Paper Group NANR 38
Automating Document Discovery in the Systematic Review Process: How to Use Chaff to Extract Wheat. Content Determination for Chess as a Source for Suspenseful Narratives. Browsing and Supporting Pluricentric Global Wordnet, or just your Wordnet of Interest. Document-based Recommender System for Job Postings using Dense Representations. What can we …
Automating Document Discovery in the Systematic Review Process: How to Use Chaff to Extract Wheat
Title | Automating Document Discovery in the Systematic Review Process: How to Use Chaff to Extract Wheat |
Authors | Christopher Norman, Mariska Leeflang, Pierre Zweigenbaum, Aur{'e}lie N{'e}v{'e}ol |
Abstract | |
Tasks | Decision Making |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1582/ |
https://www.aclweb.org/anthology/L18-1582 | |
PWC | https://paperswithcode.com/paper/automating-document-discovery-in-the |
Repo | |
Framework | |
Content Determination for Chess as a Source for Suspenseful Narratives
Title | Content Determination for Chess as a Source for Suspenseful Narratives |
Authors | Richard Doust, Pablo Gerv{'a}s |
Abstract | |
Tasks | Game of Chess, Text Generation |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-6605/ |
https://www.aclweb.org/anthology/W18-6605 | |
PWC | https://paperswithcode.com/paper/content-determination-for-chess-as-a-source |
Repo | |
Framework | |
Browsing and Supporting Pluricentric Global Wordnet, or just your Wordnet of Interest
Title | Browsing and Supporting Pluricentric Global Wordnet, or just your Wordnet of Interest |
Authors | Ant{'o}nio Branco, Ruben Branco, Chakaveh Saedi, Jo{~a}o Silva |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1722/ |
https://www.aclweb.org/anthology/L18-1722 | |
PWC | https://paperswithcode.com/paper/browsing-and-supporting-pluricentric-global |
Repo | |
Framework | |
Document-based Recommender System for Job Postings using Dense Representations
Title | Document-based Recommender System for Job Postings using Dense Representations |
Authors | Ahmed Elsafty, Martin Riedl, Chris Biemann |
Abstract | Job boards and professional social networks heavily use recommender systems in order to better support users in exploring job advertisements. Detecting the similarity between job advertisements is important for job recommendation systems as it allows, for example, the application of item-to-item based recommendations. In this work, we research the usage of dense vector representations to enhance a large-scale job recommendation system and to rank German job advertisements regarding their similarity. We follow a two-folded evaluation scheme: (1) we exploit historic user interactions to automatically create a dataset of similar jobs that enables an offline evaluation. (2) In addition, we conduct an online A/B test and evaluate the best performing method on our platform reaching more than 1 million users. We achieve the best results by combining job titles with full-text job descriptions. In particular, this method builds dense document representation using words of the titles to weigh the importance of words of the full-text description. In the online evaluation, this approach allows us to increase the click-through rate on job recommendations for active users by 8.0{%}. |
Tasks | Document Embedding, Recommendation Systems |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-3027/ |
https://www.aclweb.org/anthology/N18-3027 | |
PWC | https://paperswithcode.com/paper/document-based-recommender-system-for-job |
Repo | |
Framework | |
What can we gain from language models for morphological inflection?
Title | What can we gain from language models for morphological inflection? |
Authors | Alexey Sorokin |
Abstract | |
Tasks | Language Modelling, Machine Translation, Morphological Inflection |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/K18-3012/ |
https://www.aclweb.org/anthology/K18-3012 | |
PWC | https://paperswithcode.com/paper/what-can-we-gain-from-language-models-for |
Repo | |
Framework | |
Refining Pretrained Word Embeddings Using Layer-wise Relevance Propagation
Title | Refining Pretrained Word Embeddings Using Layer-wise Relevance Propagation |
Authors | Akira Utsumi |
Abstract | In this paper, we propose a simple method for refining pretrained word embeddings using layer-wise relevance propagation. Given a target semantic representation one would like word vectors to reflect, our method first trains the mapping between the original word vectors and the target representation using a neural network. Estimated target values are then propagated backward toward word vectors, and a relevance score is computed for each dimension of word vectors. Finally, the relevance score vectors are used to refine the original word vectors so that they are projected into the subspace that reflects the information relevant to the target representation. The evaluation experiment using binary classification of word pairs demonstrates that the refined vectors by our method achieve the higher performance than the original vectors. |
Tasks | Word Embeddings |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1520/ |
https://www.aclweb.org/anthology/D18-1520 | |
PWC | https://paperswithcode.com/paper/refining-pretrained-word-embeddings-using |
Repo | |
Framework | |
Safe Active Learning for Time-Series Modeling with Gaussian Processes
Title | Safe Active Learning for Time-Series Modeling with Gaussian Processes |
Authors | Christoph Zimmer, Mona Meister, Duy Nguyen-Tuong |
Abstract | Learning time-series models is useful for many applications, such as simulation and forecasting. In this study, we consider the problem of actively learning time-series models while taking given safety constraints into account. For time-series modeling we employ a Gaussian process with a nonlinear exogenous input structure. The proposed approach generates data appropriate for time series model learning, i.e. input and output trajectories, by dynamically exploring the input space. The approach parametrizes the input trajectory as consecutive trajectory sections, which are determined stepwise given safety requirements and past observations. We analyze the proposed algorithm and evaluate it empirically on a technical application. The results show the effectiveness of our approach in a realistic technical use case. |
Tasks | Active Learning, Gaussian Processes, Time Series |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7538-safe-active-learning-for-time-series-modeling-with-gaussian-processes |
http://papers.nips.cc/paper/7538-safe-active-learning-for-time-series-modeling-with-gaussian-processes.pdf | |
PWC | https://paperswithcode.com/paper/safe-active-learning-for-time-series-modeling |
Repo | |
Framework | |
Interactive health insight miner: an adaptive, semantic-based approach
Title | Interactive health insight miner: an adaptive, semantic-based approach |
Authors | Isabel Funke, Rim Helaoui, Aki H{"a}rm{"a} |
Abstract | E-health applications aim to support the user in adopting healthy habits. An important feature is to provide insights into the user{'}s lifestyle. To actively engage the user in the insight mining process, we propose an ontology-based framework with a Controlled Natural Language interface, which enables the user to ask for specific insights and to customize personal information. |
Tasks | Common Sense Reasoning, Text Generation, Text Summarization |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-6559/ |
https://www.aclweb.org/anthology/W18-6559 | |
PWC | https://paperswithcode.com/paper/interactive-health-insight-miner-an-adaptive |
Repo | |
Framework | |
Double JPEG Detection in Mixed JPEG Quality Factors using Deep Convolutional Neural Network
Title | Double JPEG Detection in Mixed JPEG Quality Factors using Deep Convolutional Neural Network |
Authors | Jinseok Park, Donghyeon Cho, Wonhyuk Ahn, Heung-Kyu Lee |
Abstract | Double JPEG detection is essential for detecting various image manipulations. This paper proposes a novel deep convolutional neural network for double JPEG detection using statistical histogram features from each block with a vectorized quantization table. In contrast to previous methods, the proposed approach handles mixed JPEG quality factors and is suitable for real-world situations. We collected real-world JPEG images from the image forensic service and generated a new double JPEG dataset with 1120 quantization tables to train the network. The proposed approach was verified experimentally to produce a state-of-the-art performance, successfully detecting various image manipulations. |
Tasks | Quantization |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jin-Seok_Park_Double_JPEG_Detection_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Jin-Seok_Park_Double_JPEG_Detection_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/double-jpeg-detection-in-mixed-jpeg-quality |
Repo | |
Framework | |
Making Convolutional Networks Recurrent for Visual Sequence Learning
Title | Making Convolutional Networks Recurrent for Visual Sequence Learning |
Authors | Xiaodong Yang, Pavlo Molchanov, Jan Kautz |
Abstract | Recurrent neural networks (RNNs) have emerged as a powerful model for a broad range of machine learning problems that involve sequential data. While an abundance of work exists to understand and improve RNNs in the context of language and audio signals such as language modeling and speech recognition, relatively little attention has been paid to analyze or modify RNNs for visual sequences, which by nature have distinct properties. In this paper, we aim to bridge this gap and present the first large-scale exploration of RNNs for visual sequence learning. In particular, with the intention of leveraging the strong generalization capacity of pre-trained convolutional neural networks (CNNs), we propose a novel and effective approach, PreRNN, to make pre-trained CNNs recurrent by transforming convolutional layers or fully connected layers into recurrent layers. We conduct extensive evaluations on three representative visual sequence learning tasks: sequential face alignment, dynamic hand gesture recognition, and action recognition. Our experiments reveal that PreRNN consistently outperforms the traditional RNNs and achieves state-of-the-art results on the three applications, suggesting that PreRNN is more suitable for visual sequence learning. |
Tasks | Face Alignment, Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition, Language Modelling, Speech Recognition, Temporal Action Localization |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Yang_Making_Convolutional_Networks_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Making_Convolutional_Networks_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/making-convolutional-networks-recurrent-for |
Repo | |
Framework | |
Locally Private Hypothesis Testing
Title | Locally Private Hypothesis Testing |
Authors | Or Sheffet |
Abstract | We initiate the study of differentially private hypothesis testing in the local-model, under both the standard (symmetric) randomized-response mechanism (Warner 1965, Kasiviswanathan et al, 2008) and the newer (non-symmetric) mechanisms (Bassily & Smith, 2015, Bassily et al, 2017). First, we study the general framework of mapping each user’s type into a signal and show that the problem of finding the maximum-likelihood distribution over the signals is feasible. Then we discuss the randomized-response mechanism and show that, in essence, it maps the null- and alternative-hypotheses onto new sets, an affine translation of the original sets. We then give sample complexity bounds for identity and independence testing under randomized-response. We then move to the newer non-symmetric mechanisms and show that there too the problem of finding the maximum-likelihood distribution is feasible. Under the mechanism of Bassily et al we give identity and independence testers with better sample complexity than the testers in the symmetric case, and we also propose a $\chi^2$-based identity tester which we investigate empirically. |
Tasks | |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2071 |
http://proceedings.mlr.press/v80/sheffet18a/sheffet18a.pdf | |
PWC | https://paperswithcode.com/paper/locally-private-hypothesis-testing |
Repo | |
Framework | |
Multi-task and Multi-lingual Joint Learning of Neural Lexical Utterance Classification based on Partially-shared Modeling
Title | Multi-task and Multi-lingual Joint Learning of Neural Lexical Utterance Classification based on Partially-shared Modeling |
Authors | Ryo Masumura, Tomohiro Tanaka, Ryuichiro Higashinaka, Hirokazu Masataki, Yushi Aono |
Abstract | This paper is an initial study on multi-task and multi-lingual joint learning for lexical utterance classification. A major problem in constructing lexical utterance classification modules for spoken dialogue systems is that individual data resources are often limited or unbalanced among tasks and/or languages. Various studies have examined joint learning using neural-network based shared modeling; however, previous joint learning studies focused on either cross-task or cross-lingual knowledge transfer. In order to simultaneously support both multi-task and multi-lingual joint learning, our idea is to explicitly divide state-of-the-art neural lexical utterance classification into language-specific components that can be shared between different tasks and task-specific components that can be shared between different languages. In addition, in order to effectively transfer knowledge between different task data sets and different language data sets, this paper proposes a partially-shared modeling method that possesses both shared components and components specific to individual data sets. We demonstrate the effectiveness of proposed method using Japanese and English data sets with three different lexical utterance classification tasks. |
Tasks | Feature Engineering, Spoken Dialogue Systems, Transfer Learning |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1304/ |
https://www.aclweb.org/anthology/C18-1304 | |
PWC | https://paperswithcode.com/paper/multi-task-and-multi-lingual-joint-learning |
Repo | |
Framework | |
Classifying the Informative Behaviour of Emoji in Microblogs
Title | Classifying the Informative Behaviour of Emoji in Microblogs |
Authors | Giulia Donato, Patrizia Paggio |
Abstract | |
Tasks | Text Summarization |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1108/ |
https://www.aclweb.org/anthology/L18-1108 | |
PWC | https://paperswithcode.com/paper/classifying-the-informative-behaviour-of |
Repo | |
Framework | |
Mining Biomedical Publications With The LAPPS Grid
Title | Mining Biomedical Publications With The LAPPS Grid |
Authors | Nancy Ide, Keith Suderman, Jin-Dong Kim |
Abstract | |
Tasks | Relation Extraction |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1327/ |
https://www.aclweb.org/anthology/L18-1327 | |
PWC | https://paperswithcode.com/paper/mining-biomedical-publications-with-the-lapps |
Repo | |
Framework | |
Responding E-commerce Product Questions via Exploiting QA Collections and Reviews
Title | Responding E-commerce Product Questions via Exploiting QA Collections and Reviews |
Authors | Qian Yu, Wai Lam, Zihao Wang |
Abstract | Providing instant responses for product questions in E-commerce sites can significantly improve satisfaction of potential consumers. We propose a new framework for automatically responding product questions newly posed by users via exploiting existing QA collections and review collections in a coordinated manner. Our framework can return a ranked list of snippets serving as the automated response for a given question, where each snippet can be a sentence from reviews or an existing question-answer pair. One major subtask in our framework is question-based response review ranking. Learning for response review ranking is challenging since there is no labeled response review available. The collection of existing QA pairs are exploited as distant supervision for learning to rank responses. With proposed distant supervision paradigm, the learned response ranking model makes use of the knowledge in the QA pairs and the corresponding retrieved review lists. Extensive experiments on datasets collected from a real-world commercial E-commerce site demonstrate the effectiveness of our proposed framework. |
Tasks | Learning-To-Rank |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1186/ |
https://www.aclweb.org/anthology/C18-1186 | |
PWC | https://paperswithcode.com/paper/responding-e-commerce-product-questions-via |
Repo | |
Framework | |