Paper Group NANR 64
Learning Deep Priors for Image Dehazing. JTML at SemEval-2019 Task 6: Offensive Tweets Identification using Convolutional Neural Networks. Twitter Homophily: Network Based Prediction of User’s Occupation. An Impossible Dialogue! Nominal Utterances and Populist Rhetoric in an Italian Twitter Corpus of Hate Speech against Immigrants. Learning-In-The- …
Learning Deep Priors for Image Dehazing
| Title | Learning Deep Priors for Image Dehazing |
| Authors | Yang Liu, Jinshan Pan, Jimmy Ren, Zhixun Su |
| Abstract | Image dehazing is a well-known ill-posed problem, which usually requires some image priors to make the problem well-posed. We propose an effective iteration algorithm with deep CNNs to learn haze-relevant priors for image dehazing. We formulate the image dehazing problem as the minimization of a variational model with favorable data fidelity terms and prior terms to regularize the model. We solve the variational model based on the classical gradient descent method with built-in deep CNNs so that iteration-wise image priors for the atmospheric light, transmission map and clear image can be well estimated. Our method combines the properties of both the physical formation of image dehazing as well as deep learning approaches. We show that it is able to generate clear images as well as accurate atmospheric light and transmission maps. Extensive experimental results demonstrate that the proposed algorithm performs favorably against state-of-the-art methods in both benchmark datasets and real-world images. |
| Tasks | Image Dehazing |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Learning_Deep_Priors_for_Image_Dehazing_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Learning_Deep_Priors_for_Image_Dehazing_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-priors-for-image-dehazing |
| Repo | |
| Framework | |
JTML at SemEval-2019 Task 6: Offensive Tweets Identification using Convolutional Neural Networks
| Title | JTML at SemEval-2019 Task 6: Offensive Tweets Identification using Convolutional Neural Networks |
| Authors | Johnny Torres, Carmen Vaca |
| Abstract | In this paper, we propose the use of a Convolutional Neural Network (CNN) to identify offensive tweets, as well as the type and target of the offense. We use an end-to-end model (i.e., no preprocessing) and fine-tune pre-trained embeddings (FastText) during training for learning words{'} representation. We compare the proposed CNN model to a baseline model, such as Linear Regression, and several neural models. The results show that CNN outperforms other models, and stands as a simple but strong baseline in comparison to other systems submitted to the Shared Task. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2117/ |
| https://www.aclweb.org/anthology/S19-2117 | |
| PWC | https://paperswithcode.com/paper/jtml-at-semeval-2019-task-6-offensive-tweets |
| Repo | |
| Framework | |
Twitter Homophily: Network Based Prediction of User’s Occupation
| Title | Twitter Homophily: Network Based Prediction of User’s Occupation |
| Authors | Jiaqi Pan, Rishabh Bhardwaj, Wei Lu, Hai Leong Chieu, Xinghao Pan, Ni Yi Puay |
| Abstract | In this paper, we investigate the importance of social network information compared to content information in the prediction of a Twitter user{'}s occupational class. We show that the content information of a user{'}s tweets, the profile descriptions of a user{'}s follower/following community, and the user{'}s social network provide useful information for classifying a user{'}s occupational group. In our study, we extend an existing data set for this problem, and we achieve significantly better performance by using social network homophily that has not been fully exploited in previous work. In our analysis, we found that by using the graph convolutional network to exploit social homophily, we can achieve competitive performance on this data set with just a small fraction of the training data. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1252/ |
| https://www.aclweb.org/anthology/P19-1252 | |
| PWC | https://paperswithcode.com/paper/twitter-homophily-network-based-prediction-of |
| Repo | |
| Framework | |
An Impossible Dialogue! Nominal Utterances and Populist Rhetoric in an Italian Twitter Corpus of Hate Speech against Immigrants
| Title | An Impossible Dialogue! Nominal Utterances and Populist Rhetoric in an Italian Twitter Corpus of Hate Speech against Immigrants |
| Authors | Com, Gloria ini, Viviana Patti |
| Abstract | The paper proposes an investigation on the role of populist themes and rhetoric in an Italian Twitter corpus of hate speech against immigrants. The corpus had been annotated with four new layers of analysis: Nominal Utterances, that can be seen as consistent with populist rhetoric; In-out-group rhetoric, a very common populist strategy to polarize public opinion; Slogan-like nominal utterances, that may convey the call for severe illiberal policies against immigrants; News, to recognize the role of newspapers (headlines or reference to articles) in the Twitter political discourse on immigration featured by hate speech. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3518/ |
| https://www.aclweb.org/anthology/W19-3518 | |
| PWC | https://paperswithcode.com/paper/an-impossible-dialogue-nominal-utterances-and |
| Repo | |
| Framework | |
Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations
| Title | Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations |
| Authors | Andrew Spielberg, Allan Zhao, Yuanming Hu, Tao Du, Wojciech Matusik, Daniela Rus |
| Abstract | Soft robots have continuum solid bodies that can deform in an infinite number of ways. Controlling soft robots is very challenging as there are no closed form solutions. We present a learning-in-the-loop co-optimization algorithm in which a latent state representation is learned as the robot figures out how to solve the task. Our solution marries hybrid particle-grid-based simulation with deep, variational convolutional autoencoder architectures that can capture salient features of robot dynamics with high efficacy. We demonstrate our dynamics-aware feature learning algorithm on both 2D and 3D soft robots, and show that it is more robust and faster converging than the dynamics-oblivious baseline. We validate the behavior of our algorithm with visualizations of the learned representation. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9038-learning-in-the-loop-optimization-end-to-end-control-and-co-design-of-soft-robots-through-learned-deep-latent-representations |
| http://papers.nips.cc/paper/9038-learning-in-the-loop-optimization-end-to-end-control-and-co-design-of-soft-robots-through-learned-deep-latent-representations.pdf | |
| PWC | https://paperswithcode.com/paper/learning-in-the-loop-optimization-end-to-end |
| Repo | |
| Framework | |
Deep Blind Hyperspectral Image Fusion
| Title | Deep Blind Hyperspectral Image Fusion |
| Authors | Wu Wang, Weihong Zeng, Yue Huang, Xinghao Ding, John Paisley |
| Abstract | Hyperspectral image fusion (HIF) reconstructs high spatial resolution hyperspectral images from low spatial resolution hyperspectral images and high spatial resolution multispectral images. Previous works usually assume that the linear mapping between the point spread functions of the hyperspectral camera and the spectral response functions of the conventional camera is known. This is unrealistic in many scenarios. We propose a method for blind HIF problem based on deep learning, where the estimation of the observation model and fusion process are optimized iteratively and alternatingly during the super-resolution reconstruction. In addition, the proposed framework enforces simultaneous spatial and spectral accuracy. Using three public datasets, the experimental results demonstrate that the proposed algorithm outperforms existing blind and non-blind methods. |
| Tasks | Super-Resolution |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Deep_Blind_Hyperspectral_Image_Fusion_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Deep_Blind_Hyperspectral_Image_Fusion_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-blind-hyperspectral-image-fusion |
| Repo | |
| Framework | |
Evaluating Ways of Adapting Word Similarity
| Title | Evaluating Ways of Adapting Word Similarity |
| Authors | Libby Barak, Adele Goldberg |
| Abstract | People judge pairwise similarity by deciding which aspects of the words{'} meanings are relevant for the comparison of the given pair. However, computational representations of meaning rely on dimensions of the vector representation for similarity comparisons, without considering the specific pairing at hand. Prior work has adapted computational similarity judgments by using the softmax function in order to address this limitation by capturing asymmetry in human judgments. We extend this analysis by showing that a simple modification of cosine similarity offers a better correlation with human judgments over a comprehensive dataset. The modification performs best when the similarity between two words is calculated with reference to other words that are most similar and dissimilar to the pair. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3639/ |
| https://www.aclweb.org/anthology/W19-3639 | |
| PWC | https://paperswithcode.com/paper/evaluating-ways-of-adapting-word-similarity |
| Repo | |
| Framework | |
Proceedings of the 13th International Conference on Computational Semantics - Student Papers
| Title | Proceedings of the 13th International Conference on Computational Semantics - Student Papers |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0600/ |
| https://www.aclweb.org/anthology/W19-0600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-international-6 |
| Repo | |
| Framework | |
Towards the Data-driven System for Rhetorical Parsing of Russian Texts
| Title | Towards the Data-driven System for Rhetorical Parsing of Russian Texts |
| Authors | Artem Shelmanov, Dina Pisarevskaya, Elena Chistova, Svetlana Toldova, Maria Kobozeva, Ivan Smirnov |
| Abstract | Results of the first experimental evaluation of machine learning models trained on Ru-RSTreebank {–} first Russian corpus annotated within RST framework {–} are presented. Various lexical, quantitative, morphological, and semantic features were used. In rhetorical relation classification, ensemble of CatBoost model with selected features and a linear SVM model provides the best score (macro F1 = 54.67 {\mbox{$\pm$}} 0.38). We discover that most of the important features for rhetorical relation classification are related to discourse connectives derived from the connectives lexicon for Russian and from other sources. |
| Tasks | Relation Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2711/ |
| https://www.aclweb.org/anthology/W19-2711 | |
| PWC | https://paperswithcode.com/paper/towards-the-data-driven-system-for-rhetorical |
| Repo | |
| Framework | |
Emotion Impacts Speech Recognition Performance
| Title | Emotion Impacts Speech Recognition Performance |
| Authors | Rushab Munot, Ani Nenkova |
| Abstract | It has been established that the performance of speech recognition systems depends on multiple factors including the lexical content, speaker identity and dialect. Here we use three English datasets of acted emotion to demonstrate that emotional content also impacts the performance of commercial systems. On two of the corpora, emotion is a bigger contributor to recognition errors than speaker identity and on two, neutral speech is recognized considerably better than emotional speech. We further evaluate the commercial systems on spontaneous interactions that contain portions of emotional speech. We propose and validate on the acted datasets, a method that allows us to evaluate the overall impact of emotion on recognition even when manual transcripts are not available. Using this method, we show that emotion in natural spontaneous dialogue is a less prominent but still significant factor in recognition accuracy. |
| Tasks | Speech Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-3003/ |
| https://www.aclweb.org/anthology/N19-3003 | |
| PWC | https://paperswithcode.com/paper/emotion-impacts-speech-recognition |
| Repo | |
| Framework | |
RST-Tace A tool for automatic comparison and evaluation of RST trees
| Title | RST-Tace A tool for automatic comparison and evaluation of RST trees |
| Authors | Shujun Wan, Tino Kutschbach, Anke L{"u}deling, Manfred Stede |
| Abstract | This paper presents RST-Tace, a tool for automatic comparison and evaluation of RST trees. RST-Tace serves as an implementation of Iruskieta{'}s comparison method, which allows trees to be compared and evaluated without the influence of decisions at lower levels in a tree in terms of four factors: constituent, attachment point, nuclearity as well as relation. RST-Tace can be used regardless of the language or the size of rhetorical trees. This tool aims to measure the agreement between two annotators. The result is reflected by F-measure and inter-annotator agreement. Both the comparison table and the result of the evaluation can be obtained automatically. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2712/ |
| https://www.aclweb.org/anthology/W19-2712 | |
| PWC | https://paperswithcode.com/paper/rst-tace-a-tool-for-automatic-comparison-and |
| Repo | |
| Framework | |
Rationally Reappraising ATIS-based Dialogue Systems
| Title | Rationally Reappraising ATIS-based Dialogue Systems |
| Authors | Jingcheng Niu, Gerald Penn |
| Abstract | The Air Travel Information Service (ATIS) corpus has been the most common benchmark for evaluating Spoken Language Understanding (SLU) tasks for more than three decades since it was released. Recent state-of-the-art neural models have obtained F1-scores near 98{%} on the task of slot filling. We developed a rule-based grammar for the ATIS domain that achieves a 95.82{%} F1-score on our evaluation set. In the process, we furthermore discovered numerous shortcomings in the ATIS corpus annotation, which we have fixed. This paper presents a detailed account of these shortcomings, our proposed repairs, our rule-based grammar and the neural slot-filling architectures associated with ATIS. We also rationally reappraise the motivations for choosing a neural architecture in view of this account. Fixing the annotation errors results in a relative error reduction of between 19.4 and 52{%} across all architectures. We nevertheless argue that neural models must play a different role in ATIS dialogues because of the latter{'}s lack of variety. |
| Tasks | Slot Filling, Spoken Language Understanding |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1550/ |
| https://www.aclweb.org/anthology/P19-1550 | |
| PWC | https://paperswithcode.com/paper/rationally-reappraising-atis-based-dialogue |
| Repo | |
| Framework | |
MRP 2019: Cross-Framework Meaning Representation Parsing
| Title | MRP 2019: Cross-Framework Meaning Representation Parsing |
| Authors | Stephan Oepen, Omri Abend, Jan Hajic, Daniel Hershcovich, Marco Kuhlmann, Tim O{'}Gorman, Nianwen Xue, Jayeol Chun, Milan Straka, Zdenka Uresova |
| Abstract | The 2019 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks. Five distinct approaches to the representation of sentence meaning in the form of directed graph were represented in the training and evaluation data for the task, packaged in a uniform abstract graph representation and serialization. The task received submissions from eighteen teams, of which five do not participate in the official ranking because they arrived after the closing deadline, made use of additional training data, or involved one of the task co-organizers. All technical information regarding the task, including system submissions, official results, and links to supporting resources and software are available from the task web site at: http://mrp.nlpl.eu |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2001/ |
| https://www.aclweb.org/anthology/K19-2001 | |
| PWC | https://paperswithcode.com/paper/mrp-2019-cross-framework-meaning |
| Repo | |
| Framework | |
An ensemble CNN method for biomedical entity normalization
| Title | An ensemble CNN method for biomedical entity normalization |
| Authors | Pan Deng, Haipeng Chen, Mengyao Huang, Xiaowen Ruan, Liang Xu |
| Abstract | Different representations of the same concept could often be seen in scientific reports and publications. Entity normalization (or entity linking) is the task to match the different representations to their standard concepts. In this paper, we present a two-step ensemble CNN method that normalizes microbiology-related entities in free text to concepts in standard dictionaries. The method is capable of linking entities when only a small microbiology-related biomedical corpus is available for training, and achieved reasonable performance in the online test of the BioNLP-OST19 shared task Bacteria Biotope. |
| Tasks | Entity Linking |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5721/ |
| https://www.aclweb.org/anthology/D19-5721 | |
| PWC | https://paperswithcode.com/paper/an-ensemble-cnn-method-for-biomedical-entity |
| Repo | |
| Framework | |
Multilingual segmentation based on neural networks and pre-trained word embeddings
| Title | Multilingual segmentation based on neural networks and pre-trained word embeddings |
| Authors | Mikel Iruskieta, Kepa Bengoetxea, Aitziber Atutxa Salazar, Arantza Diaz de Ilarraza |
| Abstract | The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation. We report F1 results for 6 languages: Basque (0.853), English (0.919), French (0.907), German (0.913), Portuguese (0.926) and Spanish (0.868 and 0.769). Finally, we also pursued an error analysis based on clause typology for Basque and Spanish, in order to understand the performance of the segmenter. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2716/ |
| https://www.aclweb.org/anthology/W19-2716 | |
| PWC | https://paperswithcode.com/paper/multilingual-segmentation-based-on-neural |
| Repo | |
| Framework | |
