Paper Group NANR 188
Exploration of Noise Strategies in Semi-supervised Named Entity Classification. Improving Human Needs Categorization of Events with Semantic Classification. Understanding the Effect of Textual Adversaries in Multimodal Machine Translation. Dynamic Multi-Scale Filters for Semantic Segmentation. Joint Representation and Estimator Learning for Facial …
Exploration of Noise Strategies in Semi-supervised Named Entity Classification
| Title | Exploration of Noise Strategies in Semi-supervised Named Entity Classification |
| Authors | Pooja Lakshmi Narayan, Ajay Nagesh, Mihai Surdeanu |
| Abstract | Noise is inherent in real world datasets and modeling noise is critical during training as it is effective in regularization. Recently, novel semi-supervised deep learning techniques have demonstrated tremendous potential when learning with very limited labeled training data in image processing tasks. A critical aspect of these semi-supervised learning techniques is augmenting the input or the network with noise to be able to learn robust models. While modeling noise is relatively straightforward in continuous domains such as image classification, it is not immediately apparent how noise can be modeled in discrete domains such as language. Our work aims to address this gap by exploring different noise strategies for the semi-supervised named entity classification task, including statistical methods such as adding Gaussian noise to input embeddings, and linguistically-inspired ones such as dropping words and replacing words with their synonyms. We compare their performance on two benchmark datasets (OntoNotes and CoNLL) for named entity classification. Our results indicate that noise strategies that are linguistically informed perform at least as well as statistical approaches, while being simpler and requiring minimal tuning. |
| Tasks | Image Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1020/ |
| https://www.aclweb.org/anthology/S19-1020 | |
| PWC | https://paperswithcode.com/paper/exploration-of-noise-strategies-in-semi |
| Repo | |
| Framework | |
Improving Human Needs Categorization of Events with Semantic Classification
| Title | Improving Human Needs Categorization of Events with Semantic Classification |
| Authors | Haibo Ding, Ellen Riloff, Zhe Feng |
| Abstract | Human Needs categories have been used to characterize the reason why an affective event is positive or negative. For example, {}I got the flu{''} and {}I got fired{''} are both negative (undesirable) events, but getting the flu is a Health problem while getting fired is a Financial problem. Previous work created learning models to assign events to Human Needs categories based on their words and contexts. In this paper, we introduce an intermediate step that assigns words to relevant semantic concepts. We create lightly supervised models that learn to label words with respect to 10 semantic concepts associated with Human Needs categories, and incorporate these labels as features for event categorization. Our results show that recognizing relevant semantic concepts improves both the recall and precision of Human Needs categorization for events. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1022/ |
| https://www.aclweb.org/anthology/S19-1022 | |
| PWC | https://paperswithcode.com/paper/improving-human-needs-categorization-of |
| Repo | |
| Framework | |
Understanding the Effect of Textual Adversaries in Multimodal Machine Translation
| Title | Understanding the Effect of Textual Adversaries in Multimodal Machine Translation |
| Authors | Koel Dutta Chowdhury, Desmond Elliott |
| Abstract | It is assumed that multimodal machine translation systems are better than text-only systems at translating phrases that have a direct correspondence in the image. This assumption has been challenged in experiments demonstrating that state-of-the-art multimodal systems perform equally well in the presence of randomly selected images, but, more recently, it has been shown that masking entities from the source language sentence during training can help to overcome this problem. In this paper, we conduct experiments with both visual and textual adversaries in order to understand the role of incorrect textual inputs to such systems. Our results show that when the source language sentence contains mistakes, multimodal translation systems do not leverage the additional visual signal to produce the correct translation. We also find that the degradation of translation performance caused by textual adversaries is significantly higher than by visual adversaries. |
| Tasks | Machine Translation, Multimodal Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6406/ |
| https://www.aclweb.org/anthology/D19-6406 | |
| PWC | https://paperswithcode.com/paper/understanding-the-effect-of-textual |
| Repo | |
| Framework | |
Dynamic Multi-Scale Filters for Semantic Segmentation
| Title | Dynamic Multi-Scale Filters for Semantic Segmentation |
| Authors | Junjun He, Zhongying Deng, Yu Qiao |
| Abstract | Multi-scale representation provides an effective way to address scale variation of objects and stuff in semantic segmentation. Previous works construct multi-scale representation by utilizing different filter sizes, expanding filter sizes with dilated filters or pooling grids, and the parameters of these filters are fixed after training. These methods often suffer from heavy computational cost or have more parameters, and are not adaptive to the input image during inference. To address these problems, this paper proposes a Dynamic Multi-scale Network (DMNet) to adaptively capture multi-scale contents for predicting pixel-level semantic labels. DMNet is composed of multiple Dynamic Convolutional Modules (DCMs) arranged in parallel, each of which exploits context-aware filters to estimate semantic representation for a specific scale. The outputs of multiple DCMs are further integrated for final segmentation. We conduct extensive experiments to evaluate our DMNet on three challenging semantic segmentation and scene parsing datasets, PASCAL VOC 2012, Pascal-Context, and ADE20K. DMNet achieves a new record 84.4% mIoU on PASCAL VOC 2012 test set without MS COCO pre-trained and post-processing, and also obtains state-of-the-art performance on Pascal-Context and ADE20K. |
| Tasks | Scene Parsing, Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-multi-scale-filters-for-semantic |
| Repo | |
| Framework | |
Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation
| Title | Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation |
| Authors | Yong Zhang, Baoyuan Wu, Weiming Dong, Zhifeng Li, Wei Liu, Bao-Gang Hu, Qiang Ji |
| Abstract | Facial action unit (AU) intensity is an index to characterize human expressions. Accurate AU intensity estimation depends on three major elements: image representation, intensity estimator, and supervisory information. Most existing methods learn intensity estimator with fixed image representation, and rely on the availability of fully annotated supervisory information. In this paper, a novel general framework for AU intensity estimation is presented, which differs from traditional estimation methods in two aspects. First, rather than keeping image representation fixed, it simultaneously learns representation and intensity estimator to achieve an optimal solution. Second, it allows incorporating weak supervisory training signal from human knowledge (e.g. feature smoothness, label smoothness, label ranking, and positive label), which makes our model trainable even fully annotated information is not available. More specifically, human knowledge is represented as either soft or hard constraints which are encoded as regularization terms or equality/inequality constraints, respectively. On top of our novel framework, we additionally propose an efficient algorithm for optimization based on Alternating Direction Method of Multipliers (ADMM). Evaluations on two benchmark databases show that our method outperforms competing methods under different ratios of AU intensity annotations, especially for small ratios. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Joint_Representation_and_Estimator_Learning_for_Facial_Action_Unit_Intensity_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Joint_Representation_and_Estimator_Learning_for_Facial_Action_Unit_Intensity_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/joint-representation-and-estimator-learning |
| Repo | |
| Framework | |
Word Embeddings (Also) Encode Human Personality Stereotypes
| Title | Word Embeddings (Also) Encode Human Personality Stereotypes |
| Authors | Oshin Agarwal, Funda Durup{\i}nar, Norman I. Badler, Ani Nenkova |
| Abstract | Word representations trained on text reproduce human implicit bias related to gender, race and age. Methods have been developed to remove such bias. Here, we present results that show that human stereotypes exist even for much more nuanced judgments such as personality, for a variety of person identities beyond the typically legally protected attributes and that these are similarly captured in word representations. Specifically, we collected human judgments about a person{'}s Big Five personality traits formed solely from information about the occupation, nationality or a common noun description of a hypothetical person. Analysis of the data reveals a large number of statistically significant stereotypes in people. We then demonstrate the bias captured in lexical representations is statistically significantly correlated with the documented human bias. Our results, showing bias for a large set of person descriptors for such nuanced traits put in doubt the feasibility of broadly and fairly applying debiasing methods and call for the development of new methods for auditing language technology systems and resources. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1023/ |
| https://www.aclweb.org/anthology/S19-1023 | |
| PWC | https://paperswithcode.com/paper/word-embeddings-also-encode-human-personality |
| Repo | |
| Framework | |
Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension
| Title | Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension |
| Authors | Yimeng Zhuang, Huadong Wang |
| Abstract | Multi-passage reading comprehension requires the ability to combine cross-passage information and reason over multiple passages to infer the answer. In this paper, we introduce the Dynamic Self-attention Network (DynSAN) for multi-passage reading comprehension task, which processes cross-passage information at token-level and meanwhile avoids substantial computational costs. The core module of the dynamic self-attention is a proposed gated token selection mechanism, which dynamically selects important tokens from a sequence. These chosen tokens will attend to each other via a self-attention mechanism to model long-range dependencies. Besides, convolutional layers are combined with the dynamic self-attention to enhance the model{'}s capacity of extracting local semantic. The experimental results show that the proposed DynSAN achieves new state-of-the-art performance on the SearchQA, Quasar-T and WikiHop datasets. Further ablation study also validates the effectiveness of our model components. |
| Tasks | Reading Comprehension |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1218/ |
| https://www.aclweb.org/anthology/P19-1218 | |
| PWC | https://paperswithcode.com/paper/token-level-dynamic-self-attention-network |
| Repo | |
| Framework | |
Computer Stylometric Comparison of Writings by Qassim Amin and Mohammed Abdu on Women’s Rights
| Title | Computer Stylometric Comparison of Writings by Qassim Amin and Mohammed Abdu on Women’s Rights |
| Authors | Ahmed Omer, Michael Oakes |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5601/ |
| https://www.aclweb.org/anthology/W19-5601 | |
| PWC | https://paperswithcode.com/paper/computer-stylometric-comparison-of-writings |
| Repo | |
| Framework | |
Bot2Vec: Learning Representations of Chatbots
| Title | Bot2Vec: Learning Representations of Chatbots |
| Authors | Jonathan Herzig, S, Tommy bank, Michal Shmueli-Scheuer, David Konopnicki |
| Abstract | Chatbots (i.e., bots) are becoming widely used in multiple domains, along with supporting bot programming platforms. These platforms are equipped with novel testing tools aimed at improving the quality of individual chatbots. Doing so requires an understanding of what sort of bots are being built (captured by their underlying conversation graphs) and how well they perform (derived through analysis of conversation logs). In this paper, we propose a new model, Bot2Vec, that embeds bots to a compact representation based on their structure and usage logs. Then, we utilize Bot2Vec representations to improve the quality of two bot analysis tasks. Using conversation data and graphs of over than 90 bots, we show that Bot2Vec representations improve detection performance by more than 16{%} for both tasks. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1009/ |
| https://www.aclweb.org/anthology/S19-1009 | |
| PWC | https://paperswithcode.com/paper/bot2vec-learning-representations-of-chatbots |
| Repo | |
| Framework | |
Exploiting the Entity Type Sequence to Benefit Event Detection
| Title | Exploiting the Entity Type Sequence to Benefit Event Detection |
| Authors | Yuze Ji, Youfang Lin, Jianwei Gao, Huaiyu Wan |
| Abstract | Event Detection (ED) is one of the most important task in the field of information extraction. The goal of ED is to find triggers in sentences and classify them into different event types. In previous works, the information of entity types are commonly utilized to benefit event detection. However, the sequential features of entity types have not been well utilized yet in the existing ED methods. In this paper, we propose a novel ED approach which learns sequential features from word sequences and entity type sequences separately, and combines these two types of sequential features with the help of a trigger-entity interaction learning module. The experimental results demonstrate that our proposed approach outperforms the state-of-the-art methods. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1057/ |
| https://www.aclweb.org/anthology/K19-1057 | |
| PWC | https://paperswithcode.com/paper/exploiting-the-entity-type-sequence-to |
| Repo | |
| Framework | |
Revisiting the Binary Linearization Technique for Surface Realization
| Title | Revisiting the Binary Linearization Technique for Surface Realization |
| Authors | Yevgeniy Puzikov, Claire Gardent, Ido Dagan, Iryna Gurevych |
| Abstract | End-to-end neural approaches have achieved state-of-the-art performance in many natural language processing (NLP) tasks. Yet, they often lack transparency of the underlying decision-making process, hindering error analysis and certain model improvements. In this work, we revisit the binary linearization approach to surface realization, which exhibits more interpretable behavior, but was falling short in terms of prediction accuracy. We show how enriching the training data to better capture word order constraints almost doubles the performance of the system. We further demonstrate that encoding both local and global prediction contexts yields another considerable performance boost. With the proposed modifications, the system which ranked low in the latest shared task on multilingual surface realization now achieves best results in five out of ten languages, while being on par with the state-of-the-art approaches in others. |
| Tasks | Decision Making |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8635/ |
| https://www.aclweb.org/anthology/W19-8635 | |
| PWC | https://paperswithcode.com/paper/revisiting-the-binary-linearization-technique |
| Repo | |
| Framework | |
Slot Tagging for Task Oriented Spoken Language Understanding in Human-to-Human Conversation Scenarios
| Title | Slot Tagging for Task Oriented Spoken Language Understanding in Human-to-Human Conversation Scenarios |
| Authors | Kunho Kim, Rahul Jha, Kyle Williams, Alex Marin, Imed Zitouni |
| Abstract | Task oriented language understanding (LU) in human-to-machine (H2M) conversations has been extensively studied for personal digital assistants. In this work, we extend the task oriented LU problem to human-to-human (H2H) conversations, focusing on the slot tagging task. Recent advances on LU in H2M conversations have shown accuracy improvements by adding encoded knowledge from different sources. Inspired by this, we explore several variants of a bidirectional LSTM architecture that relies on different knowledge sources, such as Web data, search engine click logs, expert feedback from H2M models, as well as previous utterances in the conversation. We also propose ensemble techniques that aggregate these different knowledge sources into a single model. Experimental evaluation on a four-turn Twitter dataset in the restaurant and music domains shows improvements in the slot tagging F1-score of up to 6.09{%} compared to existing approaches. |
| Tasks | Spoken Language Understanding |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1071/ |
| https://www.aclweb.org/anthology/K19-1071 | |
| PWC | https://paperswithcode.com/paper/slot-tagging-for-task-oriented-spoken |
| Repo | |
| Framework | |
Is an Affine Constraint Needed for Affine Subspace Clustering?
| Title | Is an Affine Constraint Needed for Affine Subspace Clustering? |
| Authors | Chong You, Chun-Guang Li, Daniel P. Robinson, Rene Vidal |
| Abstract | Subspace clustering methods based on expressing each data point as a linear combination of other data points have achieved great success in computer vision applications such as motion segmentation, face and digit clustering. In face clustering, the subspaces are linear and subspace clustering methods can be applied directly. In motion segmentation, the subspaces are affine and an additional affine constraint on the coefficients is often enforced. However, since affine subspaces can always be embedded into linear subspaces of one extra dimension, it is unclear if the affine constraint is really necessary. This paper shows, both theoretically and empirically, that when the dimension of the ambient space is high relative to the sum of the dimensions of the affine subspaces, the affine constraint has a negligible effect on clustering performance. Specifically, our analysis provides conditions that guarantee the correctness of affine subspace clustering methods both with and without the affine constraint, and shows that these conditions are satisfied for high-dimensional data. Underlying our analysis is the notion of affinely independent subspaces, which not only provides geometrically interpretable correctness conditions, but also clarifies the relationships between existing results for affine subspace clustering. |
| Tasks | Motion Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/You_Is_an_Affine_Constraint_Needed_for_Affine_Subspace_Clustering_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/You_Is_an_Affine_Constraint_Needed_for_Affine_Subspace_Clustering_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/is-an-affine-constraint-needed-for-affine |
| Repo | |
| Framework | |
An Online Platform for Community-Based Language Description and Documentation
| Title | An Online Platform for Community-Based Language Description and Documentation |
| Authors | Rebecca Everson, Wolf Honore, Scott Grimm |
| Abstract | |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6001/ |
| https://www.aclweb.org/anthology/W19-6001 | |
| PWC | https://paperswithcode.com/paper/an-online-platform-for-community-based |
| Repo | |
| Framework | |
C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection
| Title | C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection |
| Authors | Yan Gao, Boxiao Liu, Nan Guo, Xiaochun Ye, Fang Wan, Haihang You, Dongrui Fan |
| Abstract | Weakly supervised object detection (WSOD) that only needs image-level annotations has obtained much attention recently. By combining convolutional neural network with multiple instance learning method, Multiple Instance Detection Network (MIDN) has become the most popular method to address the WSOD problem and been adopted as the initial model in many works. We argue that MIDN inclines to converge to the most discriminative object parts, which limits the performance of methods based on it. In this paper, we propose a novel Coupled Multiple Instance Detection Network (C-MIDN) to address this problem. Specifically, we use a pair of MIDNs, which work in a complementary manner with proposal removal. The localization information of the MIDNs is further coupled to obtain tighter bounding boxes and localize multiple objects. We also introduce a Segmentation Guided Proposal Removal (SGPR) algorithm to guarantee the MIL constraint after the removal and ensure the robustness of C-MIDN. Through a simple implementation of the C-MIDN with online detector refinement, we obtain 53.6% and 50.3% mAP on the challenging PASCAL VOC 2007 and 2012 benchmarks respectively, which significantly outperform the previous state-of-the-arts. |
| Tasks | Multiple Instance Learning, Object Detection, Weakly Supervised Object Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Gao_C-MIDN_Coupled_Multiple_Instance_Detection_Network_With_Segmentation_Guidance_for_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Gao_C-MIDN_Coupled_Multiple_Instance_Detection_Network_With_Segmentation_Guidance_for_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/c-midn-coupled-multiple-instance-detection |
| Repo | |
| Framework | |
