Paper Group NANR 194
Accelerate Learning of Deep Hashing With Gradient Attention. Elliptical Constructions in Estonian UD Treebank. The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations. Intervention effects in object relatives in English and Italian: a study in quantitative computational syntax. Proceedings of the 4th Wor …
Accelerate Learning of Deep Hashing With Gradient Attention
| Title | Accelerate Learning of Deep Hashing With Gradient Attention |
| Authors | Long-Kai Huang, Jianda Chen, Sinno Jialin Pan |
| Abstract | Recent years have witnessed the success of learning to hash in fast large-scale image retrieval. As deep learning has shown its superior performance on many computer vision applications, recent designs of learning-based hashing models have been moving from shallow ones to deep architectures. However, based on our analysis, we find that gradient descent based algorithms used in deep hashing models would potentially cause hash codes of a pair of training instances to be updated towards the directions of each other simultaneously during optimization. In the worst case, the paired hash codes switch their directions after update, and consequently, their corresponding distance in the Hamming space remain unchanged. This makes the overall learning process highly inefficient. To address this issue, we propose a new deep hashing model integrated with a novel gradient attention mechanism. Extensive experimental results on three benchmark datasets show that our proposed algorithm is able to accelerate the learning process and obtain competitive retrieval performance compared with state-of-the-art deep hashing models. |
| Tasks | Image Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_Accelerate_Learning_of_Deep_Hashing_With_Gradient_Attention_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Huang_Accelerate_Learning_of_Deep_Hashing_With_Gradient_Attention_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/accelerate-learning-of-deep-hashing-with |
| Repo | |
| Framework | |
Elliptical Constructions in Estonian UD Treebank
| Title | Elliptical Constructions in Estonian UD Treebank |
| Authors | Kadri Muischnek, Liisi Torga |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0305/ |
| https://www.aclweb.org/anthology/W19-0305 | |
| PWC | https://paperswithcode.com/paper/elliptical-constructions-in-estonian-ud |
| Repo | |
| Framework | |
The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations
| Title | The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations |
| Authors | Jo{~a}o Sedoc, Lyle Ungar |
| Abstract | Systemic bias in word embeddings has been widely reported and studied, and efforts made to debias them; however, new contextualized embeddings such as ELMo and BERT are only now being similarly studied. Standard debiasing methods require heterogeneous lists of target words to identify the {``}bias subspace{''}. We show show that using new contextualized word embeddings in conceptor debiasing allows us to more accurately debias word embeddings by breaking target word lists into more homogeneous subsets and then combining ({''}Or{'}ing{''}) the debiasing conceptors of the different subsets. | |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3808/ |
| https://www.aclweb.org/anthology/W19-3808 | |
| PWC | https://paperswithcode.com/paper/the-role-of-protected-class-word-lists-in |
| Repo | |
| Framework | |
Intervention effects in object relatives in English and Italian: a study in quantitative computational syntax
| Title | Intervention effects in object relatives in English and Italian: a study in quantitative computational syntax |
| Authors | Giuseppe Samo, Paola Merlo |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7906/ |
| https://www.aclweb.org/anthology/W19-7906 | |
| PWC | https://paperswithcode.com/paper/intervention-effects-in-object-relatives-in |
| Repo | |
| Framework | |
Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
| Title | Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019) |
| Authors | |
| Abstract | |
| Tasks | Representation Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4300/ |
| https://www.aclweb.org/anthology/W19-4300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-4th-workshop-on-1 |
| Repo | |
| Framework | |
Multiclass Learning from Contradictions
| Title | Multiclass Learning from Contradictions |
| Authors | Sauptik Dhar, Vladimir Cherkassky, Mohak Shah |
| Abstract | We introduce the notion of learning from contradictions, a.k.a Universum learning, for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We show that learning from contradictions (using MU-SVM) incurs lower sample complexity compared to multiclass SVM (M-SVM) by deriving the Natarajan dimension for sample complexity for PAC-learnability of MU-SVM. We also propose an analytic span bound for MU-SVM and demonstrate its utility for model selection resulting in $\sim 2-4 \times$ faster computation times than standard resampling techniques. We empirically demonstrate the efficacy of MU- SVM on several real world datasets achieving $>$ 20% improvement in test accuracies compared to M-SVM. Insights into the underlying behavior of MU-SVM using a histograms-of-projections method are also provided. |
| Tasks | Model Selection |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9048-multiclass-learning-from-contradictions |
| http://papers.nips.cc/paper/9048-multiclass-learning-from-contradictions.pdf | |
| PWC | https://paperswithcode.com/paper/multiclass-learning-from-contradictions |
| Repo | |
| Framework | |
Joint Optimization for Cooperative Image Captioning
| Title | Joint Optimization for Cooperative Image Captioning |
| Authors | Gilad Vered, Gal Oren, Yuval Atzmon, Gal Chechik |
| Abstract | When describing images with natural language, descriptions can be made more informative if tuned for downstream tasks. This can be achieved by training two networks: a “speaker” that generates sentences given an image and a “listener” that uses them to perform a task. Unfortunately, training multiple networks jointly to communicate, faces two major challenges. First, the descriptions generated by a speaker network are discrete and stochastic, making optimization very hard and inefficient. Second, joint training usually causes the vocabulary used during communication to drift and diverge from natural language. To address these challenges, we present an effective optimization technique based on partial-sampling from a multinomial distribution combined with straight-through gradient updates, which we name PSST for Partial-Sampling Straight-Through. We then show that the generated descriptions can be kept close to natural by constraining them to be similar to human descriptions. Together, this approach creates descriptions that are both more discriminative and more natural than previous approaches. Evaluations on the COCO benchmark show that PSST improve the recall@10 from 60% to 86% maintaining comparable language naturalness. Human evaluations show that it also increases naturalness while keeping the discriminative power of generated captions. |
| Tasks | Image Captioning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Vered_Joint_Optimization_for_Cooperative_Image_Captioning_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Vered_Joint_Optimization_for_Cooperative_Image_Captioning_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/joint-optimization-for-cooperative-image |
| Repo | |
| Framework | |
Sentiment Polarity Detection in Azerbaijani Social News Articles
| Title | Sentiment Polarity Detection in Azerbaijani Social News Articles |
| Authors | Sevda Mammadli, Shamsaddin Huseynov, Huseyn Alkaramov, Ulviyya Jafarli, Umid Suleymanov, Samir Rustamov |
| Abstract | Text classification field of natural language processing has been experiencing remarkable growth in recent years. Especially, sentiment analysis has received a considerable attention from both industry and research community. However, only a few research examples exist for Azerbaijani language. The main objective of this research is to apply various machine learning algorithms for determining the sentiment of news articles in Azerbaijani language. Approximately, 30.000 social news articles have been collected from online news sites and labeled manually as negative or positive according to their sentiment categories. Initially, text preprocessing was implemented to data in order to eliminate the noise. Secondly, to convert text to a more machine-readable form, BOW (bag of words) model has been applied. More specifically, two methodologies of BOW model, which are tf-idf and frequency based model have been used as vectorization methods. Additionally, SVM, Random Forest, and Naive Bayes algorithms have been applied as the classification algorithms, and their combinations with two vectorization approaches have been tested and analyzed. Experimental results indicate that SVM outperforms other classification algorithms. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1082/ |
| https://www.aclweb.org/anthology/R19-1082 | |
| PWC | https://paperswithcode.com/paper/sentiment-polarity-detection-in-azerbaijani |
| Repo | |
| Framework | |
UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data
| Title | UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data |
| Authors | Arun Rajendran, Chiyu Zhang, Muhammad Abdul-Mageed |
| Abstract | We examine learning offensive content on Twitter with limited, imbalanced data. For the purpose, we investigate the utility of using various data enhancement methods with a host of classical ensemble classifiers. Among the 75 participating teams in SemEval-2019 sub-task B, our system ranks 6th (with 0.706 macro F1-score). For sub-task C, among the 65 participating teams, our system ranks 9th (with 0.587 macro F1-score). |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2136/ |
| https://www.aclweb.org/anthology/S19-2136 | |
| PWC | https://paperswithcode.com/paper/ubc-nlp-at-semeval-2019-task-6-ensemble |
| Repo | |
| Framework | |
Universality in Learning from Linear Measurements
| Title | Universality in Learning from Linear Measurements |
| Authors | Ehsan Abbasi, Fariborz Salehi, Babak Hassibi |
| Abstract | We study the problem of recovering a structured signal from independently and identically drawn linear measurements. A convex penalty function $f(\cdot)$ is considered which penalizes deviations from the desired structure, and signal recovery is performed by minimizing $f(\cdot)$ subject to the linear measurement constraints. The main question of interest is to determine the minimum number of measurements that is necessary and sufficient for the perfect recovery of the unknown signal with high probability. Our main result states that, under some mild conditions on $f(\cdot)$ and on the distribution from which the linear measurements are drawn, the minimum number of measurements required for perfect recovery depends only on the first and second order statistics of the measurement vectors. As a result, the required of number of measurements can be determining by studying measurement vectors that are Gaussian (and have the same mean vector and covariance matrix) for which a rich literature and comprehensive theory exists. As an application, we show that the minimum number of random quadratic measurements (also known as rank-one projections) required to recover a low rank positive semi-definite matrix is $3nr$, where $n$ is the dimension of the matrix and $r$ is its rank. As a consequence, we settle the long standing open question of determining the minimum number of measurements required for perfect signal recovery in phase retrieval using the celebrated PhaseLift algorithm, and show it to be $3n$. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9404-universality-in-learning-from-linear-measurements |
| http://papers.nips.cc/paper/9404-universality-in-learning-from-linear-measurements.pdf | |
| PWC | https://paperswithcode.com/paper/universality-in-learning-from-linear |
| Repo | |
| Framework | |
UVA Wahoos at SemEval-2019 Task 6: Hate Speech Identification using Ensemble Machine Learning
| Title | UVA Wahoos at SemEval-2019 Task 6: Hate Speech Identification using Ensemble Machine Learning |
| Authors | Murugesan Ramakrishnan, Wlodek Zadrozny, Narges Tabari |
| Abstract | With the growth in the usage of social media, it has become increasingly common for people to hide behind a mask and abuse others. We have attempted to detect such tweets and comments that are malicious in intent, which either targets an individual or a group. Our best classifier for identifying offensive tweets for SubTask A (Classifying offensive vs. nonoffensive) has an accuracy of 83.14{%} and a f1- score of 0.7565 on the actual test data. For SubTask B, to identify if an offensive tweet is targeted (If targeted towards an individual or a group), the classifier performs with an accuracy of 89.17{%} and f1-score of 0.5885. The paper talks about how we generated linguistic and semantic features to build an ensemble machine learning model. By training with more extracts from different sources (Facebook, and more tweets), the paper shows how the accuracy changes with additional training data. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2141/ |
| https://www.aclweb.org/anthology/S19-2141 | |
| PWC | https://paperswithcode.com/paper/uva-wahoos-at-semeval-2019-task-6-hate-speech |
| Repo | |
| Framework | |
YNUWB at SemEval-2019 Task 6: K-max pooling CNN with average meta-embedding for identifying offensive language
| Title | YNUWB at SemEval-2019 Task 6: K-max pooling CNN with average meta-embedding for identifying offensive language |
| Authors | Bin Wang, Xiaobing Zhou, Xuejie Zhang |
| Abstract | This paper describes the system submitted to SemEval 2019 Task 6: OffensEval 2019. The task aims to identify and categorize offensive language in social media, we only participate in Sub-task A, which aims to identify offensive language. In order to address this task, we propose a system based on a K-max pooling convolutional neural network model, and use an argument for averaging as a valid meta-embedding technique to get a metaembedding. Finally, we also use a cyclic learning rate policy to improve model performance. Our model achieves a Macro F1-score of 0.802 (ranked 9/103) in the Sub-task A. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2143/ |
| https://www.aclweb.org/anthology/S19-2143 | |
| PWC | https://paperswithcode.com/paper/ynuwb-at-semeval-2019-task-6-k-max-pooling |
| Repo | |
| Framework | |
Simple Construction of Mixed-Language Texts for Vocabulary Learning
| Title | Simple Construction of Mixed-Language Texts for Vocabulary Learning |
| Authors | Adithya Renduchintala, Philipp Koehn, Jason Eisner |
| Abstract | We present a machine foreign-language teacher that takes documents written in a student{'}s native language and detects situations where it can replace words with their foreign glosses such that new foreign vocabulary can be learned simply through reading the resulting mixed-language text. We show that it is possible to design such a machine teacher without any supervised data from (human) students. We accomplish this by modifying a cloze language model to incrementally learn new vocabulary items, and use this language model as a proxy for the word guessing and learning ability of real students. Our machine foreign-language teacher decides which subset of words to replace by consulting this language model. We evaluate three variants of our student proxy language models through a study on Amazon Mechanical Turk (MTurk). We find that MTurk {``}students{''} were able to guess the meanings of foreign words introduced by the machine teacher with high accuracy for both function words as well as content words in two out of the three models. In addition, we show that students are able to retain their knowledge about the foreign words after they finish reading the document. | |
| Tasks | Language Modelling |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4439/ |
| https://www.aclweb.org/anthology/W19-4439 | |
| PWC | https://paperswithcode.com/paper/simple-construction-of-mixed-language-texts |
| Repo | |
| Framework | |
The Challenges of Using Neural Machine Translation for Literature
| Title | The Challenges of Using Neural Machine Translation for Literature |
| Authors | Evgeny Matusov |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7302/ |
| https://www.aclweb.org/anthology/W19-7302 | |
| PWC | https://paperswithcode.com/paper/the-challenges-of-using-neural-machine |
| Repo | |
| Framework | |
TueFact at SemEval 2019 Task 8: Fact checking in community question answering forums: context matters
| Title | TueFact at SemEval 2019 Task 8: Fact checking in community question answering forums: context matters |
| Authors | R{'e}ka Juh{'a}sz, Franziska Barbara Linnenschmidt, Teslin Roys |
| Abstract | The SemEval 2019 Task 8 on Fact-Checking in community question answering forums aimed to classify questions into categories and verify the correctness of answers given on the QatarLiving public forum. The task was divided into two subtasks: the first classifying the question, the second the answers. The TueFact system described in this paper used different approaches for the two subtasks. Subtask A makes use of word vectors based on a bag-of-word-ngram model using up to trigrams. Predictions are done using multi-class logistic regression. The official SemEval result lists an accuracy of 0.60. Subtask B uses vectorized character n-grams up to trigrams instead. Predictions are done using a LSTM model and achieved an accuracy of 0.53 on the final SemEval Task 8 evaluation set. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2206/ |
| https://www.aclweb.org/anthology/S19-2206 | |
| PWC | https://paperswithcode.com/paper/tuefact-at-semeval-2019-task-8-fact-checking |
| Repo | |
| Framework | |
