not been used commonly in natural language processing tasks, they can outperform existing state of the art solutions for offensive language detection in social media. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1056/ |
| https://www.aclweb.org/anthology/R19-1056 | |
| PWC | https://paperswithcode.com/paper/emoji-powered-capsule-network-to-detect-type |
| Repo | |
| Framework | |
Reading KITTY: Pitch Range as an Indicator of Reading Skill
| Title | Reading KITTY: Pitch Range as an Indicator of Reading Skill |
| Authors | Alfredo Gomez, Alicia Ngo, Aless Otondo, ra, Julie Medero |
| Abstract | While affective outcomes are generally positive for the use of eBooks and computer-based reading tutors in teaching children to read, learning outcomes are often poorer (Korat and Shamir, 2004). We describe the first iteration of Reading Kitty, an iOS application that uses NLP and speech processing to focus children{'}s time on close reading and prosody in oral reading, while maintaining an emphasis on creativity and artifact creation. We also share preliminary results demonstrating that pitch range can be used to automatically predict readers{'} skill level. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3652/ |
| https://www.aclweb.org/anthology/W19-3652 | |
| PWC | https://paperswithcode.com/paper/reading-kitty-pitch-range-as-an-indicator-of |
| Repo | |
| Framework | |
Toward a Computational Multidimensional Lexical Similarity Measure for Modeling Word Association Tasks in Psycholinguistics
| Title | Toward a Computational Multidimensional Lexical Similarity Measure for Modeling Word Association Tasks in Psycholinguistics |
| Authors | Bruno Gaume, Lydia Mai Ho-Dac, Ludovic Tanguy, C{'e}cile Fabre, B{'e}n{'e}dicte Pierrejean, Nabil Hathout, J{'e}r{^o}me Farinas, Julien Pinquier, Lola Danet, Patrice P{'e}ran, Xavier De Boissezon, M{'e}lanie Jucla |
| Abstract | This paper presents the first results of a multidisciplinary project, the {``}Evolex{''} project, gathering researchers in Psycholinguistics, Neuropsychology, Computer Science, Natural Language Processing and Linguistics. The Evolex project aims at proposing a new data-based inductive method for automatically characterising the relation between pairs of french words collected in psycholinguistics experiments on lexical access. This method takes advantage of several complementary computational measures of semantic similarity. We show that some measures are more correlated than others with the frequency of lexical associations, and that they also differ in the way they capture different semantic relations. This allows us to consider building a multidimensional lexical similarity to automate the classification of lexical associations. | |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2908/ |
| https://www.aclweb.org/anthology/W19-2908 | |
| PWC | https://paperswithcode.com/paper/toward-a-computational-multidimensional |
| Repo | |
| Framework | |
