Paper Group NANR 2
The E2E NLG Challenge: A Tale of Two Systems. Tensorize, Factorize and Regularize: Robust Visual Relationship Learning. Multi-source transformer with combined losses for automatic post editing. Translation Quality Metrics. Expanding Holographic Embeddings for Knowledge Completion. Czech Legal Text Treebank 2.0. Literal, Metphorical or Both? Detecti …
The E2E NLG Challenge: A Tale of Two Systems
| Title | The E2E NLG Challenge: A Tale of Two Systems |
| Authors | Charese Smiley, Elnaz Davoodi, Dezhao Song, Frank Schilder |
| Abstract | This paper presents the two systems we entered into the 2017 E2E NLG Challenge: TemplGen, a templated-based system and SeqGen, a neural network-based system. Through the automatic evaluation, SeqGen achieved competitive results compared to the template-based approach and to other participating systems as well. In addition to the automatic evaluation, in this paper we present and discuss the human evaluation results of our two systems. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6558/ |
| https://www.aclweb.org/anthology/W18-6558 | |
| PWC | https://paperswithcode.com/paper/the-e2e-nlg-challenge-a-tale-of-two-systems |
| Repo | |
| Framework | |
Tensorize, Factorize and Regularize: Robust Visual Relationship Learning
| Title | Tensorize, Factorize and Regularize: Robust Visual Relationship Learning |
| Authors | Seong Jae Hwang, Sathya N. Ravi, Zirui Tao, Hyunwoo J. Kim, Maxwell D. Collins, Vikas Singh |
| Abstract | Visual relationships provide higher-level information of objects and their relations in an image â this enables a semantic understanding of the scene and helps downstream applications. Given a set of localized objects in some training data, visual relationship detection seeks to detect the most likely ârelationshipâ between objects in a given image. While the specific objects may be well represented in training data, their relationships may still be infrequent. The empirical distribution obtained from seeing these relationships in a dataset does not model the underlying distribution well â a serious issue for most learning methods. In this work, we start from a simple multi-relational learning model, which in principle, offers a rich formalization for deriving a strong prior for learning visual relationships. While the inference problem for deriving the regularizer is challenging, our main technical contribution is to show how adapting recent results in numerical linear algebra lead to efficient algorithms for a factorization scheme that yields highly informative priors. The factorization provides sample size bounds for inference (under mild conditions) for the underlying [[object, predicate, object]] relationship learning task on its own and surprisingly outperforms (in some cases) existing methods even without utilizing visual features. Then, when integrated with an end to-end architecture for visual relationship detection leveraging image data, we substantially improve the state-of-the-art. |
| Tasks | Relational Reasoning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Hwang_Tensorize_Factorize_and_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Hwang_Tensorize_Factorize_and_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/tensorize-factorize-and-regularize-robust |
| Repo | |
| Framework | |
Multi-source transformer with combined losses for automatic post editing
| Title | Multi-source transformer with combined losses for automatic post editing |
| Authors | Amirhossein Tebbifakhr, Ruchit Agrawal, Matteo Negri, Marco Turchi |
| Abstract | Recent approaches to the Automatic Post-editing (APE) of Machine Translation (MT) have shown that best results are obtained by neural multi-source models that correct the raw MT output by also considering information from the corresponding source sentence. To this aim, we present for the first time a neural multi-source APE model based on the Transformer architecture. Moreover, we employ sequence-level loss functions in order to avoid exposure bias during training and to be consistent with the automatic evaluation metrics used for the task. These are the main features of our submissions to the WMT 2018 APE shared task, where we participated both in the PBSMT subtask (i.e. the correction of MT outputs from a phrase-based system) and in the NMT subtask (i.e. the correction of neural outputs). In the first subtask, our system improves over the baseline up to -5.3 TER and +8.23 BLEU points ranking second out of 11 submitted runs. In the second one, characterized by the higher quality of the initial translations, we report lower but statistically significant gains (up to -0.38 TER and +0.8 BLEU), ranking first out of 10 submissions. |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6471/ |
| https://www.aclweb.org/anthology/W18-6471 | |
| PWC | https://paperswithcode.com/paper/multi-source-transformer-with-combined-losses |
| Repo | |
| Framework | |
Translation Quality Metrics
| Title | Translation Quality Metrics |
| Authors | Arle Lommel |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2005/ |
| https://www.aclweb.org/anthology/W18-2005 | |
| PWC | https://paperswithcode.com/paper/translation-quality-metrics |
| Repo | |
| Framework | |
Expanding Holographic Embeddings for Knowledge Completion
| Title | Expanding Holographic Embeddings for Knowledge Completion |
| Authors | Yexiang Xue, Yang Yuan, Zhitian Xu, Ashish Sabharwal |
| Abstract | Neural models operating over structured spaces such as knowledge graphs require a continuous embedding of the discrete elements of this space (such as entities) as well as the relationships between them. Relational embeddings with high expressivity, however, have high model complexity, making them computationally difficult to train. We propose a new family of embeddings for knowledge graphs that interpolate between a method with high model complexity and one, namely Holographic embeddings (HolE), with low dimensionality and high training efficiency. This interpolation, termed HolEx, is achieved by concatenating several linearly perturbed copies of original HolE. We formally characterize the number of perturbed copies needed to provably recover the full entity-entity or entity-relation interaction matrix, leveraging ideas from Haar wavelets and compressed sensing. In practice, using just a handful of Haar-based or random perturbation vectors results in a much stronger knowledge completion system. On the Freebase FB15K dataset, HolEx outperforms originally reported HolE by 14.7% on the HITS@10 metric, and the current path-based state-of-the-art method, PTransE, by 4% (absolute). |
| Tasks | Knowledge Graphs |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7701-expanding-holographic-embeddings-for-knowledge-completion |
| http://papers.nips.cc/paper/7701-expanding-holographic-embeddings-for-knowledge-completion.pdf | |
| PWC | https://paperswithcode.com/paper/expanding-holographic-embeddings-for |
| Repo | |
| Framework | |
Czech Legal Text Treebank 2.0
| Title | Czech Legal Text Treebank 2.0 |
| Authors | Vincent Kr{'\i}{\v{z}}, Barbora Hladk{'a} |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1713/ |
| https://www.aclweb.org/anthology/L18-1713 | |
| PWC | https://paperswithcode.com/paper/czech-legal-text-treebank-20 |
| Repo | |
| Framework | |
Literal, Metphorical or Both? Detecting Metaphoricity in Isolated Adjective-Noun Phrases
| Title | Literal, Metphorical or Both? Detecting Metaphoricity in Isolated Adjective-Noun Phrases |
| Authors | Agnieszka Mykowiecka, Malgorzata Marciniak, Aleks Wawer, er |
| Abstract | The paper addresses the classification of isolated Polish adjective-noun phrases according to their metaphoricity. We tested neural networks to predict if a phrase has a literal or metaphorical sense or can have both senses depending on usage. The input to the neural network consists of word embeddings, but we also tested the impact of information about the domain of the adjective and about the abstractness of the noun. We applied our solution to English data available on the Internet and compared it to results published in papers. We found that the solution based on word embeddings only can achieve results comparable with complex solutions requiring additional information. |
| Tasks | Machine Translation, Natural Language Inference, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0904/ |
| https://www.aclweb.org/anthology/W18-0904 | |
| PWC | https://paperswithcode.com/paper/literal-metphorical-or-both-detecting |
| Repo | |
| Framework | |
MSMO: Multimodal Summarization with Multimodal Output
| Title | MSMO: Multimodal Summarization with Multimodal Output |
| Authors | Junnan Zhu, Haoran Li, Tianshang Liu, Yu Zhou, Jiajun Zhang, Chengqing Zong |
| Abstract | Multimodal summarization has drawn much attention due to the rapid growth of multimedia data. The output of the current multimodal summarization systems is usually represented in texts. However, we have found through experiments that multimodal output can significantly improve user satisfaction for informativeness of summaries. In this paper, we propose a novel task, multimodal summarization with multimodal output (MSMO). To handle this task, we first collect a large-scale dataset for MSMO research. We then propose a multimodal attention model to jointly generate text and select the most relevant image from the multimodal input. Finally, to evaluate multimodal outputs, we construct a novel multimodal automatic evaluation (MMAE) method which considers both intra-modality salience and inter-modality relevance. The experimental results show the effectiveness of MMAE. |
| Tasks | Text Summarization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1448/ |
| https://www.aclweb.org/anthology/D18-1448 | |
| PWC | https://paperswithcode.com/paper/msmo-multimodal-summarization-with-multimodal |
| Repo | |
| Framework | |
Monocular Relative Depth Perception With Web Stereo Data Supervision
| Title | Monocular Relative Depth Perception With Web Stereo Data Supervision |
| Authors | Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Yang Xiao, Ruibo Li, Zhenbo Luo |
| Abstract | In this paper we study the problem of monocular relative depth perception in the wild. We introduce a simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and propose a new dataset that consists of diverse images as well as corresponding dense relative depth maps. Further, an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs. Experimental results demonstrate that our proposed approach not only achieves state-of-the-art accuracy of relative depth perception in the wild, but also benefits other dense per-pixel prediction tasks, e.g., metric depth estimation and semantic segmentation. |
| Tasks | Depth Estimation, Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Xian_Monocular_Relative_Depth_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Xian_Monocular_Relative_Depth_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/monocular-relative-depth-perception-with-web |
| Repo | |
| Framework | |
Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study
| Title | Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study |
| Authors | Jianmin Zhang, Jiwei Tan, Xiaojun Wan |
| Abstract | Till now, neural abstractive summarization methods have achieved great success for single document summarization (SDS). However, due to the lack of large scale multi-document summaries, such methods can be hardly applied to multi-document summarization (MDS). In this paper, we investigate neural abstractive methods for MDS by adapting a state-of-the-art neural abstractive summarization model for SDS. We propose an approach to extend the neural abstractive model trained on large scale SDS data to the MDS task. Our approach only makes use of a small number of multi-document summaries for fine tuning. Experimental results on two benchmark DUC datasets demonstrate that our approach can outperform a variety of baseline neural models. |
| Tasks | Abstractive Text Summarization, Document Summarization, Machine Translation, Multi-Document Summarization, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6545/ |
| https://www.aclweb.org/anthology/W18-6545 | |
| PWC | https://paperswithcode.com/paper/adapting-neural-single-document-summarization |
| Repo | |
| Framework | |
Improving Neural Abstractive Document Summarization with Structural Regularization
| Title | Improving Neural Abstractive Document Summarization with Structural Regularization |
| Authors | Wei Li, Xinyan Xiao, Yajuan Lyu, Yuanzhuo Wang |
| Abstract | Recent neural sequence-to-sequence models have shown significant progress on short text summarization. However, for document summarization, they fail to capture the long-term structure of both documents and multi-sentence summaries, resulting in information loss and repetitions. In this paper, we propose to leverage the structural information of both documents and multi-sentence summaries to improve the document summarization performance. Specifically, we import both structural-compression and structural-coverage regularization into the summarization process in order to capture the information compression and information coverage properties, which are the two most important structural properties of document summarization. Experimental results demonstrate that the structural regularization improves the document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperforms state-of-the-art neural abstractive methods. |
| Tasks | Abstractive Sentence Summarization, Abstractive Text Summarization, Document Summarization, Machine Translation, Text Generation, Text Summarization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1441/ |
| https://www.aclweb.org/anthology/D18-1441 | |
| PWC | https://paperswithcode.com/paper/improving-neural-abstractive-document-1 |
| Repo | |
| Framework | |
Using Deep Reinforcement Learning to Generate Rationales for Molecules
| Title | Using Deep Reinforcement Learning to Generate Rationales for Molecules |
| Authors | Benson Chen, Connor Coley, Regina Barzilay, Tommi Jaakkola |
| Abstract | Deep learning algorithms are increasingly used in modeling chemical processes. However, black box predictions without rationales have limited used in practical applications, such as drug design. To this end, we learn to identify molecular substructures – rationales – that are associated with the target chemical property (e.g., toxicity). The rationales are learned in an unsupervised fashion, requiring no additional information beyond the end-to-end task. We formulate this problem as a reinforcement learning problem over the molecular graph, parametrized by two convolution networks corresponding to the rationale selection and prediction based on it, where the latter induces the reward function. We evaluate the approach on two benchmark toxicity datasets. We demonstrate that our model sustains high performance under the additional constraint that predictions strictly follow the rationales. Additionally, we validate the extracted rationales through comparison against those described in chemical literature and through synthetic experiments. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HkJ1rgbCb |
| https://openreview.net/pdf?id=HkJ1rgbCb | |
| PWC | https://paperswithcode.com/paper/using-deep-reinforcement-learning-to-generate |
| Repo | |
| Framework | |
Deep Semantic Correlation Learning Based Hashing for Multimedia Cross-Modal Retrieval
| Title | Deep Semantic Correlation Learning Based Hashing for Multimedia Cross-Modal Retrieval |
| Authors | 孝龙公 林鹏鹏 王富伟 |
| Abstract | 对于许多大规模多媒体数据集和Web内容，基于哈希策略进行跨模态检索的最近邻搜索方法由于其查询速度快，存储成本低而备受关注。大多数现有的散列方法试图以监督的方式将不同的模态映射到汉明嵌入，其中语义信息来自大的手动标签矩阵，并且不同模态中的每个样本通常由稀疏标签矢量编码。然而，先前的研究没有解决语义相关性学习挑战，并且无法充分利用先前的语义信息。因此，它们无法保持准确的语义相似性，往往会降低散列函数学习的性能。为了填补这个空白，我们首先提出了一种新的基于深度语义关联学习的哈希框架（DSCH），它在端到端的深度学习体系结构中生成统一哈希码，用于跨模态检索任务。这项工作的主要贡献是有效地自动构建数据表示之间的语义相关性，并演示如何利用相关信息为新样本生成哈希码。特别地，DSCH将潜在语义嵌入与统一散列嵌入相结合，以增强多个模态之间的相似性信息。此外，在我们的框架中采用了额外的图正则化，以捕获来自模态间和模内的对应关系。我们的模型同时学习语义相关性和统一哈希码，这增强了跨模态检索任务的有效性。实验结果表明，我们提出的方法对两个大型数据集上的几种最先进的交叉模态方法具有极高的准确性。 |
| Tasks | Cross-Modal Retrieval |
| Published | 2018-12-31 |
| URL | https://ieeexplore.ieee.org/document/8594836/references#references |
| https://ieeexplore.ieee.org/document/8594836/references#references | |
| PWC | https://paperswithcode.com/paper/deep-semantic-correlation-learning-based |
| Repo | |
| Framework | |
THU_NGN at SemEval-2018 Task 1: Fine-grained Tweet Sentiment Intensity Analysis with Attention CNN-LSTM
| Title | THU_NGN at SemEval-2018 Task 1: Fine-grained Tweet Sentiment Intensity Analysis with Attention CNN-LSTM |
| Authors | Chuhan Wu, Fangzhao Wu, Junxin Liu, Zhigang Yuan, Sixing Wu, Yongfeng Huang |
| Abstract | Traditional sentiment analysis approaches mainly focus on classifying the sentiment polarities or emotion categories of texts. However, they can{'}t exploit the sentiment intensity information. Therefore, the SemEval-2018 Task 1 is aimed to automatically determine the intensity of emotions or sentiment of tweets to mine fine-grained sentiment information. In order to address this task, we propose a system based on an attention CNN-LSTM model. In our model, LSTM is used to extract the long-term contextual information from texts. We apply attention techniques to selecting this information. A CNN layer with different size of kernels is used to extract local features. The dense layers take the pooled CNN feature maps and predict the intensity scores. Our system reaches average Pearson correlation score of 0.722 (ranked 12/48) in emotion intensity regression task, and 0.810 in valence regression task (ranked 15/38). It indicates that our system can be further extended. |
| Tasks | Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1028/ |
| https://www.aclweb.org/anthology/S18-1028 | |
| PWC | https://paperswithcode.com/paper/thu_ngn-at-semeval-2018-task-1-fine-grained |
| Repo | |
| Framework | |
On the difference between building and extracting patterns: a causal analysis of deep generative models.
| Title | On the difference between building and extracting patterns: a causal analysis of deep generative models. |
| Authors | Michel Besserve, Dominik Janzing, Bernhard Schoelkopf |
| Abstract | Generative models are important tools to capture and investigate the properties of complex empirical data. Recent developments such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) use two very similar, but \textit{reverse}, deep convolutional architectures, one to generate and one to extract information from data. Does learning the parameters of both architectures obey the same rules? We exploit the causality principle of independence of mechanisms to quantify how the weights of successive layers adapt to each other. Using the recently introduced Spectral Independence Criterion, we quantify the dependencies between the kernels of successive convolutional layers and show that those are more independent for the generative process than for information extraction, in line with results from the field of causal inference. In addition, our experiments on generation of human faces suggest that more independence between successive layers of generators results in improved performance of these architectures. |
| Tasks | Causal Inference |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SySisz-CW |
| https://openreview.net/pdf?id=SySisz-CW | |
| PWC | https://paperswithcode.com/paper/on-the-difference-between-building-and |
| Repo | |
| Framework | |
