Paper Group NANR 258
On Computation and Generalization of Generative Adversarial Networks under Spectrum Control. Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective. Stacking for Transfer Learning. Toward a Task of Feedback Comment Generation for Writing Learning. Iterative Search for Weakly Supervised Semantic Parsing. Neural Temporality Adapt …
On Computation and Generalization of Generative Adversarial Networks under Spectrum Control
| Title | On Computation and Generalization of Generative Adversarial Networks under Spectrum Control |
| Authors | Haoming Jiang, Zhehui Chen, Minshuo Chen, Feng Liu, Dingding Wang, Tuo Zhao |
| Abstract | Generative Adversarial Networks (GANs), though powerful, is hard to train. Several recent works (Brock et al., 2016; Miyato et al., 2018) suggest that controlling the spectra of weight matrices in the discriminator can significantly improve the training of GANs. Motivated by their discovery, we propose a new framework for training GANs, which allows more flexible spectrum control (e.g., making the weight matrices of the discriminator have slow singular value decays). Specifically, we propose a new reparameterization approach for the weight matrices of the discriminator in GANs, which allows us to directly manipulate the spectra of the weight matrices through various regularizers and constraints, without intensively computing singular value decompositions. Theoretically, we further show that the spectrum control improves the generalization ability of GANs. Our experiments on CIFAR-10, STL-10, and ImgaeNet datasets confirm that compared to other competitors, our proposed method is capable of generating images with better or equal quality by utilizing spectral normalization and encouraging the slow singular value decay. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJNH6sAqY7 |
| https://openreview.net/pdf?id=rJNH6sAqY7 | |
| PWC | https://paperswithcode.com/paper/on-computation-and-generalization-of |
| Repo | |
| Framework | |
Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective
| Title | Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective |
| Authors | Abhijit Mishra, Anirban Laha, Karthik Sankaranarayanan, Parag Jain, Saravanan Krishnan |
| Abstract | In this tutorial, we wish to cover the foundational, methodological, and system development aspects of translating structured data (such as data in tabular form) and knowledge bases (such as knowledge graphs) into natural language. The attendees of the tutorial will be able to take away from this tutorial, (1) the basic ideas around how modern NLP and NLG techniques could be applied to describe and summarize textual data in format that is non-linguistic in nature or has some structure, and (2) a few interesting open-ended questions, which could lead to significant research contributions in future. The tutorial aims to convey challenges and nuances in structured data translation, data representation techniques, and domain adaptable solutions for translation of the data into natural language form. Various solutions, starting from traditional rule based/heuristic driven and modern data-driven and ultra-modern deep-neural style architectures will be discussed, followed by a brief discussion on evaluation and quality estimation. A significant portion of the tutorial will be dedicated towards unsupervised, scalable, and adaptable solutions, given that systems for such an important task will never naturally enjoy sustainable large scale domain independent labeled (parallel) data. |
| Tasks | Knowledge Graphs |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-4009/ |
| https://www.aclweb.org/anthology/P19-4009 | |
| PWC | https://paperswithcode.com/paper/storytelling-from-structured-data-and |
| Repo | |
| Framework | |
Stacking for Transfer Learning
| Title | Stacking for Transfer Learning |
| Authors | Peng Yuankai |
| Abstract | In machine learning tasks, overtting frequently crops up when the number of samples of target domain is insufficient, for the generalization ability of the classifier is poor in this circumstance. To solve this problem, transfer learning utilizes the knowledge of similar domains to improve the robustness of the learner. The main idea of existing transfer learning algorithms is to reduce the dierence between domains by sample selection or domain adaptation. However, no matter what transfer learning algorithm we use, the difference always exists and the hybrid training of source and target data leads to reducing fitting capability of the learner on target domain. Moreover, when the relatedness between domains is too low, negative transfer is more likely to occur. To tackle the problem, we proposed a two-phase transfer learning architecture based on ensemble learning, which uses the existing transfer learning algorithms to train the weak learners in the first stage, and uses the predictions of target data to train the final learner in the second stage. Under this architecture, the fitting capability and generalization capability can be guaranteed at the same time. We evaluated the proposed method on public datasets, which demonstrates the effectiveness and robustness of our proposed method. |
| Tasks | Domain Adaptation, Transfer Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryxOIsA5FQ |
| https://openreview.net/pdf?id=ryxOIsA5FQ | |
| PWC | https://paperswithcode.com/paper/stacking-for-transfer-learning |
| Repo | |
| Framework | |
Toward a Task of Feedback Comment Generation for Writing Learning
| Title | Toward a Task of Feedback Comment Generation for Writing Learning |
| Authors | Ryo Nagata |
| Abstract | In this paper, we introduce a novel task called feedback comment generation {—} a task of automatically generating feedback comments such as a hint or an explanatory note for writing learning for non-native learners of English. There has been almost no work on this task nor corpus annotated with feedback comments. We have taken the first step by creating learner corpora consisting of approximately 1,900 essays where all preposition errors are manually annotated with feedback comments. We have tested three baseline methods on the dataset, showing that a simple neural retrieval-based method sets a baseline performance with an F-measure of 0.34 to 0.41. Finally, we have looked into the results to explore what modifications we need to make to achieve better performance. We also have explored problems unaddressed in this work |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1316/ |
| https://www.aclweb.org/anthology/D19-1316 | |
| PWC | https://paperswithcode.com/paper/toward-a-task-of-feedback-comment-generation |
| Repo | |
| Framework | |
Iterative Search for Weakly Supervised Semantic Parsing
| Title | Iterative Search for Weakly Supervised Semantic Parsing |
| Authors | Pradeep Dasigi, Matt Gardner, Shikhar Murty, Luke Zettlemoyer, Eduard Hovy |
| Abstract | Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer. We propose a novel iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones. This training scheme lets us iteratively train models that provide guidance to subsequent ones to search for logical forms of increasing complexity, thus dealing with the problem of spuriousness. We evaluate these techniques on two hard datasets: WikiTableQuestions (WTQ) and Cornell Natural Language Visual Reasoning (NLVR), and show that our training algorithm outperforms the previous best systems, on WTQ in a comparable setting, and on NLVR with significantly less supervision. |
| Tasks | Semantic Parsing, Visual Reasoning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1273/ |
| https://www.aclweb.org/anthology/N19-1273 | |
| PWC | https://paperswithcode.com/paper/iterative-search-for-weakly-supervised |
| Repo | |
| Framework | |
Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models
| Title | Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models |
| Authors | Xiaolei Huang, Michael J. Paul |
| Abstract | Language usage can change across periods of time, but document classifiers models are usually trained and tested on corpora spanning multiple years without considering temporal variations. This paper describes two complementary ways to adapt classifiers to shifts across time. First, we show that diachronic word embeddings, which were originally developed to study language change, can also improve document classification, and we show a simple method for constructing this type of embedding. Second, we propose a time-driven neural classification model inspired by methods for domain adaptation. Experiments on six corpora show how these methods can make classifiers more robust over time. |
| Tasks | Document Classification, Domain Adaptation, Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1403/ |
| https://www.aclweb.org/anthology/P19-1403 | |
| PWC | https://paperswithcode.com/paper/neural-temporality-adaptation-for-document |
| Repo | |
| Framework | |
Team Jack Ryder at SemEval-2019 Task 4: Using BERT Representations for Detecting Hyperpartisan News
| Title | Team Jack Ryder at SemEval-2019 Task 4: Using BERT Representations for Detecting Hyperpartisan News |
| Authors | Daniel Shaprin, Giovanni Da San Martino, Alberto Barr{'o}n-Cede{~n}o, Preslav Nakov |
| Abstract | We describe the system submitted by the Jack Ryder team to SemEval-2019 Task 4 on Hyperpartisan News Detection. The task asked participants to predict whether a given article is hyperpartisan, i.e., extreme-left or extreme-right. We proposed an approach based on BERT with fine-tuning, which was ranked 7th out 28 teams on the distantly supervised dataset, where all articles from a hyperpartisan/non-hyperpartisan news outlet are considered to be hyperpartisan/non-hyperpartisan. On a manually annotated test dataset, where human annotators double-checked the labels, we were ranked 29th out of 42 teams. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2176/ |
| https://www.aclweb.org/anthology/S19-2176 | |
| PWC | https://paperswithcode.com/paper/team-jack-ryder-at-semeval-2019-task-4-using |
| Repo | |
| Framework | |
Team Kit Kittredge at SemEval-2019 Task 4: LSTM Voting System
| Title | Team Kit Kittredge at SemEval-2019 Task 4: LSTM Voting System |
| Authors | Rebekah Cramerus, Tatjana Scheffler |
| Abstract | This paper describes the approach of team Kit Kittredge to SemEval-2019 Task 4: Hyperpartisan News Detection. The goal was binary classification of news articles into the categories of {}biased{''} or {}unbiased{''}. We had two software submissions: one a simple bag-of-words model, and the second an LSTM (Long Short Term Memory) neural network, which was trained on a subset of the original dataset selected by a voting system of other LSTMs. This method did not prove much more successful than the baseline, however, due to the models{'} tendency to learn publisher-specific traits instead of general bias. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2178/ |
| https://www.aclweb.org/anthology/S19-2178 | |
| PWC | https://paperswithcode.com/paper/team-kit-kittredge-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
Computing committor functions for the study of rare events using deep learning with importance sampling
| Title | Computing committor functions for the study of rare events using deep learning with importance sampling |
| Authors | Qianxiao Li, Bo Lin, Weiqing Ren |
| Abstract | The committor function is a central object of study in understanding transitions between metastable states in complex systems. However, computing the committor function for realistic systems at low temperatures is a challenging task, due to the curse of dimensionality and the scarcity of transition data. In this paper, we introduce a computational approach that overcomes these issues and achieves good performance on complex benchmark problems with rough energy landscapes. The new approach combines deep learning, importance sampling and feature engineering techniques. This establishes an alternative practical method for studying rare transition events among metastable states of complex, high dimensional systems. |
| Tasks | Feature Engineering |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1lPUiRcYQ |
| https://openreview.net/pdf?id=H1lPUiRcYQ | |
| PWC | https://paperswithcode.com/paper/computing-committor-functions-for-the-study |
| Repo | |
| Framework | |
AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging
| Title | AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging |
| Authors | Bill Yuchen Lin, Dong-Ho Lee, Frank F. Xu, Ouyu Lan, Xiang Ren |
| Abstract | We introduce an open-source web-based data annotation framework (AlpacaTag) for sequence tagging tasks such as named-entity recognition (NER). The distinctive advantages of AlpacaTag are three-fold. 1) Active intelligent recommendation: dynamically suggesting annotations and sampling the most informative unlabeled instances with a back-end active learned model; 2) Automatic crowd consolidation: enhancing real-time inter-annotator agreement by merging inconsistent labels from multiple annotators; 3) Real-time model deployment: users can deploy their models in downstream systems while new annotations are being made. AlpacaTag is a comprehensive solution for sequence labeling tasks, ranging from rapid tagging with recommendations powered by active learning and auto-consolidation of crowd annotations to real-time model deployment. |
| Tasks | Active Learning, Named Entity Recognition |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-3010/ |
| https://www.aclweb.org/anthology/P19-3010 | |
| PWC | https://paperswithcode.com/paper/alpacatag-an-active-learning-based-crowd |
| Repo | |
| Framework | |
DA-LD-Hildesheim at SemEval-2019 Task 6: Tracking Offensive Content with Deep Learning using Shallow Representation
| Title | DA-LD-Hildesheim at SemEval-2019 Task 6: Tracking Offensive Content with Deep Learning using Shallow Representation |
| Authors | S Modha, ip, Prasenjit Majumder, Daksh Patel |
| Abstract | This paper presents the participation of team DA-LD-Hildesheim of Information Retrieval and Language Processing lab at DA-IICT, India in Semeval-19 OffenEval track. The aim of this shared task is to identify offensive content at fined-grained level granularity. The task is divided into three sub-tasks. The system is required to check whether social media posts contain any offensive or profane content or not, targeted or untargeted towards any entity and classifying targeted posts into the individual, group or other categories. Social media posts suffer from data sparsity problem, Therefore, the distributed word representation technique is chosen over the Bag-of-Words for the text representation. Since limited labeled data was available for the training, pre-trained word vectors are used and fine-tuned on this classification task. Various deep learning models based on LSTM, Bidirectional LSTM, CNN, and Stacked CNN are used for the classification. It has been observed that labeled data was highly affected with class imbalance and our technique to handle the class-balance was not effective, in fact performance was degraded in some of the runs. Macro F1 score is used as a primary evaluation metric for the performance. Our System achieves Macro F1 score = 0.7833 in sub-task A, 0.6456 in the sub-task B and 0.5533 in the sub-task C. |
| Tasks | Information Retrieval |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2103/ |
| https://www.aclweb.org/anthology/S19-2103 | |
| PWC | https://paperswithcode.com/paper/da-ld-hildesheim-at-semeval-2019-task-6 |
| Repo | |
| Framework | |
The Sally Smedley Hyperpartisan News Detector at SemEval-2019 Task 4
| Title | The Sally Smedley Hyperpartisan News Detector at SemEval-2019 Task 4 |
| Authors | Kazuaki Hanawa, Shota Sasaki, Hiroki Ouchi, Jun Suzuki, Kentaro Inui |
| Abstract | This paper describes our system submitted to the formal run of SemEval-2019 Task 4: Hyperpartisan news detection. Our system is based on a linear classifier using several features, i.e., 1) embedding features based on the pre-trained BERT embeddings, 2) article length features, and 3) embedding features of informative phrases extracted from by-publisher dataset. Our system achieved 80.9{%} accuracy on the test set for the formal run and got the 3rd place out of 42 teams. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2185/ |
| https://www.aclweb.org/anthology/S19-2185 | |
| PWC | https://paperswithcode.com/paper/the-sally-smedley-hyperpartisan-news-detector |
| Repo | |
| Framework | |
Team Xenophilius Lovegood at SemEval-2019 Task 4: Hyperpartisanship Classification using Convolutional Neural Networks
| Title | Team Xenophilius Lovegood at SemEval-2019 Task 4: Hyperpartisanship Classification using Convolutional Neural Networks |
| Authors | Albin Zehe, Lena Hettinger, Stefan Ernst, Christian Hauptmann, Andreas Hotho |
| Abstract | This paper describes our system for the SemEval 2019 Task 4 on hyperpartisan news detection. We build on an existing deep learning approach for sentence classification based on a Convolutional Neural Network. Modifying the original model with additional layers to increase its expressiveness and finally building an ensemble of multiple versions of the model, we obtain an accuracy of 67.52{%} and an F1 score of 73.78{%} on the main test dataset. We also report on additional experiments incorporating handcrafted features into the CNN and using it as a feature extractor for a linear SVM. |
| Tasks | Sentence Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2183/ |
| https://www.aclweb.org/anthology/S19-2183 | |
| PWC | https://paperswithcode.com/paper/team-xenophilius-lovegood-at-semeval-2019 |
| Repo | |
| Framework | |
Global Optimization under Length Constraint for Neural Text Summarization
| Title | Global Optimization under Length Constraint for Neural Text Summarization |
| Authors | Takuya Makino, Tomoya Iwakura, Hiroya Takamura, Manabu Okumura |
| Abstract | We propose a global optimization method under length constraint (GOLC) for neural text summarization models. GOLC increases the probabilities of generating summaries that have high evaluation scores, ROUGE in this paper, within a desired length. We compared GOLC with two optimization methods, a maximum log-likelihood and a minimum risk training, on CNN/Daily Mail and a Japanese single document summarization data set of The Mainichi Shimbun Newspapers. The experimental results show that a state-of-the-art neural summarization model optimized with GOLC generates fewer overlength summaries while maintaining the fastest processing speed; only 6.70{%} overlength summaries on CNN/Daily and 7.8{%} on long summary of Mainichi, compared to the approximately 20{%} to 50{%} on CNN/Daily Mail and 10{%} to 30{%} on Mainichi with the other optimization methods. We also demonstrate the importance of the generation of in-length summaries for post-editing with the dataset Mainich that is created with strict length constraints. The ex- perimental results show approximately 30{%} to 40{%} improved post-editing time by use of in-length summaries. |
| Tasks | Document Summarization, Text Summarization |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1099/ |
| https://www.aclweb.org/anthology/P19-1099 | |
| PWC | https://paperswithcode.com/paper/global-optimization-under-length-constraint |
| Repo | |
| Framework | |
Vernon-fenwick at SemEval-2019 Task 4: Hyperpartisan News Detection using Lexical and Semantic Features
| Title | Vernon-fenwick at SemEval-2019 Task 4: Hyperpartisan News Detection using Lexical and Semantic Features |
| Authors | Vertika Srivastava, Ankita Gupta, Divya Prakash, Sudeep Kumar Sahoo, Rohit R.R, Yeon Hyang Kim |
| Abstract | In this paper, we present our submission for SemEval-2019 Task 4: Hyperpartisan News Detection. Hyperpartisan news articles are sharply polarized and extremely biased (onesided). It shows blind beliefs, opinions and unreasonable adherence to a party, idea, faction or a person. Through this task, we aim to develop an automated system that can be used to detect hyperpartisan news and serve as a prescreening technique for fake news detection. The proposed system jointly uses a rich set of handcrafted textual and semantic features. Our system achieved 2nd rank on the primary metric (82.0{%} accuracy) and 1st rank on the secondary metric (82.1{%} F1-score), among all participating teams. Comparison with the best performing system on the leaderboard shows that our system is behind by only 0.2{%} absolute difference in accuracy. |
| Tasks | Fake News Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2189/ |
| https://www.aclweb.org/anthology/S19-2189 | |
| PWC | https://paperswithcode.com/paper/vernon-fenwick-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
