Paper Group NANR 152
Deep Supervised Cross-Modal Retrieval. NEC TM Data Project. Best practices for the human evaluation of automatically generated text. Association Metrics in Neural Transition-Based Dependency Parsing. Corpus Lexicography in a Wider Context. Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains. Learning …
Deep Supervised Cross-Modal Retrieval
| Title | Deep Supervised Cross-Modal Retrieval |
| Authors | Liangli Zhen, Peng Hu, Xu Wang, Dezhong Peng |
| Abstract | Cross-modal retrieval aims to enable flexible retrieval across different modalities. The core of cross-modal retrieval is how to measure the content similarity between different types of data. In this paper, we present a novel cross-modal retrieval method, called Deep Supervised Cross-modal Retrieval (DSCMR). It aims to find a common representation space, in which the samples from different modalities can be compared directly. Specifically, DSCMR minimises the discrimination loss in both the label space and the common representation space to supervise the model learning discriminative features. Furthermore, it simultaneously minimises the modality invariance loss and uses a weight sharing strategy to eliminate the cross-modal discrepancy of multimedia data in the common representation space to learn modality-invariant features. Comprehensive experimental results on four widely-used benchmark datasets demonstrate that the proposed method is effective in cross-modal learning and significantly outperforms the state-of-the-art cross-modal retrieval methods. |
| Tasks | Cross-Modal Retrieval |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhen_Deep_Supervised_Cross-Modal_Retrieval_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhen_Deep_Supervised_Cross-Modal_Retrieval_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-supervised-cross-modal-retrieval |
| Repo | |
| Framework | |
NEC TM Data Project
| Title | NEC TM Data Project |
| Authors | Alex Helle, re, Manuel Herranz |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6716/ |
| https://www.aclweb.org/anthology/W19-6716 | |
| PWC | https://paperswithcode.com/paper/nec-tm-data-project |
| Repo | |
| Framework | |
Best practices for the human evaluation of automatically generated text
| Title | Best practices for the human evaluation of automatically generated text |
| Authors | Chris van der Lee, Albert Gatt, Emiel van Miltenburg, S Wubben, er, Emiel Krahmer |
| Abstract | Currently, there is little agreement as to how Natural Language Generation (NLG) systems should be evaluated. While there is some agreement regarding automatic metrics, there is a high degree of variation in the way that human evaluation is carried out. This paper provides an overview of how human evaluation is currently conducted, and presents a set of best practices, grounded in the literature. With this paper, we hope to contribute to the quality and consistency of human evaluations in NLG. |
| Tasks | Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8643/ |
| https://www.aclweb.org/anthology/W19-8643 | |
| PWC | https://paperswithcode.com/paper/best-practices-for-the-human-evaluation-of |
| Repo | |
| Framework | |
Association Metrics in Neural Transition-Based Dependency Parsing
| Title | Association Metrics in Neural Transition-Based Dependency Parsing |
| Authors | Patricia Fischer, Sebastian P{"u}tz, Dani{"e}l de Kok |
| Abstract | |
| Tasks | Dependency Parsing, Transition-Based Dependency Parsing |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7722/ |
| https://www.aclweb.org/anthology/W19-7722 | |
| PWC | https://paperswithcode.com/paper/association-metrics-in-neural-transition |
| Repo | |
| Framework | |
Corpus Lexicography in a Wider Context
| Title | Corpus Lexicography in a Wider Context |
| Authors | Chen Gafni |
| Abstract | This paper describes a set of tools that offers comprehensive solutions for corpus lexicography. The tools perform a range of tasks, including construction of corpus lexicon, integrating information from external dictionaries, internal analysis of the lexicon, and lexical analysis of the corpus. The set of tools is particularly useful for creating dictionaries for under-resourced languages. The tools are integrated in a general-purpose software that includes additional tools for various research tasks, such as linguistic development analysis. Equipped with a user-friendly interface, the described system can be easily incorporated in research in a variety of fields. |
| Tasks | Lexical Analysis |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1041/ |
| https://www.aclweb.org/anthology/R19-1041 | |
| PWC | https://paperswithcode.com/paper/corpus-lexicography-in-a-wider-context |
| Repo | |
| Framework | |
Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains
| Title | Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains |
| Authors | Wei Shi, Vera Demberg |
| Abstract | Implicit discourse relation classification is one of the most difficult tasks in discourse parsing. Previous studies have generally focused on extracting better representations of the relational arguments. In order to solve the task, it is however additionally necessary to capture what events are expected to cause or follow each other. Current discourse relation classifiers fall short in this respect. We here show that this shortcoming can be effectively addressed by using the bidirectional encoder representation from transformers (BERT) proposed by Devlin et al. (2019), which were trained on a next-sentence prediction task, and thus encode a representation of likely next sentences. The BERT-based model outperforms the current state of the art in 11-way classification by 8{%} points on the standard PDTB dataset. Our experiments also demonstrate that the model can be successfully ported to other domains: on the BioDRB dataset, the model outperforms the state of the art system around 15{%} points. |
| Tasks | Implicit Discourse Relation Classification, Relation Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1586/ |
| https://www.aclweb.org/anthology/D19-1586 | |
| PWC | https://paperswithcode.com/paper/next-sentence-prediction-helps-implicit |
| Repo | |
| Framework | |
Learning to Search Efficient DenseNet with Layer-wise Pruning
| Title | Learning to Search Efficient DenseNet with Layer-wise Pruning |
| Authors | Xuanyang Zhang, Hao liu, Zhanxing Zhu, Zenglin Xu |
| Abstract | Deep neural networks have achieved outstanding performance in many real-world applications with the expense of huge computational resources. The DenseNet, one of the recently proposed neural network architecture, has achieved the state-of-the-art performance in many visual tasks. However, it has great redundancy due to the dense connections of the internal structure, which leads to high computational costs in training such dense networks. To address this issue, we design a reinforcement learning framework to search for efficient DenseNet architectures with layer-wise pruning (LWP) for different tasks, while retaining the original advantages of DenseNet, such as feature reuse, short paths, etc. In this framework, an agent evaluates the importance of each connection between any two block layers, and prunes the redundant connections. In addition, a novel reward-shaping trick is introduced to make DenseNet reach a better trade-off between accuracy and float point operations (FLOPs). Our experiments show that DenseNet with LWP is more compact and efficient than existing alternatives. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1fWmnR5tm |
| https://openreview.net/pdf?id=r1fWmnR5tm | |
| PWC | https://paperswithcode.com/paper/learning-to-search-efficient-densenet-with |
| Repo | |
| Framework | |
Generative model based on minimizing exact empirical Wasserstein distance
| Title | Generative model based on minimizing exact empirical Wasserstein distance |
| Authors | Akihiro Iohara, Takahito Ogawa, Toshiyuki Tanaka |
| Abstract | Generative Adversarial Networks (GANs) are a very powerful framework for generative modeling. However, they are often hard to train, and learning of GANs often becomes unstable. Wasserstein GAN (WGAN) is a promising framework to deal with the instability problem as it has a good convergence property. One drawback of the WGAN is that it evaluates the Wasserstein distance in the dual domain, which requires some approximation, so that it may fail to optimize the true Wasserstein distance. In this paper, we propose evaluating the exact empirical optimal transport cost efficiently in the primal domain and performing gradient descent with respect to its derivative to train the generator network. Experiments on the MNIST dataset show that our method is significantly stable to converge, and achieves the lowest Wasserstein distance among the WGAN variants at the cost of some sharpness of generated images. Experiments on the 8-Gaussian toy dataset show that better gradients for the generator are obtained in our method. In addition, the proposed method enables more flexible generative modeling than WGAN. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJgTZ3C5FX |
| https://openreview.net/pdf?id=BJgTZ3C5FX | |
| PWC | https://paperswithcode.com/paper/generative-model-based-on-minimizing-exact |
| Repo | |
| Framework | |
Explicit Recall for Efficient Exploration
| Title | Explicit Recall for Efficient Exploration |
| Authors | Honghua Dong, Jiayuan Mao, Xinyue Cui, Lihong Li |
| Abstract | In this paper, we advocate the use of explicit memory for efficient exploration in reinforcement learning. This memory records structured trajectories that have led to interesting states in the past, and can be used by the agent to revisit those states more effectively. In high-dimensional decision making problems, where deep reinforcement learning is considered crucial, our approach provides a simple, transparent and effective way that can be naturally combined with complex, deep learning models. We show how such explicit memory may be used to enhance existing exploration algorithms such as intrinsically motivated ones and count-based ones, and demonstrate our method’s advantages in various simulated environments. |
| Tasks | Decision Making, Efficient Exploration |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1GIB3A9YX |
| https://openreview.net/pdf?id=B1GIB3A9YX | |
| PWC | https://paperswithcode.com/paper/explicit-recall-for-efficient-exploration |
| Repo | |
| Framework | |
Holographic and other Point Set Distances for Machine Learning
| Title | Holographic and other Point Set Distances for Machine Learning |
| Authors | Lukas Balles, Thomas Fischbacher |
| Abstract | We introduce an analytic distance function for moderately sized point sets of known cardinality that is shown to have very desirable properties, both as a loss function as well as a regularizer for machine learning applications. We compare our novel construction to other point set distance functions and show proof of concept experiments for training neural networks end-to-end on point set prediction tasks such as object detection. |
| Tasks | Object Detection |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJlpUiAcYX |
| https://openreview.net/pdf?id=rJlpUiAcYX | |
| PWC | https://paperswithcode.com/paper/holographic-and-other-point-set-distances-for |
| Repo | |
| Framework | |
Probabilistic Deep Ordinal Regression Based on Gaussian Processes
| Title | Probabilistic Deep Ordinal Regression Based on Gaussian Processes |
| Authors | Yanzhu Liu, Fan Wang, Adams Wai Kin Kong |
| Abstract | With excellent representation power for complex data, deep neural networks (DNNs) based approaches are state-of-the-art for ordinal regression problem which aims to classify instances into ordinal categories. However, DNNs are not able to capture uncertainties and produce probabilistic interpretations. As a probabilistic model, Gaussian Processes (GPs) on the other hand offers uncertainty information, which is nonetheless lack of scalability for large datasets. This paper adapts traditional GPs regression for ordinal regression problem by using both conjugate and non-conjugate ordinal likelihood. Based on that, it proposes a deep neural network with a GPs layer on the top, which is trained end-to-end by the stochastic gradient descent method for both neural network parameters and GPs parameters. The parameters in the ordinal likelihood function are learned as neural network parameters so that the proposed framework is able to produce fitted likelihood functions for training sets and make probabilistic predictions for test points. Experimental results on three real-world benchmarks – image aesthetics rating, historical image grading and age group estimation – demonstrate that in terms of mean absolute error, the proposed approach outperforms state-of-the-art ordinal regression approaches and provides the confidence for predictions. |
| Tasks | Gaussian Processes |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Probabilistic_Deep_Ordinal_Regression_Based_on_Gaussian_Processes_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Probabilistic_Deep_Ordinal_Regression_Based_on_Gaussian_Processes_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-deep-ordinal-regression-based |
| Repo | |
| Framework | |
Diverse Generation for Multi-Agent Sports Games
| Title | Diverse Generation for Multi-Agent Sports Games |
| Authors | Raymond A. Yeh, Alexander G. Schwing, Jonathan Huang, Kevin Murphy |
| Abstract | In this paper, we propose a new generative model for multi-agent trajectory data, focusing on the case of multi-player sports games. Our model leverages graph neural networks (GNNs) and variational recurrent neural networks (VRNNs) to achieve a permutation equivariant model suitable for sports. On two challenging datasets (basketball and soccer), we show that we are able to produce more accurate forecasts than previous methods. We assess accuracy using various metrics, such as log-likelihood and “best of N” loss, based on N different samples of the future. We also measure the distribution of statistics of interest, such as player location or velocity, and show that the distribution induced by our generative model better matches the empirical distribution of the test set. Finally, we show that our model can perform conditional prediction, which lets us answer counterfactual questions such as “how will the players move differently if A passes the ball to B instead of C?” |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yeh_Diverse_Generation_for_Multi-Agent_Sports_Games_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Yeh_Diverse_Generation_for_Multi-Agent_Sports_Games_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/diverse-generation-for-multi-agent-sports |
| Repo | |
| Framework | |
Self-Critical Attention Learning for Person Re-Identification
| Title | Self-Critical Attention Learning for Person Re-Identification |
| Authors | Guangyi Chen, Chunze Lin, Liangliang Ren, Jiwen Lu, Jie Zhou |
| Abstract | In this paper, we propose a self-critical attention learning method for person re-identification. Unlike most existing methods which train the attention mechanism in a weakly-supervised manner and ignore the attention confidence level, we learn the attention with a critic which measures the attention quality and provides a powerful supervisory signal to guide the learning process. Moreover, the critic model facilitates the interpretation of the effectiveness of the attention mechanism during the learning process, by estimating the quality of the attention maps. Specifically, we jointly train our attention agent and critic in a reinforcement learning manner, where the agent produces the visual attention while the critic analyzes the gain from the attention and guides the agent to maximize this gain. We design spatial- and channel-wise attention models with our critic module and evaluate them on three popular benchmarks including Market-1501, DukeMTMC-ReID, and CUHK03. The experimental results demonstrate the superiority of our method, which outperforms the state-of-the-art methods by a large margin of 5.9%/2.1%, 6.3%/3.0%, and 10.5%/9.5% on mAP/Rank-1, respectively. |
| Tasks | Person Re-Identification |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Self-Critical_Attention_Learning_for_Person_Re-Identification_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Self-Critical_Attention_Learning_for_Person_Re-Identification_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/self-critical-attention-learning-for-person |
| Repo | |
| Framework | |
Investigating Machine Learning Methods for Language and Dialect Identification of Cuneiform Texts
| Title | Investigating Machine Learning Methods for Language and Dialect Identification of Cuneiform Texts |
| Authors | Ehsan Doostmohammadi, Minoo Nassajian |
| Abstract | Identification of the languages written using cuneiform symbols is a difficult task due to the lack of resources and the problem of tokenization. The Cuneiform Language Identification task in VarDial 2019 addresses the problem of identifying seven languages and dialects written in cuneiform; Sumerian and six dialects of Akkadian language: Old Babylonian, Middle Babylonian Peripheral, Standard Babylonian, Neo-Babylonian, Late Babylonian, and Neo-Assyrian. This paper describes the approaches taken by SharifCL team to this problem in VarDial 2019. The best result belongs to an ensemble of Support Vector Machines and a naive Bayes classifier, both working on character-level features, with macro-averaged F1-score of 72.10{%}. |
| Tasks | Language Identification, Tokenization |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1420/ |
| https://www.aclweb.org/anthology/W19-1420 | |
| PWC | https://paperswithcode.com/paper/investigating-machine-learning-methods-for |
| Repo | |
| Framework | |
A k-Nearest Neighbor Approach towards Multi-level Sequence Labeling
| Title | A k-Nearest Neighbor Approach towards Multi-level Sequence Labeling |
| Authors | Yue Chen, John Chen |
| Abstract | In this paper we present a new method for intent recognition for complex dialog management in low resource situations. Complex dialog management is required because our target domain is real world mixed initiative food ordering between agents and their customers, where individual customer utterances may contain multiple intents and refer to food items with complex structure. For example, a customer might say {``}Can I get a deluxe burger with large fries and oh put extra mayo on the burger would you?{''} We approach this task as a multi-level sequence labeling problem, with the constraint of limited real training data. Both traditional methods like HMM, MEMM, or CRF and newer methods like DNN or BiLSTM use only homogeneous feature sets. Newer methods perform better but also require considerably more data. Previous research has done pseudo-data synthesis to obtain the required amounts of training data. We propose to use a k-NN learner with heterogeneous feature set. We used windowed word n-grams, POS tag n-grams and pre-trained word embeddings as features. For the experiments we perform a comparison between using pseudo-data and real world data. We also perform semi-supervised self-training to obtain additional labeled data, in order to better model real world scenarios. Instead of using massive pseudo-data, we show that with only less than 1{%} of the data size, we can achieve better result than any of the methods above by annotating real world data. We achieve labeled bracketed F-scores of 75.46, 52.84 and 49.66 for the three levels of sequence labeling where each level has a longer word span than its previous level. Overall we achieve 60.71F. In comparison, two previous systems, MEMM and DNN-ELMO, achieved 52.32 and 45.25 respectively. | |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2019/ |
| https://www.aclweb.org/anthology/N19-2019 | |
| PWC | https://paperswithcode.com/paper/a-k-nearest-neighbor-approach-towards-multi |
| Repo | |
| Framework | |
