Paper Group NANR 181
The BEA-2019 Shared Task on Grammatical Error Correction. Sanskrit Sentence Generator. Collaborative Spatiotemporal Feature Learning for Video Action Recognition. Ranking Passages for Argument Convincingness. Predicting Visible Image Differences Under Varying Display Brightness and Viewing Distance. Variational Domain Adaptation. Multiple News Head …
The BEA-2019 Shared Task on Grammatical Error Correction
| Title | The BEA-2019 Shared Task on Grammatical Error Correction |
| Authors | Christopher Bryant, Mariano Felice, {\O}istein E. Andersen, Ted Briscoe |
| Abstract | This paper reports on the BEA-2019 Shared Task on Grammatical Error Correction (GEC). As with the CoNLL-2014 shared task, participants are required to correct all types of errors in test data. One of the main contributions of the BEA-2019 shared task is the introduction of a new dataset, the Write{&}Improve+LOCNESS corpus, which represents a wider range of native and learner English levels and abilities. Another contribution is the introduction of tracks, which control the amount of annotated data available to participants. Systems are evaluated in terms of ERRANT F{_}0.5, which allows us to report a much wider range of performance statistics. The competition was hosted on Codalab and remains open for further submissions on the blind test set. |
| Tasks | Grammatical Error Correction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4406/ |
| https://www.aclweb.org/anthology/W19-4406 | |
| PWC | https://paperswithcode.com/paper/the-bea-2019-shared-task-on-grammatical-error |
| Repo | |
| Framework | |
Sanskrit Sentence Generator
| Title | Sanskrit Sentence Generator |
| Authors | Amba Kulkarni, Madhusoodana Pai |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-7501/ |
| https://www.aclweb.org/anthology/W19-7501 | |
| PWC | https://paperswithcode.com/paper/sanskrit-sentence-generator |
| Repo | |
| Framework | |
Collaborative Spatiotemporal Feature Learning for Video Action Recognition
| Title | Collaborative Spatiotemporal Feature Learning for Video Action Recognition |
| Authors | Chao Li, Qiaoyong Zhong, Di Xie, Shiliang Pu |
| Abstract | Spatiotemporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D). In this paper, we propose a novel neural operation which encodes spatiotemporal features collaboratively by imposing a weight-sharing constraint on the learnable parameters. In particular, we perform 2D convolution along three orthogonal views of volumetric video data, which learns spatial appearance and temporal motion cues respectively. By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other. The complementary features are subsequently fused by a weighted summation whose coefficients are learned end-to-end. Our approach achieves state-of-the-art performance on large-scale benchmarks and won the 1st place in the Moments in Time Challenge 2018. Moreover, based on the learned coefficients of different views, we are able to quantify the contributions of spatial and temporal features. This analysis sheds light on interpretability of the model and may also guide the future design of algorithm for video recognition. |
| Tasks | Action Classification, Action Recognition In Videos, Temporal Action Localization, Video Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Collaborative_Spatiotemporal_Feature_Learning_for_Video_Action_Recognition_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Collaborative_Spatiotemporal_Feature_Learning_for_Video_Action_Recognition_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-spatiotemporal-feature-learning |
| Repo | |
| Framework | |
Ranking Passages for Argument Convincingness
| Title | Ranking Passages for Argument Convincingness |
| Authors | Peter Potash, Adam Ferguson, Timothy J. Hazen |
| Abstract | In data ranking applications, pairwise annotation is often more consistent than cardinal annotation for learning ranking models. We examine this in a case study on ranking text passages for argument convincingness. Our task is to choose text passages that provide the highest-quality, most-convincing arguments for opposing sides of a topic. Using data from a deployed system within the Bing search engine, we construct a pairwise-labeled dataset for argument convincingness that is substantially more comprehensive in topical coverage compared to existing public resources. We detail the process of extracting topical passages for queries submitted to a search engine, creating annotated sets of passages aligned to different stances on a topic, and assessing argument convincingness of passages using pairwise annotation. Using a state-of-the-art convincingness model, we evaluate several methods for using pairwise-annotated data examples to train models for ranking passages. Our results show pairwise training outperforms training that regresses to a target score for each passage. Our results also show a simple {`}win-rate{'} score is a better regression target than the previously proposed page-rank target. Lastly, addressing the need to filter noisy crowd-sourced annotations when constructing a dataset, we show that filtering for transitivity within pairwise annotations is more effective than filtering based on annotation confidence measures for individual examples. | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4517/ |
| https://www.aclweb.org/anthology/W19-4517 | |
| PWC | https://paperswithcode.com/paper/ranking-passages-for-argument-convincingness |
| Repo | |
| Framework | |
Predicting Visible Image Differences Under Varying Display Brightness and Viewing Distance
| Title | Predicting Visible Image Differences Under Varying Display Brightness and Viewing Distance |
| Authors | Nanyang Ye, Krzysztof Wolski, Rafal K. Mantiuk |
| Abstract | Numerous applications require a robust metric that can predict whether image differences are visible or not. However, the accuracy of existing white-box visibility metrics, such as HDR-VDP, is often not good enough. CNN-based black-box visibility metrics have proven to be more accurate, but they cannot account for differences in viewing conditions, such as display brightness and viewing distance. In this paper, we propose a CNN-based visibility metric, which maintains the accuracy of deep network solutions and accounts for viewing conditions. To achieve this, we extend the existing dataset of locally visible differences (LocVis) with a new set of measurements, collected considering aforementioned viewing conditions. Then, we develop a hybrid model that combines white-box processing stages for modeling the effects of luminance masking and contrast sensitivity, with a black-box deep neural network. We demonstrate that the novel hybrid model can handle the change of viewing conditions correctly and outperforms state-of-the-art metrics. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Ye_Predicting_Visible_Image_Differences_Under_Varying_Display_Brightness_and_Viewing_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Ye_Predicting_Visible_Image_Differences_Under_Varying_Display_Brightness_and_Viewing_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-visible-image-differences-under |
| Repo | |
| Framework | |
Variational Domain Adaptation
| Title | Variational Domain Adaptation |
| Authors | Hirono Okamoto, Shohei Ohsawa, Itto Higuchi, Haruka Murakami, Mizuki Sango, Zhenghang Cui, Masahiro Suzuki, Hiroshi Kajino, Yutaka Matsuo |
| Abstract | This paper proposes variational domain adaptation, a unified, scalable, simple framework for learning multiple distributions through variational inference. Unlike the existing methods on domain transfer through deep generative models, such as StarGAN (Choi et al., 2017) and UFDN (Liu et al., 2018), the variational domain adaptation has three advantages. Firstly, the samples from the target are not required. Instead, the framework requires one known source as a prior $p(x)$ and binary discriminators, $p(\mathcal{D}_ix)$, discriminating the target domain $\mathcal{D}_i$ from others. Consequently, the framework regards a target as a posterior that can be explicitly formulated through the Bayesian inference, $p(x\mathcal{D}_i) \propto p(\mathcal{D}_ix)p(x)$, as exhibited by a further proposed model of dual variational autoencoder (DualVAE). Secondly, the framework is scablable to large-scale domains. As well as VAE encodes a sample $x$ as a mode on a latent space: $\mu(x) \in \mathcal{Z}$, DualVAE encodes a domain $\mathcal{D}_i$ as a mode on the dual latent space $\mu^*(\mathcal{D}_i) \in \mathcal{Z}^*$, named domain embedding. It reformulates the posterior with a natural paring $\langle, \rangle: \mathcal{Z} \times \mathcal{Z}^* \rightarrow \Real$, which can be expanded to uncountable infinite domains such as continuous domains as well as interpolation. Thirdly, DualVAE fastly converges without sophisticated automatic/manual hyperparameter search in comparison to GANs as it requires only one additional parameter to VAE. Through the numerical experiment, we demonstrate the three benefits with multi-domain image generation task on CelebA with up to 60 domains, and exhibits that DualVAE records the state-of-the-art performance outperforming StarGAN and UFDN. |
| Tasks | Bayesian Inference, Domain Adaptation, Image Generation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ByeLmn0qtX |
| https://openreview.net/pdf?id=ByeLmn0qtX | |
| PWC | https://paperswithcode.com/paper/variational-domain-adaptation |
| Repo | |
| Framework | |
Multiple News Headlines Generation using Page Metadata
| Title | Multiple News Headlines Generation using Page Metadata |
| Authors | Kango Iwama, Yoshinobu Kano |
| Abstract | Multiple headlines of a newspaper article have an important role to express the content of the article accurately and concisely. A headline depends on the content and intent of their article. While a single headline expresses the whole corresponding article, each of multiple headlines expresses different information individually. We suggest automatic generation method of such a diverse multiple headlines in a newspaper. Our generation method is based on the Pointer-Generator Network, using page metadata on a newspaper which can change headline generation behavior. This page metadata includes headline location, headline size, article page number, etc. In a previous related work, ensemble of three different generation models was performed to obtain a single headline, where each generation model generates a single headline candidate. In contrast, we use a single model to generate multiple headlines. We conducted automatic evaluations for generated headlines. The results show that our method improved ROUGE-1 score by 4.32 points higher than baseline. These results suggest that our model using page metadata can generate various multiple headlines for an article In better performance. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8612/ |
| https://www.aclweb.org/anthology/W19-8612 | |
| PWC | https://paperswithcode.com/paper/multiple-news-headlines-generation-using-page |
| Repo | |
| Framework | |
Neural Speech Translation using Lattice Transformations and Graph Networks
| Title | Neural Speech Translation using Lattice Transformations and Graph Networks |
| Authors | Daniel Beck, Trevor Cohn, Gholamreza Haffari |
| Abstract | Speech translation systems usually follow a pipeline approach, using word lattices as an intermediate representation. However, previous work assume access to the original transcriptions used to train the ASR system, which can limit applicability in real scenarios. In this work we propose an approach for speech translation through lattice transformations and neural models based on graph networks. Experimental results show that our approach reaches competitive performance without relying on transcriptions, while also being orders of magnitude faster than previous work. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5304/ |
| https://www.aclweb.org/anthology/D19-5304 | |
| PWC | https://paperswithcode.com/paper/neural-speech-translation-using-lattice |
| Repo | |
| Framework | |
Attempting to separate inflection and derivation using vector space representations
| Title | Attempting to separate inflection and derivation using vector space representations |
| Authors | Rudolf Rosa, Zden{\v{e}}k {\v{Z}}abokrtsk{'y} |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8508/ |
| https://www.aclweb.org/anthology/W19-8508 | |
| PWC | https://paperswithcode.com/paper/attempting-to-separate-inflection-and |
| Repo | |
| Framework | |
A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing
| Title | A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing |
| Authors | Zeyu Dai, Ruihong Huang |
| Abstract | We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing. Realizing that external knowledge and linguistic constraints may not always apply in understanding a particular context, we propose a regularization approach that tightly integrates these constraints with contexts for deriving word representations. Meanwhile, it balances attentions over contexts and constraints through adding a regularization term into the objective function. Experiments show that our knowledge regularization approach outperforms all previous systems on the benchmark dataset PDTB for discourse parsing. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1295/ |
| https://www.aclweb.org/anthology/D19-1295 | |
| PWC | https://paperswithcode.com/paper/a-regularization-approach-for-incorporating |
| Repo | |
| Framework | |
Building a Morphological Network for Persian on Top of a Morpheme-Segmented Lexicon
| Title | Building a Morphological Network for Persian on Top of a Morpheme-Segmented Lexicon |
| Authors | Hamid Haghdoost, Ebrahim Ansari, Zden{\v{e}}k {\v{Z}}abokrtsk{'y}, Mahshid Nikravesh |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8511/ |
| https://www.aclweb.org/anthology/W19-8511 | |
| PWC | https://paperswithcode.com/paper/building-a-morphological-network-for-persian |
| Repo | |
| Framework | |
Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling
| Title | Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling |
| Authors | Bo-Hsiang Tseng, Marek Rei, Pawe{\l} Budzianowski, Richard Turner, Bill Byrne, Anna Korhonen |
| Abstract | Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels. However, collecting these annotations is expensive and time-consuming, holding back development in the area of dialogue modelling. In this paper, we investigate semi-supervised learning methods that are able to reduce the amount of required intermediate labelling. We find that by leveraging un-annotated data instead, the amount of turn-level annotations of dialogue state can be significantly reduced when building a neural dialogue system. Our analysis on the MultiWOZ corpus, covering a range of domains and topics, finds that annotations can be reduced by up to 30{%} while maintaining equivalent system performance. We also describe and evaluate the first end-to-end dialogue model created for the MultiWOZ corpus. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1125/ |
| https://www.aclweb.org/anthology/D19-1125 | |
| PWC | https://paperswithcode.com/paper/semi-supervised-bootstrapping-of-dialogue |
| Repo | |
| Framework | |
Machine Translation With Weakly Paired Bilingual Documents
| Title | Machine Translation With Weakly Paired Bilingual Documents |
| Authors | Lijun Wu, Jinhua Zhu, Di He, Fei Gao, Xu Tan, Tao Qin, Tie-Yan Liu |
| Abstract | Neural machine translation, which achieves near human-level performance in some languages, strongly relies on the availability of large amounts of parallel sentences, which hinders its applicability to low-resource language pairs. Recent works explore the possibility of unsupervised machine translation with monolingual data only, leading to much lower accuracy compared with the supervised one. Observing that weakly paired bilingual documents are much easier to collect than bilingual sentences, e.g., from Wikipedia, news websites or books, in this paper, we investigate the training of translation models with weakly paired bilingual documents. Our approach contains two components/steps. First, we provide a simple approach to mine implicitly bilingual sentence pairs from document pairs which can then be used as supervised signals for training. Second, we leverage the topic consistency of two weakly paired documents and learn the sentence-to-sentence translation by constraining the word distribution-level alignments. We evaluate our proposed method on weakly paired documents from Wikipedia on four tasks, the widely used WMT16 German$\leftrightarrow$English and WMT13 Spanish$\leftrightarrow$English tasks, and obtain $24.1$/$30.3$ and $28.0$/$27.6$ BLEU points separately, outperforming state-of-the-art unsupervised results by more than 5 BLEU points and reducing the gap between unsupervised translation and supervised translation up to 50%. |
| Tasks | Machine Translation, Unsupervised Machine Translation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryza73R9tQ |
| https://openreview.net/pdf?id=ryza73R9tQ | |
| PWC | https://paperswithcode.com/paper/machine-translation-with-weakly-paired |
| Repo | |
| Framework | |
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
| Title | PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees |
| Authors | Jinsung Yoon, James Jordon, Mihaela van der Schaar |
| Abstract | Machine learning has the potential to assist many communities in using the large datasets that are becoming more and more available. Unfortunately, much of that potential is not being realized because it would require sharing data in a way that compromises privacy. In this paper, we investigate a method for ensuring (differential) privacy of the generator of the Generative Adversarial Nets (GAN) framework. The resulting model can be used for generating synthetic data on which algorithms can be trained and validated, and on which competitions can be conducted, without compromising the privacy of the original dataset. Our method modifies the Private Aggregation of Teacher Ensembles (PATE) framework and applies it to GANs. Our modified framework (which we call PATE-GAN) allows us to tightly bound the influence of any individual sample on the model, resulting in tight differential privacy guarantees and thus an improved performance over models with the same guarantees. We also look at measuring the quality of synthetic data from a new angle; we assert that for the synthetic data to be useful for machine learning researchers, the relative performance of two algorithms (trained and tested) on the synthetic dataset should be the same as their relative performance (when trained and tested) on the original dataset. Our experiments, on various datasets, demonstrate that PATE-GAN consistently outperforms the state-of-the-art method with respect to this and other notions of synthetic data quality. |
| Tasks | Synthetic Data Generation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1zk9iRqF7 |
| https://openreview.net/pdf?id=S1zk9iRqF7 | |
| PWC | https://paperswithcode.com/paper/pate-gan-generating-synthetic-data-with |
| Repo | |
| Framework | |
Answer-guided and Semantic Coherent Question Generation in Open-domain Conversation
| Title | Answer-guided and Semantic Coherent Question Generation in Open-domain Conversation |
| Authors | Weichao Wang, Shi Feng, Daling Wang, Yifei Zhang |
| Abstract | Generating intriguing question is a key step towards building human-like open-domain chatbots. Although some recent works have focused on this task, compared with questions raised by humans, significant gaps remain in maintaining semantic coherence with post, which may result in generating dull or deviated questions. We observe that the answer has strong semantic coherence to its question and post, which can be used to guide question generation. Thus, we devise two methods to further enhance semantic coherence between post and question under the guidance of answer. First, the coherence score between generated question and answer is used as the reward function in a reinforcement learning framework, to encourage the cases that are consistent with the answer in semantic. Second, we incorporate adversarial training to explicitly control question generation in the direction of question-answer coherence. Extensive experiments show that our two methods outperform state-of-the-art baseline algorithms with large margins in raising semantic coherent questions. |
| Tasks | Question Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1511/ |
| https://www.aclweb.org/anthology/D19-1511 | |
| PWC | https://paperswithcode.com/paper/answer-guided-and-semantic-coherent-question |
| Repo | |
| Framework | |
