Paper Group NANR 12
Cliticization of Serbian Personal Pronouns and Auxiliary Verbs. A Dependency-Based Account. MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition. Permanent Magnetic Articulograph (PMA) vs Electromagnetic Articulograph (EMA) in Articulation-to-Speech Synthesis for Silent Speech Interface. Improving Event Co …
Cliticization of Serbian Personal Pronouns and Auxiliary Verbs. A Dependency-Based Account
| Title | Cliticization of Serbian Personal Pronouns and Auxiliary Verbs. A Dependency-Based Account |
| Authors | Jasmina Milicevic |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7708/ |
| https://www.aclweb.org/anthology/W19-7708 | |
| PWC | https://paperswithcode.com/paper/cliticization-of-serbian-personal-pronouns |
| Repo | |
| Framework | |
MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition
| Title | MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition |
| Authors | Weihe Zhang, Yali Wang, Yu Qiao |
| Abstract | Deep Neural Networks (DNNs) have achieved remarkable successes in large-scale visual recognition. However, they often suffer from overfitting under noisy labels. To alleviate this problem, we propose a conceptually simple but effective MetaCleaner, which can learn to hallucinate a clean representation of an object category, according to a small noisy subset from the same category. Specially, MetaCleaner consists of two flexible submodules. The first submodule, namely Noisy Weighting, can estimate the confidence scores of all the images in the noisy subset, by analyzing their deep features jointly. The second submodule, namely Clean Hallucinating, can generate a clean representation from the noisy subset, by summarizing the noisy images with their confidence scores. Via MetaCleaner, DNNs can strengthen its robustness to noisy labels, as well as enhance its generalization capacity with richer data diversity. Moreover, MetaCleaner can be easily integrated into the standard training procedure of DNNs, which promotes its value for real-life applications. We conduct extensive experiments on two popular benchmarks in noisy-labeled recognition, i.e., Food-101N and Clothing1M. For both datasets, our MetaCleaner significantly outperforms baselines, and achieves the state-of-the-art performance. |
| Tasks | Object Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_MetaCleaner_Learning_to_Hallucinate_Clean_Representations_for_Noisy-Labeled_Visual_Recognition_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_MetaCleaner_Learning_to_Hallucinate_Clean_Representations_for_Noisy-Labeled_Visual_Recognition_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/metacleaner-learning-to-hallucinate-clean |
| Repo | |
| Framework | |
Permanent Magnetic Articulograph (PMA) vs Electromagnetic Articulograph (EMA) in Articulation-to-Speech Synthesis for Silent Speech Interface
| Title | Permanent Magnetic Articulograph (PMA) vs Electromagnetic Articulograph (EMA) in Articulation-to-Speech Synthesis for Silent Speech Interface |
| Authors | Beiming Cao, Nordine Sebkhi, Ted Mau, Omer T. Inan, Jun Wang |
| Abstract | Silent speech interfaces (SSIs) are devices that enable speech communication when audible speech is unavailable. Articulation-to-speech (ATS) synthesis is a software design in SSI that directly converts articulatory movement information into audible speech signals. Permanent magnetic articulograph (PMA) is a wireless articulator motion tracking technology that is similar to commercial, wired Electromagnetic Articulograph (EMA). PMA has shown great potential for practical SSI applications, because it is wireless. The ATS performance of PMA, however, is unknown when compared with current EMA. In this study, we compared the performance of ATS using a PMA we recently developed and a commercially available EMA (NDI Wave system). Datasets with same stimuli and size that were collected from tongue tip were used in the comparison. The experimental results indicated the performance of PMA was close to, although not as equally good as that of EMA. Furthermore, in PMA, converting the raw magnetic signals to positional signals did not significantly affect the performance of ATS, which support the future direction in PMA-based ATS can be focused on the use of positional signals to maximize the benefit of spatial analysis. |
| Tasks | Speech Synthesis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1703/ |
| https://www.aclweb.org/anthology/W19-1703 | |
| PWC | https://paperswithcode.com/paper/permanent-magnetic-articulograph-pma-vs |
| Repo | |
| Framework | |
Improving Event Coreference Resolution by Learning Argument Compatibility from Unlabeled Data
| Title | Improving Event Coreference Resolution by Learning Argument Compatibility from Unlabeled Data |
| Authors | Yin Jou Huang, Jing Lu, Sadao Kurohashi, Vincent Ng |
| Abstract | Argument compatibility is a linguistic condition that is frequently incorporated into modern event coreference resolution systems. If two event mentions have incompatible arguments in any of the argument roles, they cannot be coreferent. On the other hand, if these mentions have compatible arguments, then this may be used as information towards deciding their coreferent status. One of the key challenges in leveraging argument compatibility lies in the paucity of labeled data. In this work, we propose a transfer learning framework for event coreference resolution that utilizes a large amount of unlabeled data to learn argument compatibility of event mentions. In addition, we adopt an interactive inference network based model to better capture the compatible and incompatible relations between the context words of event mentions. Our experiments on the KBP 2017 English dataset confirm the effectiveness of our model in learning argument compatibility, which in turn improves the performance of the overall event coreference model. |
| Tasks | Coreference Resolution, Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1085/ |
| https://www.aclweb.org/anthology/N19-1085 | |
| PWC | https://paperswithcode.com/paper/improving-event-coreference-resolution-by-2 |
| Repo | |
| Framework | |
Hear about Verbal Multiword Expressions in the Bulgarian and the Romanian Wordnets Straight from the Horse’s Mouth
| Title | Hear about Verbal Multiword Expressions in the Bulgarian and the Romanian Wordnets Straight from the Horse’s Mouth |
| Authors | Verginica Barbu Mititelu, Ivelina Stoyanova, Svetlozara Leseva, Maria Mitrofan, Tsvetana Dimitrova, Maria Todorova |
| Abstract | In this paper we focus on verbal multiword expressions (VMWEs) in Bulgarian and Romanian as reflected in the wordnets of the two languages. The annotation of VMWEs relies on the classification defined within the PARSEME Cost Action. After outlining the properties of various types of VMWEs, a cross-language comparison is drawn, aimed to highlight the similarities and the differences between Bulgarian and Romanian with respect to the lexicalization and distribution of VMWEs. The contribution of this work is in outlining essential features of the description and classification of VMWEs and the cross-language comparison at the lexical level, which is essential for the understanding of the need for uniform annotation guidelines and a viable procedure for validation of the annotation. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5102/ |
| https://www.aclweb.org/anthology/W19-5102 | |
| PWC | https://paperswithcode.com/paper/hear-about-verbal-multiword-expressions-in |
| Repo | |
| Framework | |
How Bad are PoS Tagger in Cross-Corpora Settings? Evaluating Annotation Divergence in the UD Project.
| Title | How Bad are PoS Tagger in Cross-Corpora Settings? Evaluating Annotation Divergence in the UD Project. |
| Authors | Guillaume Wisniewski, Fran{\c{c}}ois Yvon |
| Abstract | The performance of Part-of-Speech tagging varies significantly across the treebanks of the Universal Dependencies project. This work points out that these variations may result from divergences between the annotation of train and test sets. We show how the annotation variation principle, introduced by Dickinson and Meurers (2003) to automatically detect errors in gold standard, can be used to identify inconsistencies between annotations; we also evaluate their impact on prediction performance. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1019/ |
| https://www.aclweb.org/anthology/N19-1019 | |
| PWC | https://paperswithcode.com/paper/how-bad-are-pos-tagger-in-cross-corpora |
| Repo | |
| Framework | |
Shrinking Japanese Morphological Analyzers With Neural Networks and Semi-supervised Learning
| Title | Shrinking Japanese Morphological Analyzers With Neural Networks and Semi-supervised Learning |
| Authors | Arseny Tolmachev, Daisuke Kawahara, Sadao Kurohashi |
| Abstract | For languages without natural word boundaries, like Japanese and Chinese, word segmentation is a prerequisite for downstream analysis. For Japanese, segmentation is often done jointly with part of speech tagging, and this process is usually referred to as morphological analysis. Morphological analyzers are trained on data hand-annotated with segmentation boundaries and part of speech tags. A segmentation dictionary or character n-gram information is also provided as additional inputs to the model. Incorporating this extra information makes models large. Modern neural morphological analyzers can consume gigabytes of memory. We propose a compact alternative to these cumbersome approaches which do not rely on any externally provided n-gram or word representations. The model uses only unigram character embeddings, encodes them using either stacked bi-LSTM or a self-attention network, and independently infers both segmentation and part of speech information. The model is trained in an end-to-end and semi-supervised fashion, on labels produced by a state-of-the-art analyzer. We demonstrate that the proposed technique rivals performance of a previous dictionary-based state-of-the-art approach and can even surpass it when training with the combination of human-annotated and automatically-annotated data. Our model itself is significantly smaller than the dictionary-based one: it uses less than 15 megabytes of space. |
| Tasks | Chinese Word Segmentation, Morphological Analysis, Part-Of-Speech Tagging |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1281/ |
| https://www.aclweb.org/anthology/N19-1281 | |
| PWC | https://paperswithcode.com/paper/shrinking-japanese-morphological-analyzers |
| Repo | |
| Framework | |
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials
| Title | Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-5000/ |
| https://www.aclweb.org/anthology/N19-5000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2019-conference-of-the-4 |
| Repo | |
| Framework | |
Enabling Noninvasive Physical Assault Monitoring in Smart School with Commercial Wi-Fi Devices
| Title | Enabling Noninvasive Physical Assault Monitoring in Smart School with Commercial Wi-Fi Devices |
| Authors | Qizhen Zhou, Chenshu Wu, Jianchun Xing, Shuo Zhao, and Qiliang Yang |
| Abstract | Monitoring physical assault is critical for the prevention of juvenile delinquency and promotion of school harmony. A large portion of assault events, particularly school violence among teenagers, usually happen at indoor secluded places. Pioneering approaches employ always-on-body sensors or cameras in the limited surveillance area, which are privacy-invasive and cannot provide ubiquitous assault monitoring. In this paper, we present Wi-Dog, a noninvasive physical assault monitoring scheme that enables privacy-preserving monitoring in ubiquitous circumstances. Wi-Dog is based on widely deployed commodity Wi-Fi infrastructures. The key intuition is that Wi-Fi signals are easily distorted by human motions, and motion-induced signals could convey informative characteristics, such as intensity, regularity, and continuity. Specifically, to explicitly reveal the substantive properties of physical assault, we innovatively propose a set of signal processing methods for informative components extraction by selecting sensitive antenna pairs and subcarriers. Then a novel signal-complexity-based segmentation method is developed as a location-independent indicator to monitor targeted movement transitions. Finally, holistic analysis is employed based on domain knowledge, and we distinguish the violence process from both local and global perspective using time-frequency features. We implement Wi-Dog on commercial Wi-Fi devices and evaluate it in real indoor environments. Experimental results demonstrate the effectiveness of Wi-Dog which consistently outperforms the advanced abnormal detection methods with a higher true detection rate of 94% and a lower false alarm rate of 8%. |
| Tasks | RF-based Action Recognition, RF-based Pose Estimation |
| Published | 2019-04-01 |
| URL | https://doi.org/10.1155/2019/8186573 |
| http://downloads.hindawi.com/journals/wcmc/2019/8186573.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-noninvasive-physical-assault |
| Repo | |
| Framework | |
eTranslation’s Submissions to the WMT 2019 News Translation Task
| Title | eTranslation’s Submissions to the WMT 2019 News Translation Task |
| Authors | Csaba Oravecz, Katina Bontcheva, Adrien Lardilleux, L{'a}szl{'o} Tihanyi, Andreas Eisele |
| Abstract | This paper describes the submissions of the eTranslation team to the WMT 2019 news translation shared task. The systems have been developed with the aim of identifying and following rather than establishing best practices, under the constraints imposed by a low resource training and decoding environment normally used for our production systems. Thus most of the findings and results are transferable to systems used in the eTranslation service. Evaluations suggest that this approach is able to produce decent models with good performance and speed without the overhead of using prohibitively deep and complex architectures. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5334/ |
| https://www.aclweb.org/anthology/W19-5334 | |
| PWC | https://paperswithcode.com/paper/etranslations-submissions-to-the-wmt-2019 |
| Repo | |
| Framework | |
Neural Lexicons for Slot Tagging in Spoken Language Understanding
| Title | Neural Lexicons for Slot Tagging in Spoken Language Understanding |
| Authors | Kyle Williams |
| Abstract | We explore the use of lexicons or gazettes in neural models for slot tagging in spoken language understanding. We develop models that encode lexicon information as neural features for use in a Long-short term memory neural network. Experiments are performed on data from 4 domains from an intelligent assistant under conditions that often occur in an industry setting, where there may be: 1) large amounts of training data, 2) limited amounts of training data for new domains, and 3) cross domain training. Results show that the use of neural lexicon information leads to a significant improvement in slot tagging, with improvements in the F-score of up to 12{%}. Our findings have implications for how lexicons can be used to improve the performance of neural slot tagging models. |
| Tasks | Spoken Language Understanding |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2011/ |
| https://www.aclweb.org/anthology/N19-2011 | |
| PWC | https://paperswithcode.com/paper/neural-lexicons-for-slot-tagging-in-spoken |
| Repo | |
| Framework | |
Convolutional Subspace Clustering Network with Block Diagonal Prior
| Title | Convolutional Subspace Clustering Network with Block Diagonal Prior |
| Authors | Junjian Zhang, Chun-Guang Li, Tianming Du, Honggang Zhang, Jun Guo |
| Abstract | Standard methods of subspace clustering are based on self-expressiveness in the original data space, which states that a data point in a subspace can be expressed as a linear combination of other points. However, the real data in raw form are usually not well aligned with the linear subspace model. Therefore, it is crucial to obtain a proper feature space for performing high quality subspace clustering. Inspired by the success of Convolutional Neural Networks (CNN) for extraction powerful features from visual data and the block diagonal prior for learning a good affinity matrix from self-expression coefficients, in this paper, we propose a jointly trainable feature extraction and affinity learning framework with the block diagonal prior, termed as Convolutional Subspace Clustering Network with Block Diagonal prior (ConvSCN-BD), in which we solve the joint optimization problem in ConvSCN-BD via an alternating minimization algorithm, which updates the parameters in the convolutional modules and the self-expression coefficients with stochastic gradients descent and updates other variables with close-form solutions alternatingly. In addition, we derive the connection between the block diagonal prior and the subspace structured norm, and reveal that using the block diagonal prior on the affinity matrix is essentially incorporating the feedback information from spectral clustering. Experiments on three benchmark datasets demonstrated the effectiveness of our proposal. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://ieeexplore.ieee.org/document/8946632 |
| https://ieeexplore.ieee.org/document/8946632 | |
| PWC | https://paperswithcode.com/paper/convolutional-subspace-clustering-network |
| Repo | |
| Framework | |
On a Chatbot Providing Virtual Dialogues
| Title | On a Chatbot Providing Virtual Dialogues |
| Authors | Boris Galitsky, Dmitry Ilvovsky, Elizaveta Goncharova |
| Abstract | We present a chatbot that delivers content in the form of virtual dialogues automatically produced from the plain texts that are extracted and selected from the documents. This virtual dialogue content is provided in the form of answers derived from the found and selected documents split into fragments, and questions that are automatically generated for these answers based on the initial text. |
| Tasks | Chatbot |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1045/ |
| https://www.aclweb.org/anthology/R19-1045 | |
| PWC | https://paperswithcode.com/paper/on-a-chatbot-providing-virtual-dialogues |
| Repo | |
| Framework | |
Semi-Supervised Pedestrian Instance Synthesis and Detection With Mutual Reinforcement
| Title | Semi-Supervised Pedestrian Instance Synthesis and Detection With Mutual Reinforcement |
| Authors | Si Wu, Sihao Lin, Wenhao Wu, Mohamed Azzam, Hau-San Wong |
| Abstract | We propose a GAN-based scene-specific instance synthesis and classification model for semi-supervised pedestrian detection. Instead of collecting unreliable detections from unlabeled data, we adopt a class-conditional GAN for synthesizing pedestrian instances to alleviate the problem of insufficient labeled data. With the help of a base detector, we integrate pedestrian instance synthesis and detection by including a post-refinement classifier (PRC) into a minimax game. A generator and the PRC can mutually reinforce each other by synthesizing high-fidelity pedestrian instances and providing more accurate categorical information. Both of them compete with a class-conditional discriminator and a class-specific discriminator, such that the four fundamental networks in our model can be jointly trained. In our experiments, we validate that the proposed model significantly improves the performance of the base detector and achieves state-of-the-art results on multiple benchmarks. As shown in Figure 1, the result indicates the possibility of using inexpensively synthesized instances for improving semi-supervised detection models. |
| Tasks | Pedestrian Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Semi-Supervised_Pedestrian_Instance_Synthesis_and_Detection_With_Mutual_Reinforcement_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wu_Semi-Supervised_Pedestrian_Instance_Synthesis_and_Detection_With_Mutual_Reinforcement_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-pedestrian-instance-synthesis |
| Repo | |
| Framework | |
Winter is here: Summarizing Twitter Streams related to Pre-Scheduled Events
| Title | Winter is here: Summarizing Twitter Streams related to Pre-Scheduled Events |
| Authors | Anietie Andy, Derry Tanti Wijaya, Chris Callison-Burch |
| Abstract | Pre-scheduled events, such as TV shows and sports games, usually garner considerable attention from the public. Twitter captures large volumes of discussions and messages related to these events, in real-time. Twitter streams related to pre-scheduled events are characterized by the following: (1) spikes in the volume of published tweets reflect the highlights of the event and (2) some of the published tweets make reference to the characters involved in the event, in the context in which they are currently portrayed in a subevent. In this paper, we take advantage of these characteristics to identify the highlights of pre-scheduled events from tweet streams and we demonstrate a method to summarize these highlights. We evaluate our algorithm on tweets collected around 2 episodes of a popular TV show, Game of Thrones, Season 7. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3412/ |
| https://www.aclweb.org/anthology/W19-3412 | |
| PWC | https://paperswithcode.com/paper/winter-is-here-summarizing-twitter-streams |
| Repo | |
| Framework | |
