Paper Group NANR 30
Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. Never Abandon Minorities: Exhaustive Extraction of Bursty Phrases on Microblogs Using Set Cover Problem. What I think when I think about treebanks. Semantic Storytelling, Cross-lingual Event Detection and other Semantic Services for a Newsroom Content Curation Dashboard. THU_N …
Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent
| Title | Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent |
| Authors | Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, Julien Stainer |
| Abstract | We study the resilience to Byzantine failures of distributed implementations of Stochastic Gradient Descent (SGD). So far, distributed machine learning frameworks have largely ignored the possibility of failures, especially arbitrary (i.e., Byzantine) ones. Causes of failures include software bugs, network asynchrony, biases in local datasets, as well as attackers trying to compromise the entire system. Assuming a set of $n$ workers, up to $f$ being Byzantine, we ask how resilient can SGD be, without limiting the dimension, nor the size of the parameter space. We first show that no gradient aggregation rule based on a linear combination of the vectors proposed by the workers (i.e, current approaches) tolerates a single Byzantine failure. We then formulate a resilience property of the aggregation rule capturing the basic requirements to guarantee convergence despite $f$ Byzantine workers. We propose \emph{Krum}, an aggregation rule that satisfies our resilience property, which we argue is the first provably Byzantine-resilient algorithm for distributed SGD. We also report on experimental evaluations of Krum. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6617-machine-learning-with-adversaries-byzantine-tolerant-gradient-descent |
| http://papers.nips.cc/paper/6617-machine-learning-with-adversaries-byzantine-tolerant-gradient-descent.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-with-adversaries-byzantine |
| Repo | |
| Framework | |
Never Abandon Minorities: Exhaustive Extraction of Bursty Phrases on Microblogs Using Set Cover Problem
| Title | Never Abandon Minorities: Exhaustive Extraction of Bursty Phrases on Microblogs Using Set Cover Problem |
| Authors | Masumi Shirakawa, Takahiro Hara, Takuya Maekawa |
| Abstract | We propose a language-independent data-driven method to exhaustively extract bursty phrases of arbitrary forms (e.g., phrases other than simple noun phrases) from microblogs. The burst (i.e., the rapid increase of the occurrence) of a phrase causes the burst of overlapping N-grams including incomplete ones. In other words, bursty incomplete N-grams inevitably overlap bursty phrases. Thus, the proposed method performs the extraction of bursty phrases as the set cover problem in which all bursty N-grams are covered by a minimum set of bursty phrases. Experimental results using Japanese Twitter data showed that the proposed method outperformed word-based, noun phrase-based, and segmentation-based methods both in terms of accuracy and coverage. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1251/ |
| https://www.aclweb.org/anthology/D17-1251 | |
| PWC | https://paperswithcode.com/paper/never-abandon-minorities-exhaustive |
| Repo | |
| Framework | |
What I think when I think about treebanks
| Title | What I think when I think about treebanks |
| Authors | Anders S{\o}gaard |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7620/ |
| https://www.aclweb.org/anthology/W17-7620 | |
| PWC | https://paperswithcode.com/paper/what-i-think-when-i-think-about-treebanks |
| Repo | |
| Framework | |
Semantic Storytelling, Cross-lingual Event Detection and other Semantic Services for a Newsroom Content Curation Dashboard
| Title | Semantic Storytelling, Cross-lingual Event Detection and other Semantic Services for a Newsroom Content Curation Dashboard |
| Authors | Julian Moreno-Schneider, Ankit Srivastava, Peter Bourgonje, David Wabnitz, Georg Rehm |
| Abstract | We present a prototypical content curation dashboard, to be used in the newsroom, and several of its underlying semantic content analysis components (such as named entity recognition, entity linking, summarisation and temporal expression analysis). The idea is to enable journalists (a) to process incoming content (agency reports, twitter feeds, reports, blog posts, social media etc.) and (b) to create new articles more easily and more efficiently. The prototype system also allows the automatic annotation of events in incoming content for the purpose of supporting journalists in identifying important, relevant or meaningful events and also to adapt the content currently in production accordingly in a semi-automatic way. One of our long-term goals is to support journalists building up entire storylines with automatic means. In the present prototype they are generated in a backend service using clustering methods that operate on the extracted events. |
| Tasks | Entity Linking, Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4212/ |
| https://www.aclweb.org/anthology/W17-4212 | |
| PWC | https://paperswithcode.com/paper/semantic-storytelling-cross-lingual-event |
| Repo | |
| Framework | |
THU_NGN at IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases with Deep LSTM
| Title | THU_NGN at IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases with Deep LSTM |
| Authors | Chuhan Wu, Fangzhao Wu, Yongfeng Huang, Sixing Wu, Zhigang Yuan |
| Abstract | Predicting valence-arousal ratings for words and phrases is very useful for constructing affective resources for dimensional sentiment analysis. Since the existing valence-arousal resources of Chinese are mainly in word-level and there is a lack of phrase-level ones, the Dimensional Sentiment Analysis for Chinese Phrases (DSAP) task aims to predict the valence-arousal ratings for Chinese affective words and phrases automatically. In this task, we propose an approach using a densely connected LSTM network and word features to identify dimensional sentiment on valence and arousal for words and phrases jointly. We use word embedding as major feature and choose part of speech (POS) and word clusters as additional features to train the dense LSTM network. The evaluation results of our submissions (1st and 2nd in average performance) validate the effectiveness of our system to predict valence and arousal dimensions for Chinese words and phrases. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4007/ |
| https://www.aclweb.org/anthology/I17-4007 | |
| PWC | https://paperswithcode.com/paper/thu_ngn-at-ijcnlp-2017-task-2-dimensional |
| Repo | |
| Framework | |
QLUT at SemEval-2017 Task 2: Word Similarity Based on Word Embedding and Knowledge Base
| Title | QLUT at SemEval-2017 Task 2: Word Similarity Based on Word Embedding and Knowledge Base |
| Authors | Fanqing Meng, Wenpeng Lu, Yuteng Zhang, Ping Jian, Shumin Shi, Heyan Huang |
| Abstract | This paper shows the details of our system submissions in the task 2 of SemEval 2017. We take part in the subtask 1 of this task, which is an English monolingual subtask. This task is designed to evaluate the semantic word similarity of two linguistic items. The results of runs are assessed by standard Pearson and Spearman correlation, contrast with official gold standard set. The best performance of our runs is 0.781 (Final). The techniques of our runs mainly make use of the word embeddings and the knowledge-based method. The results demonstrate that the combined method is effective for the computation of word similarity, while the word embeddings and the knowledge-based technique, respectively, needs more deeply improvement in details. |
| Tasks | Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2036/ |
| https://www.aclweb.org/anthology/S17-2036 | |
| PWC | https://paperswithcode.com/paper/qlut-at-semeval-2017-task-2-word-similarity |
| Repo | |
| Framework | |
Continuous N-gram Representations for Authorship Attribution
| Title | Continuous N-gram Representations for Authorship Attribution |
| Authors | Yunita Sari, Andreas Vlachos, Mark Stevenson |
| Abstract | This paper presents work on using continuous representations for authorship attribution. In contrast to previous work, which uses discrete feature representations, our model learns continuous representations for n-gram features via a neural network jointly with the classification layer. Experimental results demonstrate that the proposed model outperforms the state-of-the-art on two datasets, while producing comparable results on the remaining two. |
| Tasks | Text Classification |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2043/ |
| https://www.aclweb.org/anthology/E17-2043 | |
| PWC | https://paperswithcode.com/paper/continuous-n-gram-representations-for |
| Repo | |
| Framework | |
Accelerated consensus via Min-Sum Splitting
| Title | Accelerated consensus via Min-Sum Splitting |
| Authors | Patrick Rebeschini, Sekhar C. Tatikonda |
| Abstract | We apply the Min-Sum message-passing protocol to solve the consensus problem in distributed optimization. We show that while the ordinary Min-Sum algorithm does not converge, a modified version of it known as Splitting yields convergence to the problem solution. We prove that a proper choice of the tuning parameters allows Min-Sum Splitting to yield subdiffusive accelerated convergence rates, matching the rates obtained by shift-register methods. The acceleration scheme embodied by Min-Sum Splitting for the consensus problem bears similarities with lifted Markov chains techniques and with multi-step first order methods in convex optimization. |
| Tasks | Distributed Optimization |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6736-accelerated-consensus-via-min-sum-splitting |
| http://papers.nips.cc/paper/6736-accelerated-consensus-via-min-sum-splitting.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-consensus-via-min-sum-splitting |
| Repo | |
| Framework | |
A Feature-based Ensemble Approach to Recognition of Emerging and Rare Named Entities
| Title | A Feature-based Ensemble Approach to Recognition of Emerging and Rare Named Entities |
| Authors | Utpal Kumar Sikdar, Bj{"o}rn Gamb{"a}ck |
| Abstract | Detecting previously unseen named entities in text is a challenging task. The paper describes how three initial classifier models were built using Conditional Random Fields (CRFs), Support Vector Machines (SVMs) and a Long Short-Term Memory (LSTM) recurrent neural network. The outputs of these three classifiers were then used as features to train another CRF classifier working as an ensemble. 5-fold cross-validation based on training and development data for the emerging and rare named entity recognition shared task showed precision, recall and F1-score of 66.87{%}, 46.75{%} and 54.97{%}, respectively. For surface form evaluation, the CRF ensemble-based system achieved precision, recall and F1 scores of 65.18{%}, 45.20{%} and 53.30{%}. When applied to unseen test data, the model reached 47.92{%} precision, 31.97{%} recall and 38.55{%} F1-score for entity level evaluation, with the corresponding surface form evaluation values of 44.91{%}, 30.47{%} and 36.31{%}. |
| Tasks | Entity Extraction, Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4424/ |
| https://www.aclweb.org/anthology/W17-4424 | |
| PWC | https://paperswithcode.com/paper/a-feature-based-ensemble-approach-to |
| Repo | |
| Framework | |
Long-term 3D Localization and Pose from Semantic Labellings
| Title | Long-term 3D Localization and Pose from Semantic Labellings |
| Authors | Carl Toft1, Carl Olsson1;2, Fredrik Kahl1;2 |
| Abstract | One of the major challenges in camera pose estimation and 3D localization is identifying features that are approximately invariant across seasons and in different weather and lighting conditions. In this paper, we present a method for performing accurate and robust six degrees-of-freedom camera pose estimation based only on the pixelwise semantic labelling of a single query image. Localization is performed using a sparse 3D model consisting of semantically labelled points and curves, and an error function based on how well these project onto corresponding curves in the query image is developed. The method is evaluated on the recently released Oxford Robotcar dataset, showing that by minimizing this error function, the pose can be recovered with decimeter accuracy in many cases. |
| Tasks | Pose Estimation |
| Published | 2017-08-01 |
| URL | https://ieeexplore.ieee.org/document/8265292 |
| http://www.maths.lth.se/matematiklth/vision/publdb/reports/pdf/toft-etal-iccv-2017.pdf | |
| PWC | https://paperswithcode.com/paper/long-term-3d-localization-and-pose-from |
| Repo | |
| Framework | |
Using a Recurrent Neural Network Model for Classification of Tweets Conveyed Influenza-related Information
| Title | Using a Recurrent Neural Network Model for Classification of Tweets Conveyed Influenza-related Information |
| Authors | Chen-Kai Wang, Onkar Singh, Zhao-Li Tang, Hong-Jie Dai |
| Abstract | Traditional disease surveillance systems depend on outpatient reporting and virological test results released by hospitals. These data have valid and accurate information about emerging outbreaks but it{'}s often not timely. In recent years the exponential growth of users getting connected to social media provides immense knowledge about epidemics by sharing related information. Social media can now flag more immediate concerns related to out-breaks in real time. In this paper we apply the long short-term memory recurrent neural net-work (RNN) architecture to classify tweets conveyed influenza-related information and compare its performance with baseline algorithms including support vector machine (SVM), decision tree, naive Bayes, simple logistics, and naive Bayes multinomial. The developed RNN model achieved an F-score of 0.845 on the MedWeb task test set, which outperforms the F-score of SVM without applying the synthetic minority oversampling technique by 0.08. The F-score of the RNN model is within 1{%} of the highest score achieved by SVM with oversampling technique. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5805/ |
| https://www.aclweb.org/anthology/W17-5805 | |
| PWC | https://paperswithcode.com/paper/using-a-recurrent-neural-network-model-for |
| Repo | |
| Framework | |
Practical Locally Private Heavy Hitters
| Title | Practical Locally Private Heavy Hitters |
| Authors | Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Guha Thakurta |
| Abstract | We present new practical local differentially private heavy hitters algorithms achieving optimal or near-optimal worst-case error – TreeHist and Bitstogram. In both algorithms, server running time is $\tilde O(n)$ and user running time is $\tilde O(1)$, hence improving on the prior state-of-the-art result of Bassily and Smith [STOC 2015] requiring $\tilde O(n^{5/2})$ server time and $\tilde O(n^{3/2})$ user time. With a typically large number of participants in local algorithms ($n$ in the millions), this reduction in time complexity, in particular at the user side, is crucial for the use of such algorithms in practice. We implemented Algorithm TreeHist to verify our theoretical analysis and compared its performance with the performance of Google’s RAPPOR code. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6823-practical-locally-private-heavy-hitters |
| http://papers.nips.cc/paper/6823-practical-locally-private-heavy-hitters.pdf | |
| PWC | https://paperswithcode.com/paper/practical-locally-private-heavy-hitters |
| Repo | |
| Framework | |
Legal Framework, Dataset and Annotation Schema for Socially Unacceptable Online Discourse Practices in Slovene
| Title | Legal Framework, Dataset and Annotation Schema for Socially Unacceptable Online Discourse Practices in Slovene |
| Authors | Darja Fi{\v{s}}er, Toma{\v{z}} Erjavec, Nikola Ljube{\v{s}}i{'c} |
| Abstract | In this paper we present the legal framework, dataset and annotation schema of socially unacceptable discourse practices on social networking platforms in Slovenia. On this basis we aim to train an automatic identification and classification system with which we wish contribute towards an improved methodology, understanding and treatment of such practices in the contemporary, increasingly multicultural information society. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3007/ |
| https://www.aclweb.org/anthology/W17-3007 | |
| PWC | https://paperswithcode.com/paper/legal-framework-dataset-and-annotation-schema |
| Repo | |
| Framework | |
Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
| Title | Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks |
| Authors | Tianyu Zhao, Tatsuya Kawahara |
| Abstract | Dialog act segmentation and recognition are basic natural language understanding tasks in spoken dialog systems. This paper investigates a unified architecture for these two tasks, which aims to improve the model{'}s performance on both of the tasks. Compared with past joint models, the proposed architecture can (1) incorporate contextual information in dialog act recognition, and (2) integrate models for tasks of different levels as a whole, i.e. dialog act segmentation on the word level and dialog act recognition on the segment level. Experimental results show that the joint training system outperforms the simple cascading system and the joint coding system on both dialog act segmentation and recognition tasks. |
| Tasks | Speech Recognition, Text Classification |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1071/ |
| https://www.aclweb.org/anthology/I17-1071 | |
| PWC | https://paperswithcode.com/paper/joint-learning-of-dialog-act-segmentation-and |
| Repo | |
| Framework | |
Active Learning from Peers
| Title | Active Learning from Peers |
| Authors | Keerthiram Murugesan, Jaime Carbonell |
| Abstract | This paper addresses the challenge of learning from peers in an online multitask setting. Instead of always requesting a label from a human oracle, the proposed method first determines if the learner for each task can acquire that label with sufficient confidence from its peers either as a task-similarity weighted sum, or from the single most similar task. If so, it saves the oracle query for later use in more difficult cases, and if not it queries the human oracle. The paper develops the new algorithm to exhibit this behavior and proves a theoretical mistake bound for the method compared to the best linear predictor in hindsight. Experiments over three multitask learning benchmark datasets show clearly superior performance over baselines such as assuming task independence, learning only from the oracle and not learning from peer tasks. |
| Tasks | Active Learning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7276-active-learning-from-peers |
| http://papers.nips.cc/paper/7276-active-learning-from-peers.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-from-peers |
| Repo | |
| Framework | |
