Paper Group NANR 77
Localization of Deep Inpainting Using High-Pass Fully Convolutional Network. KU_ai at MEDIQA 2019: Domain-specific Pre-training and Transfer Learning for Medical NLI. Parallel Optimal Transport GAN. An Analysis of Composite Neural Network Performance from Function Composition Perspective. Cross-lingual Transfer Learning and Multitask Learning for …
Localization of Deep Inpainting Using High-Pass Fully Convolutional Network
| Title | Localization of Deep Inpainting Using High-Pass Fully Convolutional Network |
| Authors | Haodong Li, Jiwu Huang |
| Abstract | Image inpainting has been substantially improved with deep learning in the past years. Deep inpainting can fill image regions with plausible contents, which are not visually apparent. Although inpainting is originally designed to repair images, it can even be used for malicious manipulations, e.g., removal of specific objects. Therefore, it is necessary to identify the presence of inpainting in an image. This paper presents a method to locate the regions manipulated by deep inpainting. The proposed method employs a fully convolutional network that is based on high-pass filtered image residuals. Firstly, we analyze and observe that the inpainted regions are more distinguishable from the untouched ones in the residual domain. Hence, a high-pass pre-filtering module is designed to get image residuals for enhancing inpainting traces. Then, a feature extraction module, which learns discriminative features from image residuals, is built with four concatenated ResNet blocks. The learned feature maps are finally enlarged by an up-sampling module, so that a pixel-wise inpainting localization map is obtained. The whole network is trained end-to-end with a loss addressing the class imbalance. Extensive experimental results evaluated on both synthetic and realistic images subjected to deep inpainting have shown the effectiveness of the proposed method. |
| Tasks | Image Inpainting |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Localization_of_Deep_Inpainting_Using_High-Pass_Fully_Convolutional_Network_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Localization_of_Deep_Inpainting_Using_High-Pass_Fully_Convolutional_Network_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/localization-of-deep-inpainting-using-high |
| Repo | |
| Framework | |
KU_ai at MEDIQA 2019: Domain-specific Pre-training and Transfer Learning for Medical NLI
| Title | KU_ai at MEDIQA 2019: Domain-specific Pre-training and Transfer Learning for Medical NLI |
| Authors | Cemil Cengiz, Ula{\c{s}} Sert, Deniz Yuret |
| Abstract | In this paper, we describe our system and results submitted for the Natural Language Inference (NLI) track of the MEDIQA 2019 Shared Task. As KU{_}ai team, we used BERT as our baseline model and pre-processed the MedNLI dataset to mitigate the negative impact of de-identification artifacts. Moreover, we investigated different pre-training and transfer learning approaches to improve the performance. We show that pre-training the language model on rich biomedical corpora has a significant effect in teaching the model domain-specific language. In addition, training the model on large NLI datasets such as MultiNLI and SNLI helps in learning task-specific reasoning. Finally, we ensembled our highest-performing models, and achieved 84.7{%} accuracy on the unseen test dataset and ranked 10th out of 17 teams in the official results. |
| Tasks | Language Modelling, Natural Language Inference, Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5045/ |
| https://www.aclweb.org/anthology/W19-5045 | |
| PWC | https://paperswithcode.com/paper/ku_ai-at-mediqa-2019-domain-specific-pre |
| Repo | |
| Framework | |
Parallel Optimal Transport GAN
| Title | Parallel Optimal Transport GAN |
| Authors | Gil Avraham, Yan Zuo, Tom Drummond |
| Abstract | Although Generative Adversarial Networks (GANs) are known for their sharp realism in image generation, they often fail to estimate areas of the data density. This leads to low modal diversity and at times distorted generated samples. These problems essentially arise from poor estimation of the distance metric responsible for training these networks. To address these issues, we introduce an additional regularisation term which performs optimal transport in parallel within a low dimensional representation space. We demonstrate that operating in a low dimension representation of the data distribution benefits from convergence rate gains in estimating the Wasserstein distance, resulting in more stable GAN training. We empirically show that our regulariser achieves a stabilising effect which leads to higher quality of generated samples and increased mode coverage of the given data distribution. Our method achieves significant improvements on the CIFAR-10, Oxford Flowers and CUB Birds datasets over several GAN baselines both qualitatively and quantitatively. |
| Tasks | Image Generation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Avraham_Parallel_Optimal_Transport_GAN_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Avraham_Parallel_Optimal_Transport_GAN_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/parallel-optimal-transport-gan |
| Repo | |
| Framework | |
An Analysis of Composite Neural Network Performance from Function Composition Perspective
| Title | An Analysis of Composite Neural Network Performance from Function Composition Perspective |
| Authors | Ming-Chuan Yang, Meng Chang Chen |
| Abstract | This work investigates the performance of a composite neural network, which is composed of pre-trained neural network models and non-instantiated neural network models, connected to form a rooted directed graph. A pre-trained neural network model is generally a well trained neural network model targeted for a specific function. The advantages of adopting such a pre-trained model in a composite neural network are two folds. One is to benefit from other’s intelligence and diligence and the other is saving the efforts in data preparation and resources and time in training. However, the overall performance of composite neural network is still not clear. In this work, we prove that a composite neural network, with high probability, performs better than any of its pre-trained components under certain assumptions. In addition, if an extra pre-trained component is added to a composite network, with high probability the overall performance will be improved. In the empirical evaluations, distinctively different applications support the above findings. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkGSniC9FQ |
| https://openreview.net/pdf?id=HkGSniC9FQ | |
| PWC | https://paperswithcode.com/paper/an-analysis-of-composite-neural-network |
| Repo | |
| Framework | |
Cross-lingual Transfer Learning and Multitask Learning for Capturing Multiword Expressions
| Title | Cross-lingual Transfer Learning and Multitask Learning for Capturing Multiword Expressions |
| Authors | Shiva Taslimipoor, Omid Rohanian, Le An Ha |
| Abstract | Recent developments in deep learning have prompted a surge of interest in the application of multitask and transfer learning to NLP problems. In this study, we explore for the first time, the application of transfer learning (TRL) and multitask learning (MTL) to the identification of Multiword Expressions (MWEs). For MTL, we exploit the shared syntactic information between MWE and dependency parsing models to jointly train a single model on both tasks. We specifically predict two types of labels: MWE and dependency parse. Our neural MTL architecture utilises the supervision of dependency parsing in lower layers and predicts MWE tags in upper layers. In the TRL scenario, we overcome the scarcity of data by learning a model on a larger MWE dataset and transferring the knowledge to a resource-poor setting in another language. In both scenarios, the resulting models achieved higher performance compared to standard neural approaches. |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5119/ |
| https://www.aclweb.org/anthology/W19-5119 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-transfer-learning-and-multitask |
| Repo | |
| Framework | |
Towards Assessing Argumentation Annotation - A First Step
| Title | Towards Assessing Argumentation Annotation - A First Step |
| Authors | Anna Lindahl, Lars Borin, Jacobo Rouces |
| Abstract | This paper presents a first attempt at using Walton{'}s argumentation schemes for annotating arguments in Swedish political text and assessing the feasibility of using this particular set of schemes with two linguistically trained annotators. The texts are not pre-annotated with argumentation structure beforehand. The results show that the annotators differ both in number of annotated arguments and selection of the conclusion and premises which make up the arguments. They also differ in their labeling of the schemes, but grouping the schemes increases their agreement. The outcome from this will be used to develop guidelines for future annotations. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4520/ |
| https://www.aclweb.org/anthology/W19-4520 | |
| PWC | https://paperswithcode.com/paper/towards-assessing-argumentation-annotation-a |
| Repo | |
| Framework | |
The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure
| Title | The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure |
| Authors | Frederic Koehler, Andrej Risteski |
| Abstract | There has been a large amount of interest, both in the past and particularly recently, into the relative advantage of different families of universal function approximators, for instance neural networks, polynomials, rational functions, etc. However, current research has focused almost exclusively on understanding this problem in a worst case setting: e.g. characterizing the best L1 or L_{infty} approximation in a box (or sometimes, even under an adversarially constructed data distribution.) In this setting many classical tools from approximation theory can be effectively used. However, in typical applications we expect data to be high dimensional, but structured – so, it would only be important to approximate the desired function well on the relevant part of its domain, e.g. a small manifold on which real input data actually lies. Moreover, even within this domain the desired quality of approximation may not be uniform; for instance in classification problems, the approximation needs to be more accurate near the decision boundary. These issues, to the best of our knowledge, have remain unexplored until now. With this in mind, we analyze the performance of neural networks and polynomial kernels in a natural regression setting where the data enjoys sparse latent structure, and the labels depend in a simple way on the latent variables. We give an almost-tight theoretical analysis of the performance of both neural networks and polynomials for this problem, as well as verify our theory with simulations. Our results both involve new (complex-analytic) techniques, which may be of independent interest, and show substantial qualitative differences with what is known in the worst-case setting. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJgTTjA9tX |
| https://openreview.net/pdf?id=rJgTTjA9tX | |
| PWC | https://paperswithcode.com/paper/the-comparative-power-of-relu-networks-and |
| Repo | |
| Framework | |
P=aṇinian Syntactico-Semantic Relation Labels
| Title | P=aṇinian Syntactico-Semantic Relation Labels |
| Authors | Amba Kulkarni, Dipti Sharma |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7724/ |
| https://www.aclweb.org/anthology/W19-7724 | |
| PWC | https://paperswithcode.com/paper/paa1inian-syntactico-semantic-relation-labels |
| Repo | |
| Framework | |
Graph convolutional networks for exploring authorship hypotheses
| Title | Graph convolutional networks for exploring authorship hypotheses |
| Authors | Tom Lippincott |
| Abstract | This work considers a task from traditional literary criticism: annotating a structured, composite document with information about its sources. We take the Documentary Hypothesis, a prominent theory regarding the composition of the first five books of the Hebrew bible, extract stylistic features designed to avoid bias or overfitting, and train several classification models. Our main result is that the recently-introduced graph convolutional network architecture outperforms structurally-uninformed models. We also find that including information about the granularity of text spans is a crucial ingredient when employing hidden layers, in contrast to simple logistic regression. We perform error analysis at several levels, noting how some characteristic limitations of the models and simple features lead to misclassifications, and conclude with an overview of future work. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2510/ |
| https://www.aclweb.org/anthology/W19-2510 | |
| PWC | https://paperswithcode.com/paper/graph-convolutional-networks-for-exploring |
| Repo | |
| Framework | |
Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums
| Title | Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums |
| Authors | Zi Chai, Xinyu Xing, Xiaojun Wan, Bo Huang |
| Abstract | Teaching machines to ask questions is an important yet challenging task. Most prior work focused on generating questions with fixed answers. As contents are highly limited by given answers, these questions are often not worth discussing. In this paper, we take the first step on teaching machines to ask open-answered questions from real-world news for open discussion (openQG). To generate high-qualified questions, effective ways for question evaluation are required. We take the perspective that the more answers a question receives, the better it is for open discussion, and analyze how language use affects the number of answers. Compared with other factors, e.g. topic and post time, linguistic factors keep our evaluation from being domain-specific. We carefully perform variable control on 11.5M questions from online forums to get a dataset, OQRanD, and further perform question analysis. Based on these conclusions, several models are built for question evaluation. For openQG task, we construct OQGenD, the first dataset as far as we know, and propose a model based on conditional generative adversarial networks and our question evaluation model. Experiments show that our model can generate questions with higher quality compared with commonly-used text generation methods. |
| Tasks | Text Generation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1497/ |
| https://www.aclweb.org/anthology/P19-1497 | |
| PWC | https://paperswithcode.com/paper/asking-the-crowd-question-analysis-evaluation |
| Repo | |
| Framework | |
Decision-making, Risk, and Gist Machine Translation in the Work of Patent Professionals
| Title | Decision-making, Risk, and Gist Machine Translation in the Work of Patent Professionals |
| Authors | Mary Nurminen |
| Abstract | |
| Tasks | Decision Making, Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7204/ |
| https://www.aclweb.org/anthology/W19-7204 | |
| PWC | https://paperswithcode.com/paper/decision-making-risk-and-gist-machine |
| Repo | |
| Framework | |
Constrained Sequence-to-sequence Semitic Root Extraction for Enriching Word Embeddings
| Title | Constrained Sequence-to-sequence Semitic Root Extraction for Enriching Word Embeddings |
| Authors | Ahmed El-Kishky, Xingyu Fu, Aseel Addawood, Nahil Sobh, Clare Voss, Jiawei Han |
| Abstract | In this paper, we tackle the problem of {``}root extraction{''} from words in the Semitic language family. A challenge in applying natural language processing techniques to these languages is the data sparsity problem that arises from their rich internal morphology, where the substructure is inherently non-concatenative and morphemes are interdigitated in word formation. While previous automated methods have relied on human-curated rules or multiclass classification, they have not fully leveraged the various combinations of regular, sequential concatenative morphology within the words and the internal interleaving within templatic stems of roots and patterns. To address this, we propose a constrained sequence-to-sequence root extraction method. Experimental results show our constrained model outperforms a variety of methods at root extraction. Furthermore, by enriching word embeddings with resulting decompositions, we show improved results on word analogy, word similarity, and language modeling tasks. | |
| Tasks | Language Modelling, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4610/ |
| https://www.aclweb.org/anthology/W19-4610 | |
| PWC | https://paperswithcode.com/paper/constrained-sequence-to-sequence-semitic-root |
| Repo | |
| Framework | |
Proceedings of the 1st International Workshop of AI Werewolf and Dialog System (AIWolfDial2019)
| Title | Proceedings of the 1st International Workshop of AI Werewolf and Dialog System (AIWolfDial2019) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8300/ |
| https://www.aclweb.org/anthology/W19-8300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-1st-international-workshop-1 |
| Repo | |
| Framework | |
An automatic discourse relation alignment experiment on TED-MDB
| Title | An automatic discourse relation alignment experiment on TED-MDB |
| Authors | Sibel Ozer, Deniz Zeyrek |
| Abstract | This paper describes an automatic discourse relation alignment experiment as an empirical justification of the planned annotation projection approach to enlarge the 3600-word multilingual corpus of TED Multilingual Discourse Bank (TED-MDB). The experiment is carried out on a single language pair (English-Turkish) included in TED-MDB. The paper first describes the creation of a large corpus of English-Turkish bi-sentences, then it presents a sense-based experiment that automatically aligns the relations in the English sentences of TED-MDB with the Turkish sentences. The results are very close to the results obtained from an earlier semi-automatic post-annotation alignment experiment validated by human annotators and are encouraging for future annotation projection tasks. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3612/ |
| https://www.aclweb.org/anthology/W19-3612 | |
| PWC | https://paperswithcode.com/paper/an-automatic-discourse-relation-alignment |
| Repo | |
| Framework | |
Formality Style Transfer for Noisy, User-generated Conversations: Extracting Labeled, Parallel Data from Unlabeled Corpora
| Title | Formality Style Transfer for Noisy, User-generated Conversations: Extracting Labeled, Parallel Data from Unlabeled Corpora |
| Authors | Isak Czeresnia Etinger, Alan W Black |
| Abstract | Typical datasets used for style transfer in NLP contain aligned pairs of two opposite extremes of a style. As each existing dataset is sourced from a specific domain and context, most use cases will have a sizable mismatch from the vocabulary and sentence structures of any dataset available. This reduces the performance of the style transfer, and is particularly significant for noisy, user-generated text. To solve this problem, we show a technique to derive a dataset of aligned pairs (style-agnostic vs stylistic sentences) from an unlabeled corpus by using an auxiliary dataset, allowing for in-domain training. We test the technique with the Yahoo Formality Dataset and 6 novel datasets we produced, which consist of scripts from 5 popular TV-shows (Friends, Futurama, Seinfeld, Southpark, Stargate SG-1) and the Slate Star Codex online forum. We gather 1080 human evaluations, which show that our method produces a sizable change in formality while maintaining fluency and context; and that it considerably outperforms OpenNMT{'}s Seq2Seq model directly trained on the Yahoo Formality Dataset. Additionally, we publish the full pipeline code and our novel datasets. |
| Tasks | Style Transfer |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5502/ |
| https://www.aclweb.org/anthology/D19-5502 | |
| PWC | https://paperswithcode.com/paper/formality-style-transfer-for-noisy-user |
| Repo | |
| Framework | |
