Paper Group NANR 220
Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model. SANet: Scene Agnostic Network for Camera Localization. The Cakewalk Method. Towards Practical Alternating Least-Squares for CCA. Tree-structured Decoding for Solving Math Word Problems. Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative …
Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model
| Title | Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model |
| Authors | Wei Li, Jingjing Xu, Yancheng He, ShengLi Yan, Yunfang Wu, Xu Sun |
| Abstract | Automatic article commenting is helpful in encouraging user engagement on online news platforms. However, the news documents are usually too long for models under traditional encoder-decoder frameworks, which often results in general and irrelevant comments. In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph. By organizing the article into graph structure, our model can better understand the internal structure of the article and the connection between topics, which makes it better able to generate coherent and informative comments. We collect and release a large scale news-comment corpus from a popular Chinese online news platform Tencent Kuaibao. Extensive experiment results show that our model can generate much more coherent and informative comments compared with several strong baseline models. |
| Tasks | Graph-to-Sequence |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1479/ |
| https://www.aclweb.org/anthology/P19-1479 | |
| PWC | https://paperswithcode.com/paper/coherent-comments-generation-for-chinese |
| Repo | |
| Framework | |
SANet: Scene Agnostic Network for Camera Localization
| Title | SANet: Scene Agnostic Network for Camera Localization |
| Authors | Luwei Yang, Ziqian Bai, Chengzhou Tang, Honghua Li, Yasutaka Furukawa, Ping Tan |
| Abstract | This paper presents a scene agnostic neural architecture for camera localization, where model parameters and scenes are independent from each other.Despite recent advancement in learning based methods, most approaches require training for each scene one by one, not applicable for online applications such as SLAM and robotic navigation, where a model must be built on-the-fly.Our approach learns to build a hierarchical scene representation and predicts a dense scene coordinate map of a query RGB image on-the-fly given an arbitrary scene. The 6D camera pose of the query image can be estimated with the predicted scene coordinate map. Additionally, the dense prediction can be used for other online robotic and AR applications such as obstacle avoidance. We demonstrate the effectiveness and efficiency of our method on both indoor and outdoor benchmarks, achieving state-of-the-art performance. |
| Tasks | Camera Localization |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yang_SANet_Scene_Agnostic_Network_for_Camera_Localization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_SANet_Scene_Agnostic_Network_for_Camera_Localization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sanet-scene-agnostic-network-for-camera |
| Repo | |
| Framework | |
The Cakewalk Method
| Title | The Cakewalk Method |
| Authors | Uri Patish, Shimon Ullman |
| Abstract | Combinatorial optimization is a common theme in computer science. While in general such problems are NP-Hard, from a practical point of view, locally optimal solutions can be useful. In some combinatorial problems however, it can be hard to define meaningful solution neighborhoods that connect large portions of the search space, thus hindering methods that search this space directly. We suggest to circumvent such cases by utilizing a policy gradient algorithm that transforms the problem to the continuous domain, and to optimize a new surrogate objective that renders the former as generic stochastic optimizer. This is achieved by producing a surrogate objective whose distribution is fixed and predetermined, thus removing the need to fine-tune various hyper-parameters in a case by case manner. Since we are interested in methods which can successfully recover locally optimal solutions, we use the problem of finding locally maximal cliques as a challenging experimental benchmark, and we report results on a large dataset of graphs that is designed to test clique finding algorithms. Notably, we show in this benchmark that fixing the distribution of the surrogate is key to consistently recovering locally optimal solutions, and that our surrogate objective leads to an algorithm that outperforms other methods we have tested in a number of measures. |
| Tasks | Combinatorial Optimization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Hkx-ii05FQ |
| https://openreview.net/pdf?id=Hkx-ii05FQ | |
| PWC | https://paperswithcode.com/paper/the-cakewalk-method |
| Repo | |
| Framework | |
Towards Practical Alternating Least-Squares for CCA
| Title | Towards Practical Alternating Least-Squares for CCA |
| Authors | Zhiqiang Xu, Ping Li |
| Abstract | Alternating least-squares (ALS) is a simple yet effective solver for canonical correlation analysis (CCA). In terms of ease of use, ALS is arguably practitioners’ first choice. Despite recent provably guaranteed variants, the empirical performance often remains unsatisfactory. To promote the practical use of ALS for CCA, we propose truly alternating least-squares. Instead of approximately solving two independent linear systems, in each iteration, it simply solves two coupled linear systems of half the size. It turns out that this coupling procedure is able to bring significant performance improvements in practice. Inspired by accelerated power method, we further propose faster alternating least-squares, where momentum terms are introduced into the update equations. Both algorithms enjoy linear convergence. To make faster ALS even more practical, we put forward adaptive alternating least-squares to avoid tuning the momentum parameter, which is as easy to use as the plain ALS while retaining advantages of the fast version. Experiments on several datasets empirically demonstrate the superiority of the proposed algorithms to recent variants. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9616-towards-practical-alternating-least-squares-for-cca |
| http://papers.nips.cc/paper/9616-towards-practical-alternating-least-squares-for-cca.pdf | |
| PWC | https://paperswithcode.com/paper/towards-practical-alternating-least-squares |
| Repo | |
| Framework | |
Tree-structured Decoding for Solving Math Word Problems
| Title | Tree-structured Decoding for Solving Math Word Problems |
| Authors | Qianying Liu, Wenyv Guan, Sujian Li, Daisuke Kawahara |
| Abstract | Automatically solving math word problems is an interesting research topic that needs to bridge natural language descriptions and formal math equations. Previous studies introduced end-to-end neural network methods, but these approaches did not efficiently consider an important characteristic of the equation, i.e., an abstract syntax tree. To address this problem, we propose a tree-structured decoding method that generates the abstract syntax tree of the equation in a top-down manner. In addition, our approach can automatically stop during decoding without a redundant stop token. The experimental results show that our method achieves single model state-of-the-art performance on Math23K, which is the largest dataset on this task. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1241/ |
| https://www.aclweb.org/anthology/D19-1241 | |
| PWC | https://paperswithcode.com/paper/tree-structured-decoding-for-solving-math |
| Repo | |
| Framework | |
Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network
| Title | Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network |
| Authors | Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu |
| Abstract | The lack of word boundaries information has been seen as one of the main obstacles to develop a high performance Chinese named entity recognition (NER) system. Fortunately, the automatically constructed lexicon contains rich word boundaries information and word semantic information. However, integrating lexical knowledge in Chinese NER tasks still faces challenges when it comes to self-matched lexical words as well as the nearest contextual lexical words. We present a Collaborative Graph Network to solve these challenges. Experiments on various datasets show that our model not only outperforms the state-of-the-art (SOTA) results, but also achieves a speed that is six to fifteen times faster than that of the SOTA model. |
| Tasks | Chinese Named Entity Recognition, Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1396/ |
| https://www.aclweb.org/anthology/D19-1396 | |
| PWC | https://paperswithcode.com/paper/leverage-lexical-knowledge-for-chinese-named |
| Repo | |
| Framework | |
Graph Attention Convolution for Point Cloud Semantic Segmentation
| Title | Graph Attention Convolution for Point Cloud Semantic Segmentation |
| Authors | Lei Wang, Yuchun Huang, Yaolin Hou, Shenman Zhang, Jie Shan |
| Abstract | Standard convolution is inherently limited for semantic segmentation of point cloud due to its isotropy about features. It neglects the structure of an object, results in poor object delineation and small spurious regions in the segmentation result. This paper proposes a novel graph attention convolution (GAC), whose kernels can be dynamically carved into specific shapes to adapt to the structure of an object. Specifically, by assigning proper attentional weights to different neighboring points, GAC is designed to selectively focus on the most relevant part of them according to their dynamically learned features. The shape of the convolution kernel is then determined by the learned distribution of the attentional weights. Though simple, GAC can capture the structured features of point clouds for fine-grained segmentation and avoid feature contamination between objects. Theoretically, we provided a thorough analysis on the expressive capabilities of GAC to show how it can learn about the features of point clouds. Empirically, we evaluated the proposed GAC on challenging indoor and outdoor datasets and achieved the state-of-the-art results in both scenarios. |
| Tasks | Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Graph_Attention_Convolution_for_Point_Cloud_Semantic_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Graph_Attention_Convolution_for_Point_Cloud_Semantic_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/graph-attention-convolution-for-point-cloud |
| Repo | |
| Framework | |
Attention-Aware Polarity Sensitive Embedding for Affective Image Retrieval
| Title | Attention-Aware Polarity Sensitive Embedding for Affective Image Retrieval |
| Authors | Xingxu Yao, Dongyu She, Sicheng Zhao, Jie Liang, Yu-Kun Lai, Jufeng Yang |
| Abstract | Images play a crucial role for people to express their opinions online due to the increasing popularity of social networks. While an affective image retrieval system is useful for obtaining visual contents with desired emotions from a massive repository, the abstract and subjective characteristics make the task challenging. To address the problem, this paper introduces an Attention-aware Polarity Sensitive Embedding (APSE) network to learn affective representations in an end-to-end manner. First, to automatically discover and model the informative regions of interest, we develop a hierarchical attention mechanism, in which both polarity- and emotion-specific attended representations are aggregated for discriminative feature embedding. Second, we present a weighted emotion-pair loss to take the inter- and intra-polarity relationships of the emotional labels into consideration. Guided by attention module, we weight the sample pairs adaptively which further improves the performance of feature embedding. Extensive experiments on four popular benchmark datasets show that the proposed method performs favorably against the state-of-the-art approaches. |
| Tasks | Image Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yao_Attention-Aware_Polarity_Sensitive_Embedding_for_Affective_Image_Retrieval_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Yao_Attention-Aware_Polarity_Sensitive_Embedding_for_Affective_Image_Retrieval_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/attention-aware-polarity-sensitive-embedding |
| Repo | |
| Framework | |
Benchmarking Hierarchical Script Knowledge
| Title | Benchmarking Hierarchical Script Knowledge |
| Authors | Yonatan Bisk, Jan Buys, Karl Pichotta, Yejin Choi |
| Abstract | Understanding procedural language requires reasoning about both hierarchical and temporal relations between events. For example, {}boiling pasta{''} is a sub-event of {}making a pasta dish{''}, typically happens before {``}draining pasta,{''} and requires the use of omitted tools (e.g. a strainer, sink…). While people are able to choose when and how to use abstract versus concrete instructions, the NLP community lacks corpora and tasks for evaluating if our models can do the same. In this paper, we introduce KidsCook, a parallel script corpus, as well as a cloze task which matches video captions with missing procedural details. Experimental results show that state-of-the-art models struggle at this task, which requires inducing functional commonsense knowledge not explicitly stated in text. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1412/ |
| https://www.aclweb.org/anthology/N19-1412 | |
| PWC | https://paperswithcode.com/paper/benchmarking-hierarchical-script-knowledge |
| Repo | |
| Framework | |
Detecting Chemical Reactions in Patents
| Title | Detecting Chemical Reactions in Patents |
| Authors | Hiyori Yoshikawa, Dat Quoc Nguyen, Zenan Zhai, Christian Druckenbrodt, Camilo Thorne, Saber A. Akhondi, Timothy Baldwin, Karin Verspoor |
| Abstract | Extracting chemical reactions from patents is a crucial task for chemists working on chemical exploration. In this paper we introduce the novel task of detecting the textual spans that describe or refer to chemical reactions within patents. We formulate this task as a paragraph-level sequence tagging problem, where the system is required to return a sequence of paragraphs which contain a description of a reaction. To address this new task, we construct an annotated dataset from an existing proprietary database of chemical reactions manually extracted from patents. We introduce several baseline methods for the task and evaluate them over our dataset. Through error analysis, we discuss what makes the task complex and challenging, and suggest possible directions for future research. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1014/ |
| https://www.aclweb.org/anthology/U19-1014 | |
| PWC | https://paperswithcode.com/paper/detecting-chemical-reactions-in-patents |
| Repo | |
| Framework | |
Deep Learning Techniques for Humor Detection in Hindi-English Code-Mixed Tweets
| Title | Deep Learning Techniques for Humor Detection in Hindi-English Code-Mixed Tweets |
| Authors | Sushmitha Reddy Sane, Suraj Tripathi, Koushik Reddy Sane, Radhika Mamidi |
| Abstract | We propose bilingual word embeddings based on word2vec and fastText models (CBOW and Skip-gram) to address the problem of Humor detection in Hindi-English code-mixed tweets in combination with deep learning architectures. We focus on deep learning approaches which are not widely used on code-mixed data and analyzed their performance by experimenting with three different neural network models. We propose convolution neural network (CNN) and bidirectional long-short term memory (biLSTM) (with and without Attention) models which take the generated bilingual embeddings as input. We make use of Twitter data to create bilingual word embeddings. All our proposed architectures outperform the state-of-the-art results, and Attention-based bidirectional LSTM model achieved an accuracy of 73.6{%} which is an increment of more than 4{%} compared to the current state-of-the-art results. |
| Tasks | Humor Detection, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1307/ |
| https://www.aclweb.org/anthology/W19-1307 | |
| PWC | https://paperswithcode.com/paper/deep-learning-techniques-for-humor-detection |
| Repo | |
| Framework | |
Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling
| Title | Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling |
| Authors | Ming Hou, Jiajia Tang, Jianhai Zhang, Wanzeng Kong, Qibin Zhao |
| Abstract | Tensor-based multimodal fusion techniques have exhibited great predictive performance. However, one limitation is that existing approaches only consider bilinear or trilinear pooling, which fails to unleash the complete expressive power of multilinear fusion with restricted orders of interactions. More importantly, simply fusing features all at once ignores the complex local intercorrelations, leading to the deterioration of prediction. In this work, we first propose a polynomial tensor pooling (PTP) block for integrating multimodal features by considering high-order moments, followed by a tensorized fully connected layer. Treating PTP as a building block, we further establish a hierarchical polynomial fusion network (HPFN) to recursively transmit local correlations into global ones. By stacking multiple PTPs, the expressivity capacity of HPFN enjoys an exponential growth w.r.t. the number of layers, which is shown by the equivalence to a very deep convolutional arithmetic circuits. Various experiments demonstrate that it can achieve the state-of-the-art performance. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9381-deep-multimodal-multilinear-fusion-with-high-order-polynomial-pooling |
| http://papers.nips.cc/paper/9381-deep-multimodal-multilinear-fusion-with-high-order-polynomial-pooling.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multimodal-multilinear-fusion-with-high |
| Repo | |
| Framework | |
Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing
| Title | Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing |
| Authors | Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya, Takuya Makino, Tomoya Iwakura |
| Abstract | We propose a method to improve named entity recognition (NER) for chemical compounds using multi-task learning by jointly training a chemical NER model and a chemical com- pound paraphrase model. Our method en- ables the long short-term memory (LSTM) of the NER model to capture chemical com- pound paraphrases by sharing the parameters of the LSTM and character embeddings be- tween the two models. The experimental re- sults on the BioCreative IV{'}s CHEMDNER task show that our method improves chemi- cal NER and achieves state-of-the-art perfor- mance. |
| Tasks | Multi-Task Learning, Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1648/ |
| https://www.aclweb.org/anthology/D19-1648 | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-chemical-named-entity |
| Repo | |
| Framework | |
Causes and Corrections for Bimodal Multi-Path Scanning With Structured Light
| Title | Causes and Corrections for Bimodal Multi-Path Scanning With Structured Light |
| Authors | Yu Zhang, Daniel L. Lau, Ying Yu |
| Abstract | Structured light illumination is an active 3D scanning technique based on projecting/capturing a set of striped patterns and measuring the warping of the patterns as they reflect off a target object’s surface. As designed, each pixel in the camera sees exactly one pixel from the projector; however, there are multi-path situations when the scanned surface has a complicated geometry with step edges and other discontinuities in depth or where the target surface has specularities that reflect light away from the camera. These situations are generally referred to multi-path where a camera pixel sees light from multiple projector positions. In the case of bimodal multi-path, the camera pixel receives light from exactly two positions which occurs along a step edge where the edge slices through a pixel so that the pixel sees both a foreground and background surface. In this paper, we present a general mathematical model to address the bimodal multi-path issue in a phase-measuring-profilometry scanner to measure the constructive and destructive interference between the two light paths, and by taking advantage of this interesting cue, separate the paths and make two decoupled phase measurements. We validate our algorithm with a number of challenging real-world scenarios, outperforming the state-of-the-art method. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Causes_and_Corrections_for_Bimodal_Multi-Path_Scanning_With_Structured_Light_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Causes_and_Corrections_for_Bimodal_Multi-Path_Scanning_With_Structured_Light_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/causes-and-corrections-for-bimodal-multi-path |
| Repo | |
| Framework | |
Parallel Sentence Retrieval From Comparable Corpora for Biomedical Text Simplification
| Title | Parallel Sentence Retrieval From Comparable Corpora for Biomedical Text Simplification |
| Authors | R{'e}mi Cardon, Natalia Grabar |
| Abstract | Parallel sentences provide semantically similar information which can vary on a given dimension, such as language or register. Parallel sentences with register variation (like expert and non-expert documents) can be exploited for the automatic text simplification. The aim of automatic text simplification is to better access and understand a given information. In the biomedical field, simplification may permit patients to understand medical and health texts. Yet, there is currently no such available resources. We propose to exploit comparable corpora which are distinguished by their registers (specialized and simplified versions) to detect and align parallel sentences. These corpora are in French and are related to the biomedical area. Manually created reference data show 0.76 inter-annotator agreement. Our purpose is to state whether a given pair of specialized and simplified sentences is parallel and can be aligned or not. We treat this task as binary classification (alignment/non-alignment). We perform experiments with a controlled ratio of imbalance and on the highly unbalanced real data. Our results show that the method we present here can be used to automatically generate a corpus of parallel sentences from our comparable corpus. |
| Tasks | Text Simplification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1020/ |
| https://www.aclweb.org/anthology/R19-1020 | |
| PWC | https://paperswithcode.com/paper/parallel-sentence-retrieval-from-comparable |
| Repo | |
| Framework | |
