Paper Group NANR 157
Bootstrapping Polar-Opposite Emotion Dimensions from Online Reviews. The JHU Parallel Corpus Filtering Systems for WMT 2018. Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts. Building A Handwritten Cuneiform Character Imageset. Visualization of the Topic Space of Argument Search Results in args.me. An Assessment o …
Bootstrapping Polar-Opposite Emotion Dimensions from Online Reviews
| Title | Bootstrapping Polar-Opposite Emotion Dimensions from Online Reviews |
| Authors | Luwen Huangfu, Mihai Surdeanu |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1098/ |
| https://www.aclweb.org/anthology/L18-1098 | |
| PWC | https://paperswithcode.com/paper/bootstrapping-polar-opposite-emotion |
| Repo | |
| Framework | |
The JHU Parallel Corpus Filtering Systems for WMT 2018
| Title | The JHU Parallel Corpus Filtering Systems for WMT 2018 |
| Authors | Huda Khayrallah, Hainan Xu, Philipp Koehn |
| Abstract | This work describes our submission to the WMT18 Parallel Corpus Filtering shared task. We use a slightly modified version of the Zipporah Corpus Filtering toolkit (Xu and Koehn, 2017), which computes an adequacy score and a fluency score on a sentence pair, and use a weighted sum of the scores as the selection criteria. This work differs from Zipporah in that we experiment with using the noisy corpus to be filtered to compute the combination weights, and thus avoids generating synthetic data as in standard Zipporah. |
| Tasks | Language Modelling, Machine Translation, Outlier Detection |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6479/ |
| https://www.aclweb.org/anthology/W18-6479 | |
| PWC | https://paperswithcode.com/paper/the-jhu-parallel-corpus-filtering-systems-for |
| Repo | |
| Framework | |
Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts
| Title | Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts |
| Authors | Wei Wu, Can Xu, Yu Wu, Zhoujun Li |
| Abstract | Conventional methods model open domain dialogue generation as a black box through end-to-end learning from large scale conversation data. In this work, we make the first step to open the black box by introducing dialogue acts into open domain dialogue generation. The dialogue acts are generally designed and reveal how people engage in social chat. Inspired by analysis on real data, we propose jointly modeling dialogue act selection and response generation, and perform learning with human-human conversations tagged with a dialogue act classifier and a reinforcement approach to further optimizing the model for long-term conversation. With the dialogue acts, we not only achieve significant improvement over state-of-the-art methods on response quality for given contexts and long-term conversation in both machine-machine simulation and human-machine conversation, but also are capable of explaining why such achievements can be made. |
| Tasks | Dialogue Generation |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Bym0cU1CZ |
| https://openreview.net/pdf?id=Bym0cU1CZ | |
| PWC | https://paperswithcode.com/paper/towards-interpretable-chit-chat-open-domain |
| Repo | |
| Framework | |
Building A Handwritten Cuneiform Character Imageset
| Title | Building A Handwritten Cuneiform Character Imageset |
| Authors | Kenji Yamauchi, Hajime Yamamoto, Wakaha Mori |
| Abstract | |
| Tasks | Machine Translation, Optical Character Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1115/ |
| https://www.aclweb.org/anthology/L18-1115 | |
| PWC | https://paperswithcode.com/paper/building-a-handwritten-cuneiform-character |
| Repo | |
| Framework | |
Visualization of the Topic Space of Argument Search Results in args.me
| Title | Visualization of the Topic Space of Argument Search Results in args.me |
| Authors | Yamen Ajjour, Henning Wachsmuth, Dora Kiesel, Patrick Riehmann, Fan Fan, Giuliano Castiglia, Rosemary Adejoh, Bernd Fr{"o}hlich, Benno Stein |
| Abstract | In times of fake news and alternative facts, pro and con arguments on controversial topics are of increasing importance. Recently, we presented args.me as the first search engine for arguments on the web. In its initial version, args.me ranked arguments solely by their relevance to a topic queried for, making it hard to learn about the diverse topical aspects covered by the search results. To tackle this shortcoming, we integrated a visualization interface for result exploration in args.me that provides an instant overview of the main aspects in a barycentric coordinate system. This topic space is generated ad-hoc from controversial issues on Wikipedia and argument-specific LDA models. In two case studies, we demonstrate how individual arguments can be found easily through interactions with the visualization, such as highlighting and filtering. |
| Tasks | Topic Models |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2011/ |
| https://www.aclweb.org/anthology/D18-2011 | |
| PWC | https://paperswithcode.com/paper/visualization-of-the-topic-space-of-argument |
| Repo | |
| Framework | |
An Assessment of Explicit Inter- and Intra-sentential Discourse Connectives in Turkish Discourse Bank
| Title | An Assessment of Explicit Inter- and Intra-sentential Discourse Connectives in Turkish Discourse Bank |
| Authors | Deniz Zeyrek, Murathan Kurfal{\i} |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1634/ |
| https://www.aclweb.org/anthology/L18-1634 | |
| PWC | https://paperswithcode.com/paper/an-assessment-of-explicit-inter-and-intra |
| Repo | |
| Framework | |
RF-based 3D skeletons
| Title | RF-based 3D skeletons |
| Authors | Mingmin Zhao, Yonglong Tian, Hang Zhao, Mohammad Abu Alsheikh, Tianhong Li, Rumen Hristov, Zachary Kabelac, Dina Katabi, Antonio Torralba |
| Abstract | This paper introduces RF-Pose3D, the first system that infers 3D human skeletons from RF signals. It requires no sensors on the body, and works with multiple people and across walls and occlusions. Further, it generates dynamic skeletons that follow the people as they move, walk or sit. As such, RF-Pose3D provides a significant leap in RF-based sensing and enables new applications in gaming, healthcare, and smart homes. RF-Pose3D is based on a novel convolutional neural network (CNN) architecture that performs high-dimensional convolutions by decomposing them into low-dimensional operations. This property allows the network to efficiently condense the spatio-temporal information in RF signals. The network first zooms in on the individuals in the scene, and crops the RF signals reflected off each person. For each individual, it localizes and tracks their body parts - head, shoulders, arms, wrists, hip, knees, and feet. Our evaluation results show that RF-Pose3D tracks each keypoint on the human body with an average error of 4.2 cm, 4.0 cm, and 4.9 cm along the X, Y, and Z axes respectively. It maintains this accuracy even in the presence of multiple people, and in new environments that it has not seen in the training set. Demo videos are available at our website: http://rfpose3d.csail.mit.edu. |
| Tasks | RF-based Pose Estimation |
| Published | 2018-08-20 |
| URL | https://doi.org/10.1145/3230543.3230579 |
| https://people.csail.mit.edu/mingmin/papers/rfpose3d-sigcomm-zhao.pdf | |
| PWC | https://paperswithcode.com/paper/rf-based-3d-skeletons |
| Repo | |
| Framework | |
ES-Port: a Spontaneous Spoken Human-Human Technical Support Corpus for Dialogue Research in Spanish
| Title | ES-Port: a Spontaneous Spoken Human-Human Technical Support Corpus for Dialogue Research in Spanish |
| Authors | Laura Garc{'\i}a-Sardi{~n}a, Manex Serras, Arantza del Pozo |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1125/ |
| https://www.aclweb.org/anthology/L18-1125 | |
| PWC | https://paperswithcode.com/paper/es-port-a-spontaneous-spoken-human-human |
| Repo | |
| Framework | |
Zero watermarking scheme for citygml
| Title | Zero watermarking scheme for citygml |
| Authors | Dayou, Jiang; Jongweon, Kim |
| Abstract | City Geography Markup Language (CityGML) is developed as an open data model, which is based on the XML format for the storage and exchange of virtual 3D city models. CityGML defines the basic entities, attributes, and relations of a 3D city model. With respect to the cost-effective sustainable maintenance of 3D city models, it allows the reuse of the same data in different application fields. However, the copyright protection in suchlike virtual 3D city filed is not popular. Therefore, we present a zero watermarking scheme based on the global geometry property of the point cloud for CityGML. Firstly, the paper analyzes the data structure of CityGML and discusses the feasibility data for the watermark. Secondly, extracts the point and topology information from CityGML. Finally, generates the zero-watermarking by using the global geometry property from vertex norm. We conduct several experiments on CityGML models with translation, rotation, uniform scaling, vertex re-ordering, simplification, smoothing, and noise attacks. Experiments show the scheme can satisfy the requests for copyright protection of CityGML models. |
| Tasks | |
| Published | 2018-10-30 |
| URL | https://www.researchgate.net/publication/329573435_Zero_watermarking_scheme_for_citygml |
| http://www.jatit.org/volumes/Vol96No22/13Vol96No22.pdf | |
| PWC | https://paperswithcode.com/paper/zero-watermarking-scheme-for-citygml |
| Repo | |
| Framework | |
Measuring sentence parallelism using Mahalanobis distances: The NRC unsupervised submissions to the WMT18 Parallel Corpus Filtering shared task
| Title | Measuring sentence parallelism using Mahalanobis distances: The NRC unsupervised submissions to the WMT18 Parallel Corpus Filtering shared task |
| Authors | Patrick Littell, Samuel Larkin, Darlene Stewart, Michel Simard, Cyril Goutte, Chi-kiu Lo |
| Abstract | The WMT18 shared task on parallel corpus filtering (Koehn et al., 2018b) challenged teams to score sentence pairs from a large high-recall, low-precision web-scraped parallel corpus (Koehn et al., 2018a). Participants could use existing sample corpora (e.g. past WMT data) as a supervisory signal to learn what a {``}clean{''} corpus looks like. However, in lower-resource situations it often happens that the target corpus of the language is the \textit{only} sample of parallel text in that language. We therefore made several unsupervised entries, setting ourselves an additional constraint that we not utilize the additional clean parallel corpora. One such entry fairly consistently scored in the top ten systems in the 100M-word conditions, and for one task{—}translating the European Medicines Agency corpus (Tiedemann, 2009){—}scored among the best systems even in the 10M-word conditions. | |
| Tasks | Anomaly Detection, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6480/ |
| https://www.aclweb.org/anthology/W18-6480 | |
| PWC | https://paperswithcode.com/paper/measuring-sentence-parallelism-using |
| Repo | |
| Framework | |
Automatically Linking Lexical Resources with Word Sense Embedding Models
| Title | Automatically Linking Lexical Resources with Word Sense Embedding Models |
| Authors | Luis Nieto-Pi{~n}a, Richard Johansson |
| Abstract | Automatically learnt word sense embeddings are developed as an attempt to refine the capabilities of coarse word embeddings. The word sense representations obtained this way are, however, sensitive to underlying corpora and parameterizations, and they might be difficult to relate to formally defined word senses. We propose to tackle this problem by devising a mechanism to establish links between word sense embeddings and lexical resources created by experts. We evaluate the applicability of these links in a task to retrieve instances of word sense unlisted in the lexicon. |
| Tasks | Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4003/ |
| https://www.aclweb.org/anthology/W18-4003 | |
| PWC | https://paperswithcode.com/paper/automatically-linking-lexical-resources-with |
| Repo | |
| Framework | |
Batch IS NOT Heavy: Learning Word Representations From All Samples
| Title | Batch IS NOT Heavy: Learning Word Representations From All Samples |
| Authors | Xin Xin, Fajie Yuan, Xiangnan He, Joemon M. Jose |
| Abstract | Stochastic Gradient Descent (SGD) with negative sampling is the most prevalent approach to learn word representations. However, it is known that sampling methods are biased especially when the sampling distribution deviates from the true data distribution. Besides, SGD suffers from dramatic fluctuation due to the one-sample learning scheme. In this work, we propose AllVec that uses batch gradient learning to generate word representations from all training samples. Remarkably, the time complexity of AllVec remains at the same level as SGD, being determined by the number of positive samples rather than all samples. We evaluate AllVec on several benchmark tasks. Experiments show that AllVec outperforms sampling-based SGD methods with comparable efficiency, especially for small training corpora. |
| Tasks | Document Classification, Named Entity Recognition, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1172/ |
| https://www.aclweb.org/anthology/P18-1172 | |
| PWC | https://paperswithcode.com/paper/batch-is-not-heavy-learning-word |
| Repo | |
| Framework | |
Joint Map and Symmetry Synchronization
| Title | Joint Map and Symmetry Synchronization |
| Authors | Yifan Sun, Zhenxiao Liang, Xiangru Huang, Qixing Huang |
| Abstract | Most existing techniques in map computation (e.g., in the form of feature or dense correspondences) assume that the underlying map between an object pair is unique. This assumption, however, easily breaks when visual objects possess self-symmetries. In this paper, we study the problem of jointly optimizing self-symmetries and pair-wise maps among a collection of similar objects. We introduce a lifting map representation for encoding both symmetry groups and maps between symmetry groups. Based on this representation, we introduce a reweighted non-linear least square framework for joint symmetry and map synchronization. Experimental results show that this approach outperforms state-of-the-art methods for self-symmetry group extraction from a single object as well as joint map optimization among a object collection. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Qixing_Huang_Joint_Map_and_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Qixing_Huang_Joint_Map_and_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/joint-map-and-symmetry-synchronization |
| Repo | |
| Framework | |
Undersampling Improves Hypernymy Prototypicality Learning
| Title | Undersampling Improves Hypernymy Prototypicality Learning |
| Authors | Koki Washio, Tsuneaki Kato |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1720/ |
| https://www.aclweb.org/anthology/L18-1720 | |
| PWC | https://paperswithcode.com/paper/undersampling-improves-hypernymy |
| Repo | |
| Framework | |
Acquiring Verb Classes Through Bottom-Up Semantic Verb Clustering
| Title | Acquiring Verb Classes Through Bottom-Up Semantic Verb Clustering |
| Authors | Olga Majewska, Diana McCarthy, Ivan Vuli{'c}, Anna Korhonen |
| Abstract | |
| Tasks | Semantic Textual Similarity |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1153/ |
| https://www.aclweb.org/anthology/L18-1153 | |
| PWC | https://paperswithcode.com/paper/acquiring-verb-classes-through-bottom-up |
| Repo | |
| Framework | |
