Paper Group NANR 49
Is this the end? Two-step tokenization of sentence boundaries. What can we learn from natural and artificial dependency trees. Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. signSGD via Zeroth-Order Oracle. Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification. What goes in …
Is this the end? Two-step tokenization of sentence boundaries
| Title | Is this the end? Two-step tokenization of sentence boundaries |
| Authors | Linda Wiechetek, Sjur N{\o}rsteb{\o} Moshagen, Thomas Omma |
| Abstract | |
| Tasks | Tokenization |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0312/ |
| https://www.aclweb.org/anthology/W19-0312 | |
| PWC | https://paperswithcode.com/paper/is-this-the-end-two-step-tokenization-of |
| Repo | |
| Framework | |
What can we learn from natural and artificial dependency trees
| Title | What can we learn from natural and artificial dependency trees |
| Authors | Marine Courtin, Chunxiao Yan |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7915/ |
| https://www.aclweb.org/anthology/W19-7915 | |
| PWC | https://paperswithcode.com/paper/what-can-we-learn-from-natural-and-artificial |
| Repo | |
| Framework | |
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks
| Title | Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks |
| Authors | Jing Ma, Wei Gao, Shafiq Joty, Kam-Fai Wong |
| Abstract | Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications. It is cumbersome and inefficient for human fact-checkers to find consistent pieces of evidence, from which solid verdict could be inferred against the claim. In this paper, we propose a novel end-to-end hierarchical attention network focusing on learning to represent coherent evidence as well as their semantic relatedness with the claim. Our model consists of three main components: 1) A coherence-based attention layer embeds coherent evidence considering the claim and sentences from relevant articles; 2) An entailment-based attention layer attends on sentences that can semantically infer the claim on top of the first attention; and 3) An output layer predicts the verdict based on the embedded evidence. Experimental results on three public benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1244/ |
| https://www.aclweb.org/anthology/P19-1244 | |
| PWC | https://paperswithcode.com/paper/sentence-level-evidence-embedding-for-claim |
| Repo | |
| Framework | |
signSGD via Zeroth-Order Oracle
| Title | signSGD via Zeroth-Order Oracle |
| Authors | Sijia Liu, Pin-Yu Chen, Xiangyi Chen, Mingyi Hong |
| Abstract | In this paper, we design and analyze a new zeroth-order (ZO) stochastic optimization algorithm, ZO-signSGD, which enjoys dual advantages of gradient-free operations and signSGD. The latter requires only the sign information of gradient estimates but is able to achieve a comparable or even better convergence speed than SGD-type algorithms. Our study shows that ZO signSGD requires $\sqrt{d}$ times more iterations than signSGD, leading to a convergence rate of $O(\sqrt{d}/\sqrt{T})$ under mild conditions, where $d$ is the number of optimization variables, and $T$ is the number of iterations. In addition, we analyze the effects of different types of gradient estimators on the convergence of ZO-signSGD, and propose two variants of ZO-signSGD that at least achieve $O(\sqrt{d}/\sqrt{T})$ convergence rate. On the application side we explore the connection between ZO-signSGD and black-box adversarial attacks in robust deep learning. Our empirical evaluations on image classification datasets MNIST and CIFAR-10 demonstrate the superior performance of ZO-signSGD on the generation of adversarial examples from black-box neural networks. |
| Tasks | Image Classification, Stochastic Optimization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJe-DsC5Fm |
| https://openreview.net/pdf?id=BJe-DsC5Fm | |
| PWC | https://paperswithcode.com/paper/signsgd-via-zeroth-order-oracle |
| Repo | |
| Framework | |
Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification
| Title | Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification |
| Authors | Wen-Hsuan Chu, Yu-Jhe Li, Jing-Cheng Chang, Yu-Chiang Frank Wang |
| Abstract | Few-shot learning (FSL) requires one to learn from object categories with a small amount of training data (as novel classes), while the remaining categories (as base classes) contain a sufficient amount of data for training. It is often desirable to transfer knowledge from the base classes and derive dominant features efficiently for the novel samples. In this work, we propose a sampling method that de-correlates an image based on maximum entropy reinforcement learning, and extracts varying sequences of patches on every forward-pass with discriminative information observed. This can be viewed as a form of “learned” data augmentation in the sense that we search for different sequences of patches within an image and performs classification with aggregation of the extracted features, resulting in improved FSL performances. In addition, our positive and negative sampling policies along with a newly defined reward function would favorably improve the effectiveness of our model. Our experiments on two benchmark datasets confirm the effectiveness of our framework and its superiority over recent FSL approaches. |
| Tasks | Data Augmentation, Few-Shot Image Classification, Few-Shot Learning, Image Classification |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chu_Spot_and_Learn_A_Maximum-Entropy_Patch_Sampler_for_Few-Shot_Image_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chu_Spot_and_Learn_A_Maximum-Entropy_Patch_Sampler_for_Few-Shot_Image_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spot-and-learn-a-maximum-entropy-patch |
| Repo | |
| Framework | |
What goes into a word: generating image descriptions with top-down spatial knowledge
| Title | What goes into a word: generating image descriptions with top-down spatial knowledge |
| Authors | Mehdi Ghanimifard, Simon Dobnik |
| Abstract | Generating grounded image descriptions requires associating linguistic units with their corresponding visual clues. A common method is to train a decoder language model with attention mechanism over convolutional visual features. Attention weights align the stratified visual features arranged by their location with tokens, most commonly words, in the target description. However, words such as spatial relations (e.g. \textit{next{\textasciitilde}to} and \textit{under}) are not directly referring to geometric arrangements of pixels but to complex geometric and conceptual representations. The aim of this paper is to evaluate what representations facilitate generating image descriptions with spatial relations and lead to better grounded language generation. In particular, we investigate the contribution of three different representational modalities in generating relational referring expressions: (i) pre-trained convolutional visual features, (ii) different top-down geometric relational knowledge between objects, and (iii) world knowledge captured by contextual embeddings in language models. |
| Tasks | Language Modelling, Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8668/ |
| https://www.aclweb.org/anthology/W19-8668 | |
| PWC | https://paperswithcode.com/paper/what-goes-into-a-word-generating-image |
| Repo | |
| Framework | |
Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates
| Title | Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates |
| Authors | Sebastian Pad{'o}, Andre Blessing, Nico Blokker, Erenay Dayanik, Sebastian Haunss, Jonas Kuhn |
| Abstract | Understanding the structures of political debates (which actors make what claims) is essential for understanding democratic political decision making. The vision of computational construction of such discourse networks from newspaper reports brings together political science and natural language processing. This paper presents three contributions towards this goal: (a) a requirements analysis, linking the task to knowledge base population; (b) an annotated pilot corpus of migration claims based on German newspaper reports; (c) initial modeling results. |
| Tasks | Decision Making, Knowledge Base Population |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1273/ |
| https://www.aclweb.org/anthology/P19-1273 | |
| PWC | https://paperswithcode.com/paper/who-sides-with-whom-towards-computational |
| Repo | |
| Framework | |
Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition
| Title | Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition |
| Authors | Yaping Zhang, Shuai Nie, Wenju Liu, Xing Xu, Dongxiang Zhang, Heng Tao Shen |
| Abstract | Domain adaptation has shown promising advances for alleviating domain shift problem. However, recent visual domain adaptation works usually focus on non-sequential object recognition with a global coarse alignment, which is inadequate to transfer effective knowledge for sequence-like text images with variable-length fine-grained character information. In this paper, we develop a Sequence-to-Sequence Domain Adaptation Network (SSDAN) for robust text image recognition, which could exploit unsupervised sequence data by an attention-based sequence encoder-decoder network. In the SSDAN, a gated attention similarity (GAS) unit is introduced to adaptively focus on aligning the distribution of the source and target sequence data in an attended character-level feature space rather than a global coarse alignment. Extensive text recognition experiments show the SSDAN could efficiently transfer sequence knowledge and validate the promising power of the proposed model towards real world applications in various recognition scenarios, including the natural scene text, handwritten text and even mathematical expression recognition. |
| Tasks | Domain Adaptation, Object Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Sequence-To-Sequence_Domain_Adaptation_Network_for_Robust_Text_Image_Recognition_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Sequence-To-Sequence_Domain_Adaptation_Network_for_Robust_Text_Image_Recognition_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sequence-to-sequence-domain-adaptation |
| Repo | |
| Framework | |
Separate to Adapt: Open Set Domain Adaptation via Progressive Separation
| Title | Separate to Adapt: Open Set Domain Adaptation via Progressive Separation |
| Authors | Hong Liu, Zhangjie Cao, Mingsheng Long, Jianmin Wang, Qiang Yang |
| Abstract | Domain adaptation has become a resounding success in leveraging labeled data from a source domain to learn an accurate classifier for an unlabeled target domain. When deployed in the wild, the target domain usually contains unknown classes that are not observed in the source domain. Such setting is termed Open Set Domain Adaptation (OSDA). While several methods have been proposed to address OSDA, none of them takes into account the openness of the target domain, which is measured by the proportion of unknown classes in all target classes. Openness is a critical point in open set domain adaptation and exerts a significant impact on performance. In addition, current work aligns the entire target domain with the source domain without excluding unknown samples, which may give rise to negative transfer due to the mismatch between unknown and known classes. To this end, this paper presents Separate to Adapt (STA), an end-to-end approach to open set domain adaptation. The approach adopts a coarse-to-fine weighting mechanism to progressively separate the samples of unknown and known classes, and simultaneously weigh their importance on feature distribution alignment. Our approach allows openness-robust open set domain adaptation, which can be adaptive to a variety of openness in the target domain. We evaluate STA on several benchmark datasets of various openness levels. Results verify that STA significantly outperforms previous methods. |
| Tasks | Domain Adaptation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Separate_to_Adapt_Open_Set_Domain_Adaptation_via_Progressive_Separation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Separate_to_Adapt_Open_Set_Domain_Adaptation_via_Progressive_Separation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/separate-to-adapt-open-set-domain-adaptation |
| Repo | |
| Framework | |
Spatial-Aware Graph Relation Network for Large-Scale Object Detection
| Title | Spatial-Aware Graph Relation Network for Large-Scale Object Detection |
| Authors | Hang Xu, Chenhan Jiang, Xiaodan Liang, Zhenguo Li |
| Abstract | How to proper encode high-order object relation in the detection system without any external knowledge? How to leverage the information between co-occurrence and locations of objects for better reasoning? These questions are key challenges towards large-scale object detection system that aims to recognize thousands of objects entangled with complex spatial and semantic relationships nowadays. Distilling key relations that may affect object recognition is crucially important since treating each region separately leads to a big performance drop when facing heavy long-tail data distributions and plenty of confusing categories. Recent works try to encode relation by constructing graphs, e.g. using handcraft linguistic knowledge between classes or implicitly learning a fully-connected graph between regions. However, the handcraft linguistic knowledge cannot be individualized for each image due to the semantic gap between linguistic and visual context while the fully-connected graph is inefficient and noisy by incorporating redundant and distracted relations/edges from irrelevant objects and backgrounds. In this work, we introduce a Spatial-aware Graph Relation Network (SGRN) to adaptive discover and incorporate key semantic and spatial relationships for reasoning over each object. Our method considers the relative location layouts and interactions among which can be easily injected into any detection pipelines to boost the performance. Specifically, our SGRN integrates a graph learner module for learning a interpatable sparse graph structure to encode relevant contextual regions and a spatial graph reasoning module with learnable spatial Gaussian kernels to perform graph inference with spatial awareness. Extensive experiments verify the effectiveness of our method, e.g. achieving around 32% improvement on VG(3000 classes) and 28% on ADE in terms of mAP. |
| Tasks | Object Detection, Object Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Xu_Spatial-Aware_Graph_Relation_Network_for_Large-Scale_Object_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Xu_Spatial-Aware_Graph_Relation_Network_for_Large-Scale_Object_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-aware-graph-relation-network-for |
| Repo | |
| Framework | |
Deconstructing multimodality: visual properties and visual context in human semantic processing
| Title | Deconstructing multimodality: visual properties and visual context in human semantic processing |
| Authors | Christopher Davis, Luana Bulat, Anita Lilla Vero, Ekaterina Shutova |
| Abstract | Multimodal semantic models that extend linguistic representations with additional perceptual input have proved successful in a range of natural language processing (NLP) tasks. Recent research has successfully used neural methods to automatically create visual representations for words. However, these works have extracted visual features from complete images, and have not examined how different kinds of visual information impact performance. In contrast, we construct multimodal models that differentiate between internal visual properties of the objects and their external visual context. We evaluate the models on the task of decoding brain activity associated with the meanings of nouns, demonstrating their advantage over those based on complete images. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1013/ |
| https://www.aclweb.org/anthology/S19-1013 | |
| PWC | https://paperswithcode.com/paper/deconstructing-multimodality-visual |
| Repo | |
| Framework | |
Projecting Temporal Properties, Events and Actions
| Title | Projecting Temporal Properties, Events and Actions |
| Authors | Fern, Tim o |
| Abstract | Temporal notions based on a finite set \textit{A} of properties are represented in strings, on which projections are defined that vary the granularity \textit{A}. The structure of properties in \textit{A} is elaborated to describe statives, events and actions, subject to a distinction in meaning (advocated by Levin and Rappaport Hovav) between what the lexicon prescribes and what a context of use supplies. The projections proposed are deployed as labels for records and record types amenable to finite-state methods. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0401/ |
| https://www.aclweb.org/anthology/W19-0401 | |
| PWC | https://paperswithcode.com/paper/projecting-temporal-properties-events-and |
| Repo | |
| Framework | |
A Semantic Annotation Scheme for Quantification
| Title | A Semantic Annotation Scheme for Quantification |
| Authors | Harry Bunt |
| Abstract | This paper describes in brief the proposal called {}QuantML{'} which was accepted by the International Organisation for Standards (ISO) last February as a starting point for developing a standard for the interoperable annotation of quantification phenomena in natural language, as part of the ISO 24617 Semantic Annotation Framework. The proposal, firmly rooted in the theory of generalised quantifiers, neo-Davidsonian semantics, and DRT, covers a wide range of quantification phenomena. The QuantML scheme consists of (1) an abstract syntax which defines {}annotation structures{'} as triples and other set-theoretic constructs; (b) a compositional semantics of annotation structures; (3) an XML representation of annotation structures. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0403/ |
| https://www.aclweb.org/anthology/W19-0403 | |
| PWC | https://paperswithcode.com/paper/a-semantic-annotation-scheme-for |
| Repo | |
| Framework | |
A Practical Dialogue-Act-Driven Conversation Model for Multi-Turn Response Selection
| Title | A Practical Dialogue-Act-Driven Conversation Model for Multi-Turn Response Selection |
| Authors | Harshit Kumar, Arvind Agarwal, Sachindra Joshi |
| Abstract | Dialogue Acts play an important role in conversation modeling. Research has shown the utility of dialogue acts for the response selection task, however, the underlying assumption is that the dialogue acts are readily available, which is impractical, as dialogue acts are rarely available for new conversations. This paper proposes an end-to-end multi-task model for conversation modeling, which is optimized for two tasks, dialogue act prediction and response selection, with the latter being the task of interest. It proposes a novel way of combining the predicted dialogue acts of context and response with the context (previous utterances) and response (follow-up utterance) in a crossway fashion, such that, it achieves at par performance for the response selection task compared to the model that uses actual dialogue acts. Through experiments on two well known datasets, we demonstrate that the multi-task model not only improves the accuracy of the dialogue act prediction task but also improves the MRR for the response selection task. Also, the cross-stitching of dialogue acts of context and response with the context and response is better than using either one of them individually. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1205/ |
| https://www.aclweb.org/anthology/D19-1205 | |
| PWC | https://paperswithcode.com/paper/a-practical-dialogue-act-driven-conversation |
| Repo | |
| Framework | |
The Dreem Headband as an Alternative to Polysomnography for EEG Signal Acquisition and Sleep Staging
| Title | The Dreem Headband as an Alternative to Polysomnography for EEG Signal Acquisition and Sleep Staging |
| Authors | Pierrick J. Arnal, Valentin Thorey, Michael E. Ballard, Albert Bou Hernandez, Antoine Guillot, Hugo Jourde, Mason Harris, Mathias Guillard, Pascal Van Beers, Mounir Chennaoui, Fabien Sauvet |
| Abstract | Despite the central role of sleep in our lives and the high prevalence of sleep disorders, sleep is still poorly understood. The development of ambulatory technologies capable of monitoring brain activity during sleep longitudinally is critical to advancing sleep science and facilitating the diagnosis of sleep disorders. We introduced the Dreem headband (DH) as an affordable, comfortable, and user-friendly alternative to polysomnography (PSG). The purpose of this study was to assess the signal acquisition of the DH and the performance of its embedded automatic sleep staging algorithms compared to the gold-standard clinical PSG scored by 5 sleep experts. Thirty-one subjects completed an over-night sleep study at a sleep center while wearing both a PSG and the DH simultaneously. We assessed 1) the EEG signal quality between the DH and the PSG, 2) the heart rate, breathing frequency, and respiration rate variability (RRV) agreement between the DH and the PSG, and 3) the performance of the DH’s automatic sleep staging according to AASM guidelines vs. PSG sleep experts manual scoring. Results demonstrate a strong correlation between the EEG signals acquired by the DH and those from the PSG, and the signals acquired by the DH enable monitoring of alpha (r= 0.71 ± 0.13), beta (r= 0.71 ± 0.18), delta (r = 0.76 ± 0.14), and theta (r = 0.61 ± 0.12) frequencies during sleep. The mean absolute error for heart rate, breathing frequency and RRV was 1.2 ± 0.5 bpm, 0.3 ± 0.2 cpm and 3.2 ± 0.6 %, respectively. Automatic Sleep Staging reached an overall accuracy of 83.5 ± 6.4% (F1 score : 83.8 ± 6.3) for the DH to be compared with an average of 86.4 ± 8.0% (F1 score: 86.3 ± 7.4) for the five sleep experts. These results demonstrate the capacity of the DH to both precisely monitor sleep-related physiological signals and process them accurately into sleep stages. This device paves the way for high-quality, large-scale, longitudinal sleep studies. |
| Tasks | EEG, Sleep Quality, Sleep Stage Detection |
| Published | 2019-06-10 |
| URL | https://doi.org/10.1101/662734 |
| https://www.biorxiv.org/content/biorxiv/early/2019/06/10/662734.full-text.pdf | |
| PWC | https://paperswithcode.com/paper/the-dreem-headband-as-an-alternative-to |
| Repo | |
| Framework | |
