Paper Group NAWR 17
Detecting Perspectives in Political Debates. Error-repair Dependency Parsing for Ungrammatical Texts. An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling. Kyoto University Participation to WAT 2017. Fitting Low-Rank Tensors in Constant Time. Learning discriminative and transformation covariant local feature detectors.. Deep Lea …
Detecting Perspectives in Political Debates
| Title | Detecting Perspectives in Political Debates |
| Authors | David Vilares, Yulan He |
| Abstract | We explore how to detect people{'}s perspectives that occupy a certain proposition. We propose a Bayesian modelling approach where topics (or propositions) and their associated perspectives (or viewpoints) are modeled as latent variables. Words associated with topics or perspectives follow different generative routes. Based on the extracted perspectives, we can extract the top associated sentences from text to generate a succinct summary which allows a quick glimpse of the main viewpoints in a document. The model is evaluated on debates from the House of Commons of the UK Parliament, revealing perspectives from the debates without the use of labelled data and obtaining better results than previous related solutions under a variety of evaluations. |
| Tasks | Topic Models |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1165/ |
| https://www.aclweb.org/anthology/D17-1165 | |
| PWC | https://paperswithcode.com/paper/detecting-perspectives-in-political-debates |
| Repo | https://github.com/aghie/lam |
| Framework | none |
Error-repair Dependency Parsing for Ungrammatical Texts
| Title | Error-repair Dependency Parsing for Ungrammatical Texts |
| Authors | Keisuke Sakaguchi, Matt Post, Benjamin Van Durme |
| Abstract | We propose a new dependency parsing scheme which jointly parses a sentence and repairs grammatical errors by extending the non-directional transition-based formalism of Goldberg and Elhadad (2010) with three additional actions: SUBSTITUTE, DELETE, INSERT. Because these actions may cause an infinite loop in derivation, we also introduce simple constraints that ensure the parser termination. We evaluate our model with respect to dependency accuracy and grammaticality improvements for ungrammatical sentences, demonstrating the robustness and applicability of our scheme. |
| Tasks | Dependency Parsing |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2030/ |
| https://www.aclweb.org/anthology/P17-2030 | |
| PWC | https://paperswithcode.com/paper/error-repair-dependency-parsing-for |
| Repo | https://github.com/keisks/error-repair-parsing |
| Framework | none |
An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling
| Title | An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling |
| Authors | Sheng Zhang, Rachel Rudinger, Benjamin Van Durme |
| Abstract | |
| Tasks | Common Sense Reasoning, Open Information Extraction, Semantic Role Labeling |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6944/ |
| https://www.aclweb.org/anthology/W17-6944 | |
| PWC | https://paperswithcode.com/paper/an-evaluation-of-predpatt-and-open-ie-via |
| Repo | https://github.com/hltcoe/PredPatt |
| Framework | none |
Kyoto University Participation to WAT 2017
| Title | Kyoto University Participation to WAT 2017 |
| Authors | Fabien Cromieres, Raj Dabre, Toshiaki Nakazawa, Sadao Kurohashi |
| Abstract | We describe here our approaches and results on the WAT 2017 shared translation tasks. Following our good results with Neural Machine Translation in the previous shared task, we continue this approach this year, with incremental improvements in models and training methods. We focused on the ASPEC dataset and could improve the state-of-the-art results for Chinese-to-Japanese and Japanese-to-Chinese translations. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5714/ |
| https://www.aclweb.org/anthology/W17-5714 | |
| PWC | https://paperswithcode.com/paper/kyoto-university-participation-to-wat-2017 |
| Repo | https://github.com/fabiencro/knmt |
| Framework | none |
Fitting Low-Rank Tensors in Constant Time
| Title | Fitting Low-Rank Tensors in Constant Time |
| Authors | Kohei Hayashi, Yuichi Yoshida |
| Abstract | In this paper, we develop an algorithm that approximates the residual error of Tucker decomposition, one of the most popular tensor decomposition methods, with a provable guarantee. Given an order-$K$ tensor $X\in\mathbb{R}^{N_1\times\cdots\times N_K}$, our algorithm randomly samples a constant number $s$ of indices for each mode and creates a ``mini’’ tensor $\tilde{X}\in\mathbb{R}^{s\times\cdots\times s}$, whose elements are given by the intersection of the sampled indices on $X$. Then, we show that the residual error of the Tucker decomposition of $\tilde{X}$ is sufficiently close to that of $X$ with high probability. This result implies that we can figure out how much we can fit a low-rank tensor to $X$ \emph{in constant time}, regardless of the size of $X$. This is useful for guessing the favorable rank of Tucker decomposition. Finally, we demonstrate how the sampling method works quickly and accurately using multiple real datasets. | |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6841-fitting-low-rank-tensors-in-constant-time |
| http://papers.nips.cc/paper/6841-fitting-low-rank-tensors-in-constant-time.pdf | |
| PWC | https://paperswithcode.com/paper/fitting-low-rank-tensors-in-constant-time |
| Repo | https://github.com/hayasick/CTFT |
| Framework | none |
Learning discriminative and transformation covariant local feature detectors.
| Title | Learning discriminative and transformation covariant local feature detectors. |
| Authors | Xu Zhang, Felix X. Yu, Svebor Karaman, Shih-Fu Chang |
| Abstract | Robust covariant local feature detectors are important for detecting local features that are (1) discriminative of the image content and (2) can be repeatably detected at consistent locations when the image undergoes diverse transformations.Such detectors are critical for applications such as image search and scene reconstruction. Many learningbased local feature detectors address one of these two problems while overlooking the other. In this work, we propose a novel learning-based method to simultaneously address both issues. Specifically, we extend the covariant constraint proposed by Lenc and Vedaldi [8] by defining the concepts of “standard patch” and “canonical feature” and leverage these to train a novel robust covariant detector. We show that the introduction of these concepts greatly simplifies the learning stage of the covariant detector, and also makes the detector much more robust. Extensive experiments show that our method outperforms previous handcrafted and learning-based detectors by large margins in terms of repeatability. |
| Tasks | Image Retrieval |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhang_Learning_Discriminative_and_CVPR_2017_paper.pdf |
| https://sci-hub.tw/10.1109/CVPR.2017.523 | |
| PWC | https://paperswithcode.com/paper/learning-discriminative-and-transformation-1 |
| Repo | https://github.com/ColumbiaDVMM/Transform_Covariant_Detector |
| Framework | tf |
Deep Learning for ECG Classification
| Title | Deep Learning for ECG Classification |
| Authors | Boris Pyakillya, Natasha Kazachenko, Nick Mikhailovsky |
| Abstract | The importance of ECG classification is very high now due to many current medical applications where this problem can be stated. Currently, there are many machine learning (ML) solutions which can be used for analyzing and classifying ECG data. However, the main disadvantages of these ML results is use of heuristic hand-crafted or engineered features with shallow feature learning architectures. The problem relies in the possibility not to find most appropriate features which will give high classification accuracy in this ECG problem. One of the proposing solution is to use deep learning architectures where first layers of convolutional neurons behave as feature extractors and in the end some fully-connected (FCN) layers are used for making final decision about ECG classes. In this work the deep learning architecture with 1D convolutional layers and FCN layers for ECG classification is presented and some classification results are showed. |
| Tasks | ECG Classification, Electrocardiography (ECG) |
| Published | 2017-01-01 |
| URL | http://doi.org/10.1088/1742-6596/913/1/012004 |
| http://iopscience.iop.org/article/10.1088/1742-6596/913/1/012004/pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-ecg-classification |
| Repo | https://github.com/ismorphism/DeepECG |
| Framework | tf |
Vancouver Welcomes You! Minimalist Location Metonymy Resolution
| Title | Vancouver Welcomes You! Minimalist Location Metonymy Resolution |
| Authors | Milan Gritta, Mohammad Taher Pilehvar, Nut Limsopatham, Nigel Collier |
| Abstract | Named entities are frequently used in a metonymic manner. They serve as references to related entities such as people and organisations. Accurate identification and interpretation of metonymy can be directly beneficial to various NLP applications, such as Named Entity Recognition and Geographical Parsing. Until now, metonymy resolution (MR) methods mainly relied on parsers, taggers, dictionaries, external word lists and other handcrafted lexical resources. We show how a minimalist neural approach combined with a novel predicate window method can achieve competitive results on the SemEval 2007 task on Metonymy Resolution. Additionally, we contribute with a new Wikipedia-based MR dataset called RelocaR, which is tailored towards locations as well as improving previous deficiencies in annotation guidelines. |
| Tasks | Named Entity Recognition |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1115/ |
| https://www.aclweb.org/anthology/P17-1115 | |
| PWC | https://paperswithcode.com/paper/vancouver-welcomes-you-minimalist-location |
| Repo | https://github.com/milangritta/Minimalist-Location-Metonymy-Resolution |
| Framework | tf |
Natural Language Does Not Emerge `Naturally’ in Multi-Agent Dialog
| Title | Natural Language Does Not Emerge `Naturally’ in Multi-Agent Dialog | |
| Authors | Satwik Kottur, Jos{'e} Moura, Stefan Lee, Dhruv Batra |
| Abstract | A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the protocols developed by the agents, learned without any human supervision! In this paper, using a Task {&} Talk reference game between two agents as a testbed, we present a sequence of {}negative{'} results culminating in a {}positive{'} one {–} showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not interpretable or compositional. In essence, we find that natural language does not emerge {`}naturally{'},despite the semblance of ease of natural-language-emergence that one may gather from recent literature. We discuss how it is possible to coax the invented languages to become more and more human-like and compositional by increasing restrictions on how two agents may communicate. | |
| Tasks | Slot Filling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1321/ |
| https://www.aclweb.org/anthology/D17-1321 | |
| PWC | https://paperswithcode.com/paper/natural-language-does-not-emerge-anaturallya |
| Repo | https://github.com/batra-mlp-lab/lang-emerge |
| Framework | pytorch |
Enhanced UD Dependencies with Neutralized Diathesis Alternation
| Title | Enhanced UD Dependencies with Neutralized Diathesis Alternation |
| Authors | C, Marie ito, Bruno Guillaume, Guy Perrier, Djam{'e} Seddah |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6507/ |
| https://www.aclweb.org/anthology/W17-6507 | |
| PWC | https://paperswithcode.com/paper/enhanced-ud-dependencies-with-neutralized |
| Repo | https://github.com/bguil/Depling2017 |
| Framework | none |
Improving Low-Resource Neural Machine Translation with Filtered Pseudo-Parallel Corpus
| Title | Improving Low-Resource Neural Machine Translation with Filtered Pseudo-Parallel Corpus |
| Authors | Aizhan Imankulova, Takayuki Sato, Mamoru Komachi |
| Abstract | Large-scale parallel corpora are indispensable to train highly accurate machine translators. However, manually constructed large-scale parallel corpora are not freely available in many language pairs. In previous studies, training data have been expanded using a pseudo-parallel corpus obtained using machine translation of the monolingual corpus in the target language. However, in low-resource language pairs in which only low-accuracy machine translation systems can be used, translation quality is reduces when a pseudo-parallel corpus is used naively. To improve machine translation performance with low-resource language pairs, we propose a method to expand the training data effectively via filtering the pseudo-parallel corpus using a quality estimation based on back-translation. As a result of experiments with three language pairs using small, medium, and large parallel corpora, language pairs with fewer training data filtered out more sentence pairs and improved BLEU scores more significantly. |
| Tasks | Language Modelling, Low-Resource Neural Machine Translation, Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5704/ |
| https://www.aclweb.org/anthology/W17-5704 | |
| PWC | https://paperswithcode.com/paper/improving-low-resource-neural-machine |
| Repo | https://github.com/aizhanti/filtered-pseudo-parallel-corpora |
| Framework | none |
