Paper Group NANR 175
Generating Responses with a Specific Emotion in Dialog. SemEval-2019 Task 4: Hyperpartisan News Detection. Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling. SimpleNLG-DE: Adapting SimpleNLG 4 to German. ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation. Machine Reading Comprehe …
Generating Responses with a Specific Emotion in Dialog
| Title | Generating Responses with a Specific Emotion in Dialog |
| Authors | Zhenqiao Song, Xiaoqing Zheng, Lu Liu, Mu Xu, Xuanjing Huang |
| Abstract | It is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction. After a careful investigation of real-life conversation data, we found that there are at least two ways to express emotions with language. One is to describe emotional states by explicitly using strong emotional words; another is to increase the intensity of the emotional experiences by implicitly combining neutral words in distinct ways. We propose an emotional dialogue system (EmoDS) that can generate the meaningful responses with a coherent structure for a post, and meanwhile express the desired emotion explicitly or implicitly within a unified framework. Experimental results showed EmoDS performed better than the baselines in BLEU, diversity and the quality of emotional expression. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1359/ |
| https://www.aclweb.org/anthology/P19-1359 | |
| PWC | https://paperswithcode.com/paper/generating-responses-with-a-specific-emotion |
| Repo | |
| Framework | |
SemEval-2019 Task 4: Hyperpartisan News Detection
| Title | SemEval-2019 Task 4: Hyperpartisan News Detection |
| Authors | Johannes Kiesel, Maria Mestre, Rishabh Shukla, Emmanuel Vincent, Payam Adineh, David Corney, Benno Stein, Martin Potthast |
| Abstract | Hyperpartisan news is news that takes an extreme left-wing or right-wing standpoint. If one is able to reliably compute this meta information, news articles may be automatically tagged, this way encouraging or discouraging readers to consume the text. It is an open question how successfully hyperpartisan news detection can be automated, and the goal of this SemEval task was to shed light on the state of the art. We developed new resources for this purpose, including a manually labeled dataset with 1,273 articles, and a second dataset with 754,000 articles, labeled via distant supervision. The interest of the research community in our task exceeded all our expectations: The datasets were downloaded about 1,000 times, 322 teams registered, of which 184 configured a virtual machine on our shared task cloud service TIRA, of which in turn 42 teams submitted a valid run. The best team achieved an accuracy of 0.822 on a balanced sample (yes : no hyperpartisan) drawn from the manually tagged corpus; an ensemble of the submitted systems increased the accuracy by 0.048. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2145/ |
| https://www.aclweb.org/anthology/S19-2145 | |
| PWC | https://paperswithcode.com/paper/semeval-2019-task-4-hyperpartisan-news |
| Repo | |
| Framework | |
Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling
| Title | Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling |
| Authors | Ping Li, Xiaoyun Li, Cun-Hui Zhang |
| Abstract | Jaccard similarity is widely used as a distance measure in many machine learning and search applications. Typically, hashing methods are essential for the use of Jaccard similarity to be practical in large-scale settings. For hashing binary (0/1) data, the idea of one permutation hashing (OPH) with densification significantly accelerates traditional minwise hashing algorithms while providing unbiased and accurate estimates. In this paper, we propose a strategy named “re-randomization” in the process of densification that could achieve the smallest variance among all densification schemes. The success of this idea naturally inspires us to generalize one permutation hashing to weighted (non-binary) data, which results in the socalled “bin-wise consistent weighted sampling (BCWS)” algorithm. We analyze the behavior of BCWS and compare it with a recent alternative. Extensive experiments on various datasets illustrates the effectiveness of our proposed methods. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9721-re-randomized-densification-for-one-permutation-hashing-and-bin-wise-consistent-weighted-sampling |
| http://papers.nips.cc/paper/9721-re-randomized-densification-for-one-permutation-hashing-and-bin-wise-consistent-weighted-sampling.pdf | |
| PWC | https://paperswithcode.com/paper/re-randomized-densification-for-one |
| Repo | |
| Framework | |
SimpleNLG-DE: Adapting SimpleNLG 4 to German
| Title | SimpleNLG-DE: Adapting SimpleNLG 4 to German |
| Authors | Daniel Braun, Kira Klimt, Daniela Schneider, Florian Matthes |
| Abstract | SimpleNLG is a popular open source surface realiser for the English language. For German, however, the availability of open source and non-domain specific realisers is sparse, partly due to the complexity of the German language. In this paper, we present SimpleNLG-DE, an adaption of SimpleNLG to German. We discuss which parts of the German language have been implemented and how we evaluated our implementation using the TIGER Corpus and newly created data-sets. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8651/ |
| https://www.aclweb.org/anthology/W19-8651 | |
| PWC | https://paperswithcode.com/paper/simplenlg-de-adapting-simplenlg-4-to-german |
| Repo | |
| Framework | |
ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation
| Title | ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation |
| Authors | Di Lin, Dingguo Shen, Siting Shen, Yuanfeng Ji, Dani Lischinski, Daniel Cohen-Or, Hui Huang |
| Abstract | Multi-scale context information has proven to be essential for object segmentation tasks. Recent works construct the multi-scale context by aggregating convolutional feature maps extracted by different levels of a deep neural network. This is typically done by propagating and fusing features in a one-directional, top-down and bottom-up, manner. In this work, we introduce ZigZagNet, which aggregates a richer multi-context feature map by using not only dense top-down and bottom-up propagation, but also by introducing pathways crossing between different levels of the top-down and the bottom-up hierarchies, in a zig-zag fashion. Furthermore, the context information is exchanged and aggregated over multiple stages, where the fused feature maps from one stage are fed into the next one, yielding a more comprehensive context for improved segmentation performance. Our extensive evaluation on the public benchmarks demonstrates that ZigZagNet surpasses the state-of-the-art accuracy for both semantic segmentation and instance segmentation tasks. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lin_ZigZagNet_Fusing_Top-Down_and_Bottom-Up_Context_for_Object_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lin_ZigZagNet_Fusing_Top-Down_and_Bottom-Up_Context_for_Object_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/zigzagnet-fusing-top-down-and-bottom-up |
| Repo | |
| Framework | |
Machine Reading Comprehension Using Structural Knowledge Graph-aware Network
| Title | Machine Reading Comprehension Using Structural Knowledge Graph-aware Network |
| Authors | Delai Qiu, Yuanzhe Zhang, Xinwei Feng, Xiangwen Liao, Wenbin Jiang, Yajuan Lyu, Kang Liu, Jun Zhao |
| Abstract | Leveraging external knowledge is an emerging trend in machine comprehension task. Previous work usually utilizes knowledge graphs such as ConceptNet as external knowledge, and extracts triples from them to enhance the initial representation of the machine comprehension context. However, such method cannot capture the structural information in the knowledge graph. To this end, we propose a Structural Knowledge Graph-aware Network(SKG) model, constructing sub-graphs for entities in the machine comprehension context. Our method dynamically updates the representation of the knowledge according to the structural information of the constructed sub-graph. Experiments show that SKG achieves state-of-the-art performance on the ReCoRD dataset. |
| Tasks | Knowledge Graphs, Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1602/ |
| https://www.aclweb.org/anthology/D19-1602 | |
| PWC | https://paperswithcode.com/paper/machine-reading-comprehension-using |
| Repo | |
| Framework | |
Predicting the Difficulty of Multiple Choice Questions in a High-stakes Medical Exam
| Title | Predicting the Difficulty of Multiple Choice Questions in a High-stakes Medical Exam |
| Authors | Le An Ha, Victoria Yaneva, Peter Baldwin, Janet Mee |
| Abstract | Predicting the construct-relevant difficulty of Multiple-Choice Questions (MCQs) has the potential to reduce cost while maintaining the quality of high-stakes exams. In this paper, we propose a method for estimating the difficulty of MCQs from a high-stakes medical exam, where all questions were deliberately written to a common reading level. To accomplish this, we extract a large number of linguistic features and embedding types, as well as features quantifying the difficulty of the items for an automatic question-answering system. The results show that the proposed approach outperforms various baselines with a statistically significant difference. Best results were achieved when using the full feature set, where embeddings had the highest predictive power, followed by linguistic features. An ablation study of the various types of linguistic features suggested that information from all levels of linguistic processing contributes to predicting item difficulty, with features related to semantic ambiguity and the psycholinguistic properties of words having a slightly higher importance. Owing to its generic nature, the presented approach has the potential to generalize over other exams containing MCQs. |
| Tasks | Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4402/ |
| https://www.aclweb.org/anthology/W19-4402 | |
| PWC | https://paperswithcode.com/paper/predicting-the-difficulty-of-multiple-choice |
| Repo | |
| Framework | |
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Minima and Regularization Effects
| Title | The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Minima and Regularization Effects |
| Authors | Zhanxing Zhu, Jingfeng Wu, Bing Yu, Lei Wu, Jinwen Ma |
| Abstract | Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we theoretically study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics. Through investigating this general optimization dynamics, we analyze the behavior of SGD on escaping from minima and its regularization effects. A novel indicator is derived to characterize the efficiency of escaping from minima through measuring the alignment of noise covariance and the curvature of loss function. Based on this indicator, two conditions are established to show which type of noise structure is superior to isotropic noise in term of escaping efficiency. We further show that the anisotropic noise in SGD satisfies the two conditions, and thus helps to escape from sharp and poor minima effectively, towards more stable and flat minima that typically generalize well. We verify our understanding through comparing this anisotropic diffusion with full gradient descent plus isotropic diffusion (i.e. Langevin dynamics) and other types of position-dependent noise. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1M7soActX |
| https://openreview.net/pdf?id=H1M7soActX | |
| PWC | https://paperswithcode.com/paper/the-anisotropic-noise-in-stochastic-gradient-1 |
| Repo | |
| Framework | |
Co-Mining: Deep Face Recognition With Noisy Labels
| Title | Co-Mining: Deep Face Recognition With Noisy Labels |
| Authors | Xiaobo Wang, Shuo Wang, Jun Wang, Hailin Shi, Tao Mei |
| Abstract | Face recognition has achieved significant progress with the growing scale of collected datasets, which empowers us to train strong convolutional neural networks (CNNs). While a variety of CNN architectures and loss functions have been devised recently, we still have a limited understanding of how to train the CNN models with the label noise inherent in existing face recognition datasets. To address this issue, this paper develops a novel co-mining strategy to effectively train on the datasets with noisy labels. Specifically, we simultaneously use the loss values as the cue to detect noisy labels, exchange the high-confidence clean faces to alleviate the errors accumulated issue caused by the sample-selection bias, and re-weight the predicted clean faces to make them dominate the discriminative model training in a mini-batch fashion. Extensive experiments by training on three popular datasets (i.e., CASIA-WebFace, MS-Celeb-1M and VggFace2) and testing on several benchmarks, including LFW, AgeDB, CFP, CALFW, CPLFW, RFW, and MegaFace, have demonstrated the effectiveness of our new approach over the state-of-the-art alternatives. |
| Tasks | Face Recognition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Co-Mining_Deep_Face_Recognition_With_Noisy_Labels_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Co-Mining_Deep_Face_Recognition_With_Noisy_Labels_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/co-mining-deep-face-recognition-with-noisy |
| Repo | |
| Framework | |
NUIG at the FinSBD Task: Sentence Boundary Detection for Noisy Financial PDFs in English and French
| Title | NUIG at the FinSBD Task: Sentence Boundary Detection for Noisy Financial PDFs in English and French |
| Authors | Tobias Daudert, Sina Ahmadi |
| Abstract | |
| Tasks | Boundary Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5519/ |
| https://www.aclweb.org/anthology/W19-5519 | |
| PWC | https://paperswithcode.com/paper/nuig-at-the-finsbd-task-sentence-boundary |
| Repo | |
| Framework | |
Recurrent Experience Replay in Distributed Reinforcement Learning
| Title | Recurrent Experience Replay in Distributed Reinforcement Learning |
| Authors | Steven Kapturowski, Georg Ostrovski, Will Dabney, John Quan, Remi Munos |
| Abstract | Building on the recent successes of distributed training of RL agents, in this paper we investigate the training of RNN-based RL agents from distributed prioritized experience replay. We study the effects of parameter lag resulting in representational drift and recurrent state staleness and empirically derive an improved training strategy. Using a single network architecture and fixed set of hyperparameters, the resulting agent, Recurrent Replay Distributed DQN, quadruples the previous state of the art on Atari-57, and surpasses the state of the art on DMLab-30. It is the first agent to exceed human-level performance in 52 of the 57 Atari games. |
| Tasks | Atari Games |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1lyTjAqYX |
| https://openreview.net/pdf?id=r1lyTjAqYX | |
| PWC | https://paperswithcode.com/paper/recurrent-experience-replay-in-distributed |
| Repo | |
| Framework | |
Proceedings of the 6th International Sanskrit Computational Linguistics Symposium
| Title | Proceedings of the 6th International Sanskrit Computational Linguistics Symposium |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-7500/ |
| https://www.aclweb.org/anthology/W19-7500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-6th-international-sanskrit |
| Repo | |
| Framework | |
Future Directions in Technological Support for Language Documentation
| Title | Future Directions in Technological Support for Language Documentation |
| Authors | Daan van Esch, Ben Foley, Nay San |
| Abstract | |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6003/ |
| https://www.aclweb.org/anthology/W19-6003 | |
| PWC | https://paperswithcode.com/paper/future-directions-in-technological-support |
| Repo | |
| Framework | |
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
| Title | Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2000/ |
| https://www.aclweb.org/anthology/N19-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2019-conference-of-the-1 |
| Repo | |
| Framework | |
No-Press Diplomacy: Modeling Multi-Agent Gameplay
| Title | No-Press Diplomacy: Modeling Multi-Agent Gameplay |
| Authors | Philip Paquette, Yuchen Lu, Seton Steven Bocco, Max Smith, Satya O.-G., Jonathan K. Kummerfeld, Joelle Pineau, Satinder Singh, Aaron C. Courville |
| Abstract | Diplomacy is a seven-player non-stochastic, non-cooperative game, where agents acquire resources through a mix of teamwork and betrayal. Reliance on trust and coordination makes Diplomacy the first non-cooperative multi-agent benchmark for complex sequential social dilemmas in a rich environment. In this work, we focus on training an agent that learns to play the No Press version of Diplomacy where there is no dedicated communication channel between players. We present DipNet, a neural-network-based policy model for No Press Diplomacy. The model was trained on a new dataset of more than 150,000 human games. Our model is trained by supervised learning (SL) from expert trajectories, which is then used to initialize a reinforcement learning (RL) agent trained through self-play. Both the SL and the RL agent demonstrate state-of-the-art No Press performance by beating popular rule-based bots. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8697-no-press-diplomacy-modeling-multi-agent-gameplay |
| http://papers.nips.cc/paper/8697-no-press-diplomacy-modeling-multi-agent-gameplay.pdf | |
| PWC | https://paperswithcode.com/paper/no-press-diplomacy-modeling-multi-agent-1 |
| Repo | |
| Framework | |
