Paper Group NANR 239
Mawdoo3 AI at MADAR Shared Task: Arabic Fine-Grained Dialect Identification with Ensemble Learning. Relational Attention Network for Crowd Counting. Amodal Instance Segmentation With KINS Dataset. Asynchronous SGD without gradient delay for efficient distributed training. OCR evaluation tools for the 21st century. Dialogue-Act Prediction of Future …
Mawdoo3 AI at MADAR Shared Task: Arabic Fine-Grained Dialect Identification with Ensemble Learning
| Title | Mawdoo3 AI at MADAR Shared Task: Arabic Fine-Grained Dialect Identification with Ensemble Learning |
| Authors | Ahmad Ragab, Haitham Seelawi, Mostafa Samir, Abdelrahman Mattar, Hesham Al-Bataineh, Mohammad Zaghloul, Ahmad Mustafa, Bashar Talafha, Abed Alhakim Freihat, Hussein Al-Natsheh |
| Abstract | In this paper we discuss several models we used to classify 25 city-level Arabic dialects in addition to Modern Standard Arabic (MSA) as part of MADAR shared task (sub-task 1). We propose an ensemble model of a group of experimentally designed best performing classifiers on a various set of features. Our system achieves an accuracy of 69.3{%} macro F1-score with an improvement of 1.4{%} accuracy from the baseline model on the DEV dataset. Our best run submitted model ranked as third out of 19 participating teams on the TEST dataset with only 0.12{%} macro F1-score behind the top ranked system. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4630/ |
| https://www.aclweb.org/anthology/W19-4630 | |
| PWC | https://paperswithcode.com/paper/mawdoo3-ai-at-madar-shared-task-arabic-fine |
| Repo | |
| Framework | |
Relational Attention Network for Crowd Counting
| Title | Relational Attention Network for Crowd Counting |
| Authors | Anran Zhang, Jiayi Shen, Zehao Xiao, Fan Zhu, Xiantong Zhen, Xianbin Cao, Ling Shao |
| Abstract | Crowd counting is receiving rapidly growing research interests due to its potential application value in numerous real-world scenarios. However, due to various challenges such as occlusion, insufficient resolution and dynamic backgrounds, crowd counting remains an unsolved problem in computer vision. Density estimation is a popular strategy for crowd counting, where conventional density estimation methods perform pixel-wise regression without explicitly accounting the interdependence of pixels. As a result, independent pixel-wise predictions can be noisy and inconsistent. In order to address such an issue, we propose a Relational Attention Network (RANet) with a self-attention mechanism for capturing interdependence of pixels. The RANet enhances the self-attention mechanism by accounting both short-range and long-range interdependence of pixels, where we respectively denote these implementations as local self-attention (LSA) and global self-attention (GSA). We further introduce a relation module to fuse LSA and GSA to achieve more informative aggregated feature representations. We conduct extensive experiments on four public datasets, including ShanghaiTech A, ShanghaiTech B, UCF-CC-50 and UCF-QNRF. Experimental results on all datasets suggest RANet consistently reduces estimation errors and surpasses the state-of-the-art approaches by large margins. |
| Tasks | Crowd Counting, Density Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Relational_Attention_Network_for_Crowd_Counting_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Relational_Attention_Network_for_Crowd_Counting_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/relational-attention-network-for-crowd |
| Repo | |
| Framework | |
Amodal Instance Segmentation With KINS Dataset
| Title | Amodal Instance Segmentation With KINS Dataset |
| Authors | Lu Qi, Li Jiang, Shu Liu, Xiaoyong Shen, Jiaya Jia |
| Abstract | Amodal instance segmentation, a new direction of instance segmentation, aims to segment each object instance involving its invisible, occluded parts to imitate human ability. This task requires to reason objects’ complex structure. Despite important and futuristic, this task lacks data with large-scale and detailed annotations, due to the difficulty of correctly and consistently labeling invisible parts, which creates the huge barrier to explore the frontier of visual recognition. In this paper, we augment KITTI with more instance pixel-level annotation for 8 categories, which we call KITTI INStance dataset (KINS). We propose the network structure to reason invisible parts via a new multi-task framework with Multi-View Coding (MVC), which combines information in various recognition levels. Extensive experiments show that our MVC effectively improves both amodal and inmodal segmentation. The KINS dataset and our proposed method will be made publicly available. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Qi_Amodal_Instance_Segmentation_With_KINS_Dataset_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Qi_Amodal_Instance_Segmentation_With_KINS_Dataset_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/amodal-instance-segmentation-with-kins |
| Repo | |
| Framework | |
Asynchronous SGD without gradient delay for efficient distributed training
| Title | Asynchronous SGD without gradient delay for efficient distributed training |
| Authors | Roman Talyansky, Pavel Kisilev, Zach Melamed, Natan Peterfreund, Uri Verner |
| Abstract | Asynchronous distributed gradient descent algorithms for training of deep neural networks are usually considered as inefficient, mainly because of the Gradient delay problem. In this paper, we propose a novel asynchronous distributed algorithm that tackles this limitation by well-thought-out averaging of model updates, computed by workers. The algorithm allows computing gradients along the process of gradient merge, thus, reducing or even completely eliminating worker idle time due to communication overhead, which is a pitfall of existing asynchronous methods. We provide theoretical analysis of the proposed asynchronous algorithm, and show its regret bounds. According to our analysis, the crucial parameter for keeping high convergence rate is the maximal discrepancy between local parameter vectors of any pair of workers. As long as it is kept relatively small, the convergence rate of the algorithm is shown to be the same as the one of a sequential online learning. Furthermore, in our algorithm, this discrepancy is bounded by an expression that involves the staleness parameter of the algorithm, and is independent on the number of workers. This is the main differentiator between our approach and other solutions, such as Elastic Asynchronous SGD or Downpour SGD, in which that maximal discrepancy is bounded by an expression that depends on the number of workers, due to gradient delay problem. To demonstrate effectiveness of our approach, we conduct a series of experiments on image classification task on a cluster with 4 machines, equipped with a commodity communication switch and with a single GPU card per machine. Our experiments show a linear scaling on 4-machine cluster without sacrificing the test accuracy, while eliminating almost completely worker idle time. Since our method allows using commodity communication switch, it paves a way for large scale distributed training performed on commodity clusters. |
| Tasks | Image Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1lo3sC9KX |
| https://openreview.net/pdf?id=H1lo3sC9KX | |
| PWC | https://paperswithcode.com/paper/asynchronous-sgd-without-gradient-delay-for |
| Repo | |
| Framework | |
OCR evaluation tools for the 21st century
| Title | OCR evaluation tools for the 21st century |
| Authors | Eddie Antonio Santos |
| Abstract | |
| Tasks | Optical Character Recognition |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6004/ |
| https://www.aclweb.org/anthology/W19-6004 | |
| PWC | https://paperswithcode.com/paper/ocr-evaluation-tools-for-the-21st-century |
| Repo | |
| Framework | |
Dialogue-Act Prediction of Future Responses Based on Conversation History
| Title | Dialogue-Act Prediction of Future Responses Based on Conversation History |
| Authors | Koji Tanaka, Junya Takayama, Yuki Arase |
| Abstract | Sequence-to-sequence models are a common approach to develop a chatbot. They can train a conversational model in an end-to-end manner. One significant drawback of such a neural network based approach is that the response generation process is a black-box, and how a specific response is generated is unclear. To tackle this problem, an interpretable response generation mechanism is desired. As a step toward this direction, we focus on dialogue-acts (DAs) that may provide insight to understand the response generation process. In particular, we propose a method to predict a DA of the next response based on the history of previous utterances and their DAs. Experiments using a Switch Board Dialogue Act corpus show that compared to the baseline considering only a single utterance, our model achieves 10.8{%} higher F1-score and 3.0{%} higher accuracy on DA prediction. |
| Tasks | Chatbot |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2027/ |
| https://www.aclweb.org/anthology/P19-2027 | |
| PWC | https://paperswithcode.com/paper/dialogue-act-prediction-of-future-responses |
| Repo | |
| Framework | |
Erroneous data generation for Grammatical Error Correction
| Title | Erroneous data generation for Grammatical Error Correction |
| Authors | Shuyao Xu, Jiehao Zhang, Jin Chen, Long Qin |
| Abstract | It has been demonstrated that the utilization of a monolingual corpus in neural Grammatical Error Correction (GEC) systems can significantly improve the system performance. The previous state-of-the-art neural GEC system is an ensemble of four Transformer models pretrained on a large amount of Wikipedia Edits. The Singsound GEC system follows a similar approach but is equipped with a sophisticated erroneous data generating component. Our system achieved an F0:5 of 66.61 in the BEA 2019 Shared Task: Grammatical Error Correction. With our novel erroneous data generating component, the Singsound neural GEC system yielded an M2 of 63.2 on the CoNLL-2014 benchmark (8.4{%} relative improvement over the previous state-of-the-art system). |
| Tasks | Grammatical Error Correction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4415/ |
| https://www.aclweb.org/anthology/W19-4415 | |
| PWC | https://paperswithcode.com/paper/erroneous-data-generation-for-grammatical |
| Repo | |
| Framework | |
WTMED at MEDIQA 2019: A Hybrid Approach to Biomedical Natural Language Inference
| Title | WTMED at MEDIQA 2019: A Hybrid Approach to Biomedical Natural Language Inference |
| Authors | Zhaofeng Wu, Yan Song, Sicong Huang, Yuanhe Tian, Fei Xia |
| Abstract | Natural language inference (NLI) is challenging, especially when it is applied to technical domains such as biomedical settings. In this paper, we propose a hybrid approach to biomedical NLI where different types of information are exploited for this task. Our base model includes a pre-trained text encoder as the core component, and a syntax encoder and a feature encoder to capture syntactic and domain-specific information. Then we combine the output of different base models to form more powerful ensemble models. Finally, we design two conflict resolution strategies when the test data contain multiple (premise, hypothesis) pairs with the same premise. We train our models on the MedNLI dataset, yielding the best performance on the test set of the MEDIQA 2019 Task 1. |
| Tasks | Natural Language Inference |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5044/ |
| https://www.aclweb.org/anthology/W19-5044 | |
| PWC | https://paperswithcode.com/paper/wtmed-at-mediqa-2019-a-hybrid-approach-to |
| Repo | |
| Framework | |
Reinforced Imitation Learning from Observations
| Title | Reinforced Imitation Learning from Observations |
| Authors | Konrad Zolna, Negar Rostamzadeh, Yoshua Bengio, Sungjin Ahn, Pedro O. Pinheiro |
| Abstract | Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent has access to a sparse reward function and state-only expert observations. We propose a method which gradually balances between the imitation learning cost and the reinforcement learning objective. Built upon an existing imitation learning method, our approach works with state-only observations. We show, through navigation scenarios, that (i) an agent is able to efficiently leverage sparse rewards to outperform standard state-only imitation learning, (ii) it can learn a policy even when learner’s actions are different from the expert, and (iii) the performance of the agent is not bounded by that of the expert due to the optimized usage of sparse rewards. |
| Tasks | Imitation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rklhb2R9Y7 |
| https://openreview.net/pdf?id=rklhb2R9Y7 | |
| PWC | https://paperswithcode.com/paper/reinforced-imitation-learning-from |
| Repo | |
| Framework | |
Specificity-Driven Cascading Approach for Unsupervised Sentiment Modification
| Title | Specificity-Driven Cascading Approach for Unsupervised Sentiment Modification |
| Authors | Pengcheng Yang, Junyang Lin, Jingjing Xu, Jun Xie, Qi Su, Xu Sun |
| Abstract | The task of unsupervised sentiment modification aims to reverse the sentiment polarity of the input text while preserving its semantic content without any parallel data. Most previous work follows a two-step process. They first separate the content from the original sentiment, and then directly generate text with the target sentiment only based on the content produced by the first step. However, the second step bears both the target sentiment addition and content reconstruction, thus resulting in a lack of specific information like proper nouns in the generated text. To remedy this, we propose a specificity-driven cascading approach in this work, which can effectively increase the specificity of the generated text and further improve content preservation. In addition, we propose a more reasonable metric to evaluate sentiment modification. The experiments show that our approach outperforms competitive baselines by a large margin, which achieves 11{%} and 38{%} relative improvements of the overall metric on the Yelp and Amazon datasets, respectively. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1553/ |
| https://www.aclweb.org/anthology/D19-1553 | |
| PWC | https://paperswithcode.com/paper/specificity-driven-cascading-approach-for |
| Repo | |
| Framework | |
Neural Question Generation using Interrogative Phrases
| Title | Neural Question Generation using Interrogative Phrases |
| Authors | Yuichi Sasazawa, Sho Takase, Naoaki Okazaki |
| Abstract | Question Generation (QG) is the task of generating questions from a given passage. One of the key requirements of QG is to generate a question such that it results in a target answer. Previous works used a target answer to obtain a desired question. However, we also want to specify how to ask questions and improve the quality of generated questions. In this study, we explore the use of interrogative phrases as additional sources to control QG. By providing interrogative phrases, we expect that QG can generate a more reliable sequence of words subsequent to an interrogative phrase. We present a baseline sequence-to-sequence model with the attention, copy, and coverage mechanisms, and show that the simple baseline achieves state-of-the-art performance. The experiments demonstrate that interrogative phrases contribute to improving the performance of QG. In addition, we report the superiority of using interrogative phrases in human evaluation. Finally, we show that a question answering system can provide target answers more correctly when the questions are generated with interrogative phrases. |
| Tasks | Question Answering, Question Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8613/ |
| https://www.aclweb.org/anthology/W19-8613 | |
| PWC | https://paperswithcode.com/paper/neural-question-generation-using |
| Repo | |
| Framework | |
The AIP-Tohoku System at the BEA-2019 Shared Task
| Title | The AIP-Tohoku System at the BEA-2019 Shared Task |
| Authors | Hiroki Asano, Masato Mita, Tomoya Mizumoto, Jun Suzuki |
| Abstract | We introduce the AIP-Tohoku grammatical error correction (GEC) system for the BEA-2019 shared task in Track 1 (Restricted Track) and Track 2 (Unrestricted Track) using the same system architecture. Our system comprises two key components: error generation and sentence-level error detection. In particular, GEC with sentence-level grammatical error detection is a novel and versatile approach, and we experimentally demonstrate that it significantly improves the precision of the base model. Our system is ranked 9th in Track 1 and 2nd in Track 2. |
| Tasks | Grammatical Error Correction, Grammatical Error Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4418/ |
| https://www.aclweb.org/anthology/W19-4418 | |
| PWC | https://paperswithcode.com/paper/the-aip-tohoku-system-at-the-bea-2019-shared |
| Repo | |
| Framework | |
Knowledge-Based Word Sense Disambiguation with Distributional Semantic Expansion
| Title | Knowledge-Based Word Sense Disambiguation with Distributional Semantic Expansion |
| Authors | Hossein Rouhizadeh, Mehrnoush Shamsfard, Masoud Rouhizadeh |
| Abstract | In this paper, we presented a WSD system that uses LDA topics for semantic expansion of document words. Our system also uses sense frequency information from SemCor to give higher priority to the senses which are more probable to happen. |
| Tasks | Word Sense Disambiguation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3604/ |
| https://www.aclweb.org/anthology/W19-3604 | |
| PWC | https://paperswithcode.com/paper/knowledge-based-word-sense-disambiguation-1 |
| Repo | |
| Framework | |
Exploiting Monolingual Data at Scale for Neural Machine Translation
| Title | Exploiting Monolingual Data at Scale for Neural Machine Translation |
| Authors | Lijun Wu, Yiren Wang, Yingce Xia, Tao Qin, Jianhuang Lai, Tie-Yan Liu |
| Abstract | While target-side monolingual data has been proven to be very useful to improve neural machine translation (briefly, NMT) through back translation, source-side monolingual data is not well investigated. In this work, we study how to use both the source-side and target-side monolingual data for NMT, and propose an effective strategy leveraging both of them. First, we generate synthetic bitext by translating monolingual data from the two domains into the other domain using the models pretrained on genuine bitext. Next, a model is trained on a noised version of the concatenated synthetic bitext where each source sequence is randomly corrupted. Finally, the model is fine-tuned on the genuine bitext and a clean version of a subset of the synthetic bitext without adding any noise. Our approach achieves state-of-the-art results on WMT16, WMT17, WMT18 English$\leftrightarrow$German translations and WMT19 German$\to$French translations, which demonstrate the effectiveness of our method. We also conduct a comprehensive study on how each part in the pipeline works. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1430/ |
| https://www.aclweb.org/anthology/D19-1430 | |
| PWC | https://paperswithcode.com/paper/exploiting-monolingual-data-at-scale-for |
| Repo | |
| Framework | |
Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts
| Title | Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts |
| Authors | Elizabeth Clark, Asli Celikyilmaz, Noah A. Smith |
| Abstract | For evaluating machine-generated texts, automatic methods hold the promise of avoiding collection of human judgments, which can be expensive and time-consuming. The most common automatic metrics, like BLEU and ROUGE, depend on exact word matching, an inflexible approach for measuring semantic similarity. We introduce methods based on sentence mover{'}s similarity; our automatic metrics evaluate text in a continuous space using word and sentence embeddings. We find that sentence-based metrics correlate with human judgments significantly better than ROUGE, both on machine-generated summaries (average length of 3.4 sentences) and human-authored essays (average length of 7.5). We also show that sentence mover{'}s similarity can be used as a reward when learning a generation model via reinforcement learning; we present both automatic and human evaluations of summaries learned in this way, finding that our approach outperforms ROUGE. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Sentence Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1264/ |
| https://www.aclweb.org/anthology/P19-1264 | |
| PWC | https://paperswithcode.com/paper/sentence-movers-similarity-automatic |
| Repo | |
| Framework | |
