Paper Group NANR 252
GSI-UPM at SemEval-2019 Task 5: Semantic Similarity and Word Embeddings for Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter. HATEMINER at SemEval-2019 Task 5: Hate speech detection against Immigrants and Women in Twitter using a Multinomial Naive Bayes Classifier. A3-108 Machine Translation System for LoResMT 2019. Nor …
GSI-UPM at SemEval-2019 Task 5: Semantic Similarity and Word Embeddings for Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter
| Title | GSI-UPM at SemEval-2019 Task 5: Semantic Similarity and Word Embeddings for Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter |
| Authors | Diego Benito, Oscar Araque, Carlos A. Iglesias |
| Abstract | This paper describes the GSI-UPM system for SemEval-2019 Task 5, which tackles multilingual detection of hate speech on Twitter. The main contribution of the paper is the use of a method based on word embeddings and semantic similarity combined with traditional paradigms, such as n-grams, TF-IDF and POS. This combination of several features is fine-tuned through ablation tests, demonstrating the usefulness of different features. While our approach outperforms baseline classifiers on different sub-tasks, the best of our submitted runs reached the 5th position on the Spanish sub-task A. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2070/ |
| https://www.aclweb.org/anthology/S19-2070 | |
| PWC | https://paperswithcode.com/paper/gsi-upm-at-semeval-2019-task-5-semantic |
| Repo | |
| Framework | |
HATEMINER at SemEval-2019 Task 5: Hate speech detection against Immigrants and Women in Twitter using a Multinomial Naive Bayes Classifier
| Title | HATEMINER at SemEval-2019 Task 5: Hate speech detection against Immigrants and Women in Twitter using a Multinomial Naive Bayes Classifier |
| Authors | Nikhil Chakravartula |
| Abstract | This paper describes our participation in the SemEval 2019 Task 5 - Multilingual Detection of Hate. This task aims to identify hate speech against two specific targets, immigrants and women. We compare and contrast the performance of different word and sentence level embeddings on the state-of-the-art classification algorithms. Our final submission is a Multinomial binarized Naive Bayes model for both the subtasks in the English version. |
| Tasks | Hate Speech Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2071/ |
| https://www.aclweb.org/anthology/S19-2071 | |
| PWC | https://paperswithcode.com/paper/hateminer-at-semeval-2019-task-5-hate-speech |
| Repo | |
| Framework | |
A3-108 Machine Translation System for LoResMT 2019
| Title | A3-108 Machine Translation System for LoResMT 2019 |
| Authors | Saumitra Yadav, V Mujadia, an, Manish Shrivastava |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6810/ |
| https://www.aclweb.org/anthology/W19-6810 | |
| PWC | https://paperswithcode.com/paper/a3-108-machine-translation-system-for-loresmt |
| Repo | |
| Framework | |
Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation
| Title | Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation |
| Authors | Yogesh Balaji, Rama Chellappa, Soheil Feizi |
| Abstract | Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, we focus on mixture distributions that arise naturally in several application domains where the data contains different sub-populations. For mixture distributions, established distance measures such as the Wasserstein distance do not take into account imbalanced mixture proportions. Thus, even if two mixture distributions have identical mixture components but different mixture proportions, the Wasserstein distance between them will be large. This often leads to undesired results in distance-based learning methods for mixture distributions. In this paper, we resolve this issue by introducing the Normalized Wasserstein measure. The key idea is to introduce mixture proportions as optimization variables, effectively normalizing mixture proportions in the Wasserstein formulation. Using the proposed normalized Wasserstein measure leads to significant performance gains for mixture distributions with imbalanced mixture proportions compared to the vanilla Wasserstein distance. We demonstrate the effectiveness of the proposed measure in GANs, domain adaptation and adversarial clustering in several benchmark datasets. |
| Tasks | Domain Adaptation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Balaji_Normalized_Wasserstein_for_Mixture_Distributions_With_Applications_in_Adversarial_Learning_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Balaji_Normalized_Wasserstein_for_Mixture_Distributions_With_Applications_in_Adversarial_Learning_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/normalized-wasserstein-for-mixture |
| Repo | |
| Framework | |
MineriaUNAM at SemEval-2019 Task 5: Detecting Hate Speech in Twitter using Multiple Features in a Combinatorial Framework
| Title | MineriaUNAM at SemEval-2019 Task 5: Detecting Hate Speech in Twitter using Multiple Features in a Combinatorial Framework |
| Authors | Luis Enrique Argota Vega, Jorge Carlos Reyes-Maga{~n}a, Helena G{'o}mez-Adorno, Gemma Bel-Enguix |
| Abstract | This paper presents our approach to the Task 5 of Semeval-2019, which aims at detecting hate speech against immigrants and women in Twitter. The task consists of two sub-tasks, in Spanish and English: (A) detection of hate speech and (B) classification of hateful tweets as aggressive or not, and identification of the target harassed as individual or group. We used linguistically motivated features and several types of n-grams (words, characters, functional words, punctuation symbols, POS, among others). For task A, we trained a Support Vector Machine using a combinatorial framework, whereas for task B we followed a multi-labeled approach using the Random Forest classifier. Our approach achieved the highest F1-score in sub-task A for the Spanish language. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2079/ |
| https://www.aclweb.org/anthology/S19-2079 | |
| PWC | https://paperswithcode.com/paper/mineriaunam-at-semeval-2019-task-5-detecting |
| Repo | |
| Framework | |
A large-scale study of the effects of word frequency and predictability in naturalistic reading
| Title | A large-scale study of the effects of word frequency and predictability in naturalistic reading |
| Authors | Cory Shain |
| Abstract | A number of psycholinguistic studies have factorially manipulated words{'} contextual predictabilities and corpus frequencies and shown separable effects of each on measures of human sentence processing, a pattern which has been used to support distinct mechanisms underlying prediction on the one hand and lexical retrieval on the other. This paper examines the generalizability of this finding to more realistic conditions of sentence processing by studying effects of frequency and predictability in three large-scale naturalistic reading corpora. Results show significant effects of word frequency and predictability in isolation but no effect of frequency over and above predictability, and thus do not provide evidence of distinct mechanisms. The non-replication of separable effects in a naturalistic setting raises doubts about the existence of such a distinction in everyday sentence comprehension. Instead, these results are consistent with previous claims that apparent effects of frequency are underlyingly effects of predictability. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1413/ |
| https://www.aclweb.org/anthology/N19-1413 | |
| PWC | https://paperswithcode.com/paper/a-large-scale-study-of-the-effects-of-word |
| Repo | |
| Framework | |
Negative Focus Detection via Contextual Attention Mechanism
| Title | Negative Focus Detection via Contextual Attention Mechanism |
| Authors | Longxiang Shen, Bowei Zou, Yu Hong, Guodong Zhou, Qiaoming Zhu, AiTi Aw |
| Abstract | Negation is a universal but complicated linguistic phenomenon, which has received considerable attention from the NLP community over the last decade, since a negated statement often carries both an explicit negative focus and implicit positive meanings. For the sake of understanding a negated statement, it is critical to precisely detect the negative focus in context. However, how to capture contextual information for negative focus detection is still an open challenge. To well address this, we come up with an attention-based neural network to model contextual information. In particular, we introduce a framework which consists of a Bidirectional Long Short-Term Memory (BiLSTM) neural network and a Conditional Random Fields (CRF) layer to effectively encode the order information and the long-range context dependency in a sentence. Moreover, we design two types of attention mechanisms, word-level contextual attention and topic-level contextual attention, to take advantage of contextual information across sentences from both the word perspective and the topic perspective, respectively. Experimental results on the SEM{'}12 shared task corpus show that our approach achieves the best performance on negative focus detection, yielding an absolute improvement of 2.11{%} over the state-of-the-art. This demonstrates the great effectiveness of the two types of contextual attention mechanisms. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1230/ |
| https://www.aclweb.org/anthology/D19-1230 | |
| PWC | https://paperswithcode.com/paper/negative-focus-detection-via-contextual |
| Repo | |
| Framework | |
Spatiotemporal Feature Residual Propagation for Action Prediction
| Title | Spatiotemporal Feature Residual Propagation for Action Prediction |
| Authors | He Zhao, Richard P. Wildes |
| Abstract | Recognizing actions from limited preliminary video observations has seen considerable recent progress. Typically, however, such progress has been had without explicitly modeling fine-grained motion evolution as a potentially valuable information source. In this study, we address this task by investigating how action patterns evolve over time in a spatial feature space. There are three key components to our system. First, we work with intermediate-layer ConvNet features, which allow for abstraction from raw data, while retaining spatial layout, which is sacrificed in approaches that rely on vectorized global representations. Second, instead of propagating features per se, we propagate their residuals across time, which allows for a compact representation that reduces redundancy while retaining essential information about evolution over time. Third, we employ a Kalman filter to combat error build-up and unify across prediction start times. Extensive experimental results on the JHMDB21, UCF101 and BIT datasets show that our approach leads to a new state-of-the-art in action prediction. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhao_Spatiotemporal_Feature_Residual_Propagation_for_Action_Prediction_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhao_Spatiotemporal_Feature_Residual_Propagation_for_Action_Prediction_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spatiotemporal-feature-residual-propagation |
| Repo | |
| Framework | |
Attribute Manipulation Generative Adversarial Networks for Fashion Images
| Title | Attribute Manipulation Generative Adversarial Networks for Fashion Images |
| Authors | Kenan E. Ak, Joo Hwee Lim, Jo Yew Tham, Ashraf A. Kassim |
| Abstract | Recent advances in Generative Adversarial Networks (GANs) have made it possible to conduct multi-domain image-to-image translation using a single generative network. While recent methods such as Ganimation and SaGAN are able to conduct translations on attribute-relevant regions using attention, they do not perform well when the number of attributes increases as the training of attention masks mostly rely on classification losses. To address this and other limitations, we introduce Attribute Manipulation Generative Adversarial Networks (AMGAN) for fashion images. While AMGAN’s generator network uses class activation maps (CAMs) to empower its attention mechanism, it also exploits perceptual losses by assigning reference (target) images based on attribute similarities. AMGAN incorporates an additional discriminator network that focuses on attribute-relevant regions to detect unrealistic translations. Additionally, AMGAN can be controlled to perform attribute manipulations on specific regions such as the sleeve or torso regions. Experiments show that AMGAN outperforms state-of-the-art methods using traditional evaluation metrics as well as an alternative one that is based on image retrieval. |
| Tasks | Image Retrieval, Image-to-Image Translation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Ak_Attribute_Manipulation_Generative_Adversarial_Networks_for_Fashion_Images_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Ak_Attribute_Manipulation_Generative_Adversarial_Networks_for_Fashion_Images_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/attribute-manipulation-generative-adversarial |
| Repo | |
| Framework | |
INGEOTEC at SemEval-2019 Task 5 and Task 6: A Genetic Programming Approach for Text Classification
| Title | INGEOTEC at SemEval-2019 Task 5 and Task 6: A Genetic Programming Approach for Text Classification |
| Authors | Mario Graff, Mir, Sabino a-Jim{'e}nez, Eric Tellez, Daniela Alej Ochoa, ra |
| Abstract | This paper describes our participation in HatEval and OffensEval challenges for English and Spanish languages. We used several approaches, B4MSA, FastText, and EvoMSA. Best results were achieved with EvoMSA, which is a multilingual and domain-independent architecture that combines the prediction of different knowledge sources to solve text classification problems. |
| Tasks | Text Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2114/ |
| https://www.aclweb.org/anthology/S19-2114 | |
| PWC | https://paperswithcode.com/paper/ingeotec-at-semeval-2019-task-5-and-task-6-a |
| Repo | |
| Framework | |
Towards Natural and Accurate Future Motion Prediction of Humans and Animals
| Title | Towards Natural and Accurate Future Motion Prediction of Humans and Animals |
| Authors | Zhenguang Liu, Shuang Wu, Shuyuan Jin, Qi Liu, Shijian Lu, Roger Zimmermann, Li Cheng |
| Abstract | Anticipating the future motions of 3D articulate objects is challenging due to its non-linear and highly stochastic nature. Current approaches typically represent the skeleton of an articulate object as a set of 3D joints, which unfortunately ignores the relationship between joints, and fails to encode fine-grained anatomical constraints. Moreover, conventional recurrent neural networks, such as LSTM and GRU, are employed to model motion contexts, which inherently have difficulties in capturing long-term dependencies. To address these problems, we propose to explicitly encode anatomical constraints by modeling their skeletons with a Lie algebra representation. Importantly, a hierarchical recurrent network structure is developed to simultaneously encodes local contexts of individual frames and global contexts of the sequence. We proceed to explore the applications of our approach to several distinct quantities including human, fish, and mouse. Extensive experiments show that our approach achieves more natural and accurate predictions over state-of-the-art methods. |
| Tasks | motion prediction |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Towards_Natural_and_Accurate_Future_Motion_Prediction_of_Humans_and_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Towards_Natural_and_Accurate_Future_Motion_Prediction_of_Humans_and_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/towards-natural-and-accurate-future-motion |
| Repo | |
| Framework | |
Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue
| Title | Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue |
| Authors | Chenguang Zhu, Michael Zeng, Xuedong Huang |
| Abstract | In task-oriented dialogues, Natural Language Generation (NLG) is the final yet crucial step to produce user-facing system utterances. The result of NLG is directly related to the perceived quality and usability of a dialogue system. While most existing systems provide semantically correct responses given goals to present, they struggle to match the variation and fluency in the human language. In this paper, we propose a novel multi-task learning framework, NLG-LM, for natural language generation. In addition to generating high-quality responses conveying the required information, it also explicitly targets for naturalness in generated responses via an unconditioned language model. This can significantly improve the learning of style and variation in human language. Empirical results show that this multi-task learning framework outperforms previous models across multiple datasets. For example, it improves the previous best BLEU score on the E2E-NLG dataset by 2.2{%}, and on the Laptop dataset by 6.1{%}. |
| Tasks | Language Modelling, Multi-Task Learning, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1123/ |
| https://www.aclweb.org/anthology/D19-1123 | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-natural-language |
| Repo | |
| Framework | |
Duluth at SemEval-2019 Task 4: The Pioquinto Manterola Hyperpartisan News Detector
| Title | Duluth at SemEval-2019 Task 4: The Pioquinto Manterola Hyperpartisan News Detector |
| Authors | Saptarshi Sengupta, Ted Pedersen |
| Abstract | This paper describes the Pioquinto Manterola Hyperpartisan News Detector, which participated in SemEval-2019 Task 4. Hyperpartisan news is highly polarized and takes a very biased or one{–}sided view of a particular story. We developed two variants of our system, the more successful was a Logistic Regression classifier based on unigram features. This was our official entry in the task, and it placed 23rd of 42 participating teams. Our second variant was a Convolutional Neural Network that did not perform as well. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2162/ |
| https://www.aclweb.org/anthology/S19-2162 | |
| PWC | https://paperswithcode.com/paper/duluth-at-semeval-2019-task-4-the-pioquinto |
| Repo | |
| Framework | |
Enhancing Neural Data-To-Text Generation Models with External Background Knowledge
| Title | Enhancing Neural Data-To-Text Generation Models with External Background Knowledge |
| Authors | Shuang Chen, Jinpeng Wang, Xiaocheng Feng, Feng Jiang, Bing Qin, Chin-Yew Lin |
| Abstract | Recent neural models for data-to-text generation rely on massive parallel pairs of data and text to learn the writing knowledge. They often assume that writing knowledge can be acquired from the training data alone. However, when people are writing, they not only rely on the data but also consider related knowledge. In this paper, we enhance neural data-to-text models with external knowledge in a simple but effective way to improve the fidelity of generated text. Besides relying on parallel data and text as in previous work, our model attends to relevant external knowledge, encoded as a temporary memory, and combines this knowledge with the context representation of data before generating words. This allows the model to infer relevant facts which are not explicitly stated in the data table from an external knowledge source. Experimental results on twenty-one Wikipedia infobox-to-text datasets show our model, KBAtt, consistently improves a state-of-the-art model on most of the datasets. In addition, to quantify when and why external knowledge is effective, we design a metric, KBGain, which shows a strong correlation with the observed performance boost. This result demonstrates the relevance of external knowledge and sparseness of original data are the main factors affecting system performance. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1299/ |
| https://www.aclweb.org/anthology/D19-1299 | |
| PWC | https://paperswithcode.com/paper/enhancing-neural-data-to-text-generation |
| Repo | |
| Framework | |
UNBNLP at SemEval-2019 Task 5 and 6: Using Language Models to Detect Hate Speech and Offensive Language
| Title | UNBNLP at SemEval-2019 Task 5 and 6: Using Language Models to Detect Hate Speech and Offensive Language |
| Authors | Ali Hakimi Parizi, Milton King, Paul Cook |
| Abstract | In this paper we apply a range of approaches to language modeling {–} including word-level n-gram and neural language models, and character-level neural language models {–} to the problem of detecting hate speech and offensive language. Our findings indicate that language models are able to capture knowledge of whether text is hateful or offensive. However, our findings also indicate that more conventional approaches to text classification often perform similarly or better. |
| Tasks | Language Modelling, Text Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2092/ |
| https://www.aclweb.org/anthology/S19-2092 | |
| PWC | https://paperswithcode.com/paper/unbnlp-at-semeval-2019-task-5-and-6-using |
| Repo | |
| Framework | |
