Paper Group NANR 99
Psychophysical vs. learnt texture representations in novelty detection. Unsupervised Morphological Segmentation for Low-Resource Polysynthetic Languages. NICT’s Supervised Neural Machine Translation Systems for the WMT19 Translation Robustness Task. Efficient learning of Output Tier-based Strictly 2-Local functions. Relation Parsing Neural Network …
Psychophysical vs. learnt texture representations in novelty detection
| Title | Psychophysical vs. learnt texture representations in novelty detection |
| Authors | Michael Grunwald, Matthias Hermann, Fabian Freiberg, Matthias O. Franz |
| Abstract | Parametric texture models have been applied successfully to synthesize artificial images. Psychophysical studies show that under defined conditions observers are unable to differentiate between model-generated and original natural textures. In industrial applications the reverse case is of interest: a texture analysis system should decide if human observers are able to discriminate between a reference and a novel texture. For example, in case of inspecting decorative surfaces the de- tection of visible texture anomalies without any prior knowledge is required. Here, we implemented a human-vision-inspired novelty detection approach. Assuming that the features used for texture synthesis are important for human texture percep- tion, we compare psychophysical as well as learnt texture representations based on activations of a pretrained CNN in a novelty detection scenario. Additionally, we introduce a novel objective function to train one-class neural networks for novelty detection and compare the results to standard one-class SVM approaches. Our experiments clearly show the differences between human-vision-inspired texture representations and learnt features in detecting visual anomalies. Based on a dig- ital print inspection scenario we show that psychophysical texture representations are able to outperform CNN-encoded features. |
| Tasks | Texture Classification, Texture Synthesis |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJEOOsCqKm |
| https://openreview.net/pdf?id=BJEOOsCqKm | |
| PWC | https://paperswithcode.com/paper/psychophysical-vs-learnt-texture |
| Repo | |
| Framework | |
Unsupervised Morphological Segmentation for Low-Resource Polysynthetic Languages
| Title | Unsupervised Morphological Segmentation for Low-Resource Polysynthetic Languages |
| Authors | Esk, Ramy er, Judith Klavans, Smar Muresan, a |
| Abstract | Polysynthetic languages pose a challenge for morphological analysis due to the root-morpheme complexity and to the word class {``}squish{''}. In addition, many of these polysynthetic languages are low-resource. We propose unsupervised approaches for morphological segmentation of low-resource polysynthetic languages based on Adaptor Grammars (AG) (Eskander et al., 2016). We experiment with four languages from the Uto-Aztecan family. Our AG-based approaches outperform other unsupervised approaches and show promise when compared to supervised methods, outperforming them on two of the four languages. | |
| Tasks | Morphological Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4222/ |
| https://www.aclweb.org/anthology/W19-4222 | |
| PWC | https://paperswithcode.com/paper/unsupervised-morphological-segmentation-for |
| Repo | |
| Framework | |
NICT’s Supervised Neural Machine Translation Systems for the WMT19 Translation Robustness Task
| Title | NICT’s Supervised Neural Machine Translation Systems for the WMT19 Translation Robustness Task |
| Authors | Raj Dabre, Eiichiro Sumita |
| Abstract | In this paper we describe our neural machine translation (NMT) systems for Japanese↔English translation which we submitted to the translation robustness task. We focused on leveraging transfer learning via fine tuning to improve translation quality. We used a fairly well established domain adaptation technique called Mixed Fine Tuning (MFT) (Chu et. al., 2017) to improve translation quality for Japanese↔English. We also trained bi-directional NMT models instead of uni-directional ones as the former are known to be quite robust, especially in low-resource scenarios. However, given the noisy nature of the in-domain training data, the improvements we obtained are rather modest. |
| Tasks | Domain Adaptation, Machine Translation, Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5362/ |
| https://www.aclweb.org/anthology/W19-5362 | |
| PWC | https://paperswithcode.com/paper/nicts-supervised-neural-machine-translation-1 |
| Repo | |
| Framework | |
Efficient learning of Output Tier-based Strictly 2-Local functions
| Title | Efficient learning of Output Tier-based Strictly 2-Local functions |
| Authors | Phillip Burness, Kevin McMullin |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5707/ |
| https://www.aclweb.org/anthology/W19-5707 | |
| PWC | https://paperswithcode.com/paper/efficient-learning-of-output-tier-based |
| Repo | |
| Framework | |
Relation Parsing Neural Network for Human-Object Interaction Detection
| Title | Relation Parsing Neural Network for Human-Object Interaction Detection |
| Authors | Penghao Zhou, Mingmin Chi |
| Abstract | Human-Object Interaction Detection devotes to infer a triplet < human, verb, object > between human and objects. In this paper, we propose a novel model, i.e., Relation Parsing Neural Network (RPNN), to detect human-object interactions. Specifically, the network is represented by two graphs, i.e., Object-Bodypart Graph and Human-Bodypart Graph. Here, the Object-Bodypart Graph dynamically captures the relationship between body parts and the surrounding objects. The Human-Bodypart Graph infers the relationship between human and body parts, and assembles body part contexts to predict actions. These two graphs are associated through an action passing mechanism. The proposed RPNN model is able to implicitly parse a pairwise relation in two graphs without supervised labels. Experiments conducted on V-COCO and HICO-DET datasets confirm the effectiveness of the proposed RPNN network which significantly outperforms state-of-the-art methods. |
| Tasks | Human-Object Interaction Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhou_Relation_Parsing_Neural_Network_for_Human-Object_Interaction_Detection_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_Relation_Parsing_Neural_Network_for_Human-Object_Interaction_Detection_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/relation-parsing-neural-network-for-human |
| Repo | |
| Framework | |
Finance document Extraction Using Data Augmentation and Attention
| Title | Finance document Extraction Using Data Augmentation and Attention |
| Authors | Ke Tian, Zi Jun Peng |
| Abstract | |
| Tasks | Data Augmentation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6401/ |
| https://www.aclweb.org/anthology/W19-6401 | |
| PWC | https://paperswithcode.com/paper/finance-document-extraction-using-data |
| Repo | |
| Framework | |
Modelling the interplay of metaphor and emotion through multitask learning
| Title | Modelling the interplay of metaphor and emotion through multitask learning |
| Authors | Verna Dankers, Marek Rei, Martha Lewis, Ekaterina Shutova |
| Abstract | Metaphors allow us to convey emotion by connecting physical experiences and abstract concepts. The results of previous research in linguistics and psychology suggest that metaphorical phrases tend to be more emotionally evocative than their literal counterparts. In this paper, we investigate the relationship between metaphor and emotion within a computational framework, by proposing the first joint model of these phenomena. We experiment with several multitask learning architectures for this purpose, involving both hard and soft parameter sharing. Our results demonstrate that metaphor identification and emotion prediction mutually benefit from joint learning and our models advance the state of the art in both of these tasks. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1227/ |
| https://www.aclweb.org/anthology/D19-1227 | |
| PWC | https://paperswithcode.com/paper/modelling-the-interplay-of-metaphor-and |
| Repo | |
| Framework | |
Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition
| Title | Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition |
| Authors | Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Meng Fang, Rick Siow Mong Goh, Kenneth Kwok |
| Abstract | We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER). Specifically, two variants of DATNet, i.e., DATNet-F and DATNet-P, are investigated to explore effective feature fusion between high and low resource. To address the noisy and imbalanced training data, we propose a novel Generalized Resource-Adversarial Discriminator (GRAD). Additionally, adversarial training is adopted to boost model generalization. In experiments, we examine the effects of different components in DATNet across domains and languages and show that significant improvement can be obtained especially for low-resource data, without augmenting any additional hand-crafted features and pre-trained language model. |
| Tasks | Language Modelling, Named Entity Recognition |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1336/ |
| https://www.aclweb.org/anthology/P19-1336 | |
| PWC | https://paperswithcode.com/paper/dual-adversarial-neural-transfer-for-low |
| Repo | |
| Framework | |
Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts
| Title | Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts |
| Authors | Jue Wang, Shaoli Huang, Xinchao Wang, Dacheng Tao |
| Abstract | Not all the human body parts have the same degree of freedom (DOF) due to the physiological structure. For example, the limbs may move more flexibly and freely than the torso does. Most of the existing 3D pose estimation methods, despite the very promising results achieved, treat the body joints equally and consequently often lead to larger reconstruction errors on the limbs. In this paper, we propose a progressive approach that explicitly accounts for the distinct DOFs among the body parts. We model parts with higher DOFs like the elbows, as dependent components of the corresponding parts with lower DOFs like the torso, of which the 3D locations can be more reliably estimated. Meanwhile, the high-DOF parts may, in turn, impose a constraint on where the low-DOF ones lie. As a result, parts with different DOFs supervise one another, yielding physically constrained and plausible pose-estimation results. To further facilitate the prediction of the high-DOF parts, we introduce a pose-attribution estimation, where the relative location of a limb joint with respect to the torso, which has the least DOF of a human body, is explicitly estimated and further fed to the joint-estimation module. The proposed approach achieves very promising results, outperforming the state of the art on several benchmarks. |
| Tasks | 3D Pose Estimation, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Not_All_Parts_Are_Created_Equal_3D_Pose_Estimation_by_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Not_All_Parts_Are_Created_Equal_3D_Pose_Estimation_by_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/not-all-parts-are-created-equal-3d-pose-1 |
| Repo | |
| Framework | |
JHU 2019 Robustness Task System Description
| Title | JHU 2019 Robustness Task System Description |
| Authors | Matt Post, Kevin Duh |
| Abstract | We describe the JHU submissions to the French{–}English, Japanese{–}English, and English{–}Japanese Robustness Task at WMT 2019. Our goal was to evaluate the performance of baseline systems on both the official noisy test set as well as news data, in order to ensure that performance gains in the latter did not come at the expense of general-domain performance. To this end, we built straightforward 6-layer Transformer models and experimented with a handful of variables including subword processing (FR→EN) and a handful of hyperparameters settings (JA↔EN). As expected, our systems performed reasonably. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5366/ |
| https://www.aclweb.org/anthology/W19-5366 | |
| PWC | https://paperswithcode.com/paper/jhu-2019-robustness-task-system-description |
| Repo | |
| Framework | |
Neural MMO: A massively multiplayer game environment for intelligent agents
| Title | Neural MMO: A massively multiplayer game environment for intelligent agents |
| Authors | Joseph Suarez, Yilun Du, Phillip Isola, Igor Mordatch |
| Abstract | We present an artificial intelligence research platform inspired by the human game genre of MMORPGs (Massively Multiplayer Online Role-Playing Games, a.k.a. MMOs). We demonstrate how this platform can be used to study behavior and learning in large populations of neural agents. Unlike currently popular game environments, our platform supports persistent environments, with variable number of agents, and open-ended task descriptions. The emergence of complex life on Earth is often attributed to the arms race that ensued from a huge number of organisms all competing for finite resources. Our platform aims to simulate this setting in microcosm: we conduct a series of experiments to test how large-scale multiagent competition can incentivize the development of skillful behavior. We find that population size magnifies the complexity of the behaviors that emerge and results in agents that out-compete agents trained in smaller populations. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1gWz2CcKX |
| https://openreview.net/pdf?id=S1gWz2CcKX | |
| PWC | https://paperswithcode.com/paper/neural-mmo-a-massively-multiplayer-game |
| Repo | |
| Framework | |
At the Lower End of Language—Exploring the Vulgar and Obscene Side of German
| Title | At the Lower End of Language—Exploring the Vulgar and Obscene Side of German |
| Authors | Elisabeth Eder, Ulrike Krieg-Holz, Udo Hahn |
| Abstract | In this paper, we describe a workflow for the data-driven acquisition and semantic scaling of a lexicon that covers lexical items from the lower end of the German language register{—}terms typically considered as rough, vulgar or obscene. Since the fine semantic representation of grades of obscenity can only inadequately be captured at the categorical level (e.g., obscene vs. non-obscene, or rough vs. vulgar), our main contribution lies in applying best-worst scaling, a rating methodology that has already been shown to be useful for emotional language, to capture the relative strength of obscenity of lexical items. We describe the empirical foundations for bootstrapping such a low-end lexicon for German by starting from manually supplied lexicographic categorizations of a small seed set of rough and vulgar lexical items and automatically enlarging this set by means of distributional semantics. We then determine the degrees of obscenity for the full set of all acquired lexical items by letting crowdworkers comparatively assess their pejorative grade using best-worst scaling. This semi-automatically enriched lexicon already comprises 3,300 lexical items and incorporates 33,000 vulgarity ratings. Using it as a seed lexicon for fully automatic lexical acquisition, we were able to raise its coverage up to slightly more than 11,000 entries. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3513/ |
| https://www.aclweb.org/anthology/W19-3513 | |
| PWC | https://paperswithcode.com/paper/at-the-lower-end-of-language-exploring-the |
| Repo | |
| Framework | |
Findings of the WMT 2019 Shared Tasks on Quality Estimation
| Title | Findings of the WMT 2019 Shared Tasks on Quality Estimation |
| Authors | Erick Fonseca, Lisa Yankovskaya, Andr{'e} F. T. Martins, Mark Fishel, Christian Federmann |
| Abstract | We report the results of the WMT19 shared task on Quality Estimation, i.e. the task of predicting the quality of the output of machine translation systems given just the source text and the hypothesis translations. The task includes estimation at three granularity levels: word, sentence and document. A novel addition is evaluating sentence-level QE against human judgments: in other words, designing MT metrics that do not need a reference translation. This year we include three language pairs, produced solely by neural machine translation systems. Participating teams from eleven institutions submitted a variety of systems to different task variants and language pairs. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5401/ |
| https://www.aclweb.org/anthology/W19-5401 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-wmt-2019-shared-tasks-on |
| Repo | |
| Framework | |
Probabilistic Semantic Embedding
| Title | Probabilistic Semantic Embedding |
| Authors | Yue Jiao, Jonathon Hare, Adam Prügel-Bennett |
| Abstract | We present an extension of a variational auto-encoder that creates semantically richcoupled probabilistic latent representations that capture the semantics of multiplemodalities of data. We demonstrate this model through experiments using imagesand textual descriptors as inputs and images as outputs. Our latent representationsare not only capable of driving a decoder to generate novel data, but can also be useddirectly for annotation or classification. Using the MNIST and Fashion-MNISTdatasets we show that the embedding not only provides better reconstruction andclassification performance than the current state-of-the-art, but it also allows us toexploit the semantic content of the pretrained word embedding spaces to do taskssuch as image generation from labels outside of those seen during training. |
| Tasks | Image Generation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1xwqjRcY7 |
| https://openreview.net/pdf?id=r1xwqjRcY7 | |
| PWC | https://paperswithcode.com/paper/probabilistic-semantic-embedding |
| Repo | |
| Framework | |
USF at SemEval-2019 Task 6: Offensive Language Detection Using LSTM With Word Embeddings
| Title | USF at SemEval-2019 Task 6: Offensive Language Detection Using LSTM With Word Embeddings |
| Authors | Bharti Goel, Ravi Sharma |
| Abstract | In this paper, we present a system description for the SemEval-2019 Task 6 submitted by our team. For the task, our system takes tweet as an input and determine if the tweet is offensive or non-offensive (Sub-task A). In case a tweet is offensive, our system identifies if a tweet is targeted (insult or threat) or non-targeted like swearing (Sub-task B). In targeted tweets, our system identifies the target as an individual or group (Sub-task C). We used data pre-processing techniques like splitting hashtags into words, removing special characters, stop-word removal, stemming, lemmatization, capitalization, and offensive word dictionary. Later, we used keras tokenizer and word embeddings for feature extraction. For classification, we used the LSTM (Long short-term memory) model of keras framework. Our accuracy scores for Sub-task A, B and C are \textit{0.8128}, \textit{0.8167} and \textit{0.3662} respectively. Our results indicate that fine-grained classification to identify offense target was difficult for the system. Lastly, in the future scope section, we will discuss the ways to improve system performance. |
| Tasks | Lemmatization, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2139/ |
| https://www.aclweb.org/anthology/S19-2139 | |
| PWC | https://paperswithcode.com/paper/usf-at-semeval-2019-task-6-offensive-language |
| Repo | |
| Framework | |
