Paper Group NANR 96
Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification. Accent Adaptation for the Air Traffic Control Domain. Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion. Pulling Out the Stops: Rethinking Stopword Removal for Topic Models. Multimodal Topic Labelling. Bib2vec: Embedding …
Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification
| Title | Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification |
| Authors | Jinseok Nam, Eneldo Loza Mencía, Hyunwoo J. Kim, Johannes Fürnkranz |
| Abstract | Multi-label classification is the task of predicting a set of labels for a given input instance. Classifier chains are a state-of-the-art method for tackling such problems, which essentially converts this problem into a sequential prediction problem, where the labels are first ordered in an arbitrary fashion, and the task is to predict a sequence of binary values for these labels. In this paper, we replace classifier chains with recurrent neural networks, a sequence-to-sequence prediction algorithm which has recently been successfully applied to sequential prediction tasks in many domains. The key advantage of this approach is that it allows to focus on the prediction of the positive labels only, a much smaller set than the full set of possible labels. Moreover, parameter sharing across all classifiers allows to better exploit information of previous decisions. As both, classifier chains and recurrent neural networks depend on a fixed ordering of the labels, which is typically not part of a multi-label problem specification, we also compare different ways of ordering the label set, and give some recommendations on suitable ordering strategies. |
| Tasks | Multi-Label Classification |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7125-maximizing-subset-accuracy-with-recurrent-neural-networks-in-multi-label-classification |
| http://papers.nips.cc/paper/7125-maximizing-subset-accuracy-with-recurrent-neural-networks-in-multi-label-classification.pdf | |
| PWC | https://paperswithcode.com/paper/maximizing-subset-accuracy-with-recurrent |
| Repo | |
| Framework | |
Accent Adaptation for the Air Traffic Control Domain
| Title | Accent Adaptation for the Air Traffic Control Domain |
| Authors | Matthew Garber, Meital Singer, Christopher Ward |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3016/ |
| https://www.aclweb.org/anthology/P17-3016 | |
| PWC | https://paperswithcode.com/paper/accent-adaptation-for-the-air-traffic-control |
| Repo | |
| Framework | |
Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion
| Title | Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion |
| Authors | Ryan Cotterell, John Sylak-Glassman, Christo Kirov |
| Abstract | Many of the world{'}s languages contain an abundance of inflected forms for each lexeme. A critical task in processing such languages is predicting these inflected forms. We develop a novel statistical model for the problem, drawing on graphical modeling techniques and recent advances in deep learning. We derive a Metropolis-Hastings algorithm to jointly decode the model. Our Bayesian network draws inspiration from principal parts morphological analysis. We demonstrate improvements on 5 languages. |
| Tasks | Morphological Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2120/ |
| https://www.aclweb.org/anthology/E17-2120 | |
| PWC | https://paperswithcode.com/paper/neural-graphical-models-over-strings-for |
| Repo | |
| Framework | |
Pulling Out the Stops: Rethinking Stopword Removal for Topic Models
| Title | Pulling Out the Stops: Rethinking Stopword Removal for Topic Models |
| Authors | Alex Schofield, ra, M{\aa}ns Magnusson, David Mimno |
| Abstract | It is often assumed that topic models benefit from the use of a manually curated stopword list. Constructing this list is time-consuming and often subject to user judgments about what kinds of words are important to the model and the application. Although stopword removal clearly affects which word types appear as most probable terms in topics, we argue that this improvement is superficial, and that topic inference benefits little from the practice of removing stopwords beyond very frequent terms. Removing corpus-specific stopwords after model inference is more transparent and produces similar results to removing those words prior to inference. |
| Tasks | Language Modelling, Topic Models |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2069/ |
| https://www.aclweb.org/anthology/E17-2069 | |
| PWC | https://paperswithcode.com/paper/pulling-out-the-stops-rethinking-stopword |
| Repo | |
| Framework | |
Multimodal Topic Labelling
| Title | Multimodal Topic Labelling |
| Authors | Ionut Sorodoc, Jey Han Lau, Nikolaos Aletras, Timothy Baldwin |
| Abstract | Topics generated by topic models are typically presented as a list of topic terms. Automatic topic labelling is the task of generating a succinct label that summarises the theme or subject of a topic, with the intention of reducing the cognitive load of end-users when interpreting these topics. Traditionally, topic label systems focus on a single label modality, e.g. textual labels. In this work we propose a multimodal approach to topic labelling using a simple feedforward neural network. Given a topic and a candidate image or textual label, our method automatically generates a rating for the label, relative to the topic. Experiments show that this multimodal approach outperforms single-modality topic labelling systems. |
| Tasks | Topic Models |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2111/ |
| https://www.aclweb.org/anthology/E17-2111 | |
| PWC | https://paperswithcode.com/paper/multimodal-topic-labelling |
| Repo | |
| Framework | |
Bib2vec: Embedding-based Search System for Bibliographic Information
| Title | Bib2vec: Embedding-based Search System for Bibliographic Information |
| Authors | Takuma Yoneda, Koki Mori, Makoto Miwa, Yutaka Sasaki |
| Abstract | We propose a novel embedding model that represents relationships among several elements in bibliographic information with high representation ability and flexibility. Based on this model, we present a novel search system that shows the relationships among the elements in the ACL Anthology Reference Corpus. The evaluation results show that our model can achieve a high prediction ability and produce reasonable search results. |
| Tasks | Network Embedding, Topic Models |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3028/ |
| https://www.aclweb.org/anthology/E17-3028 | |
| PWC | https://paperswithcode.com/paper/bib2vec-embedding-based-search-system-for |
| Repo | |
| Framework | |
Improving Verb Metaphor Detection by Propagating Abstractness to Words, Phrases and Individual Senses
| Title | Improving Verb Metaphor Detection by Propagating Abstractness to Words, Phrases and Individual Senses |
| Authors | Maximilian K{"o}per, Sabine Schulte im Walde |
| Abstract | Abstract words refer to things that can not be seen, heard, felt, smelled, or tasted as opposed to concrete words. Among other applications, the degree of abstractness has been shown to be a useful information for metaphor detection. Our contribution to this topic are as follows: i) we compare supervised techniques to learn and extend abstractness ratings for huge vocabularies ii) we learn and investigate norms for larger units by propagating abstractness to verb-noun pairs which lead to better metaphor detection iii) we overcome the limitation of learning a single rating per word and show that multi-sense abstractness ratings are potentially useful for metaphor detection. Finally, with this paper we publish automatically created abstractness norms for 3million English words and multi-words as well as automatically created sense specific abstractness ratings |
| Tasks | Semantic Textual Similarity, Topic Models, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1903/ |
| https://www.aclweb.org/anthology/W17-1903 | |
| PWC | https://paperswithcode.com/paper/improving-verb-metaphor-detection-by |
| Repo | |
| Framework | |
Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image
| Title | Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image |
| Authors | Rui Zhu, Hamed Kiani Galoogahi, Chaoyang Wang, Simon Lucey |
| Abstract | An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image. Hitherto, the problem has been addressed through the application of canonical deep learning methods to regress from the image directly to the 3D shape and pose labels. These approaches, however, are problematic from two perspectives. First, they are minimizing the error between 3D shapes and pose labels - with little thought about the nature of this “label error” when reprojecting the shape back onto the image. Second, they rely on the onerous and ill-posed task of hand labeling natural images with respect to 3D shape and pose. In this paper we define the new task of pose-aware shape reconstruction from a single image, and we advocate that cheaper 2D annotations of objects silhouettes in natural images can be utilized. We design architectures of pose-aware shape reconstruction which reproject the predicted shape back on to the image using the predicted pose. Our evaluation on several object categories demonstrates the superiority of our method for predicting pose-aware 3D shapes from natural images. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Rethinking_Reprojection_Closing_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Zhu_Rethinking_Reprojection_Closing_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-reprojection-closing-the-loop-for-1 |
| Repo | |
| Framework | |
From which world is your graph
| Title | From which world is your graph |
| Authors | Cheng Li, Felix Mf Wong, Zhenming Liu, Varun Kanade |
| Abstract | Discovering statistical structure from links is a fundamental problem in the analysis of social networks. Choosing a misspecified model, or equivalently, an incorrect inference algorithm will result in an invalid analysis or even falsely uncover patterns that are in fact artifacts of the model. This work focuses on unifying two of the most widely used link-formation models: the stochastic block model (SBM) and the small world (or latent space) model (SWM). Integrating techniques from kernel learning, spectral graph theory, and nonlinear dimensionality reduction, we develop the first statistically sound polynomial-time algorithm to discover latent patterns in sparse graphs for both models. When the network comes from an SBM, the algorithm outputs a block structure. When it is from an SWM, the algorithm outputs estimates of each node’s latent position. |
| Tasks | Dimensionality Reduction |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6745-from-which-world-is-your-graph |
| http://papers.nips.cc/paper/6745-from-which-world-is-your-graph.pdf | |
| PWC | https://paperswithcode.com/paper/from-which-world-is-your-graph-1 |
| Repo | |
| Framework | |
A Layered Language Model based Hybrid Approach to Automatic Full Diacritization of Arabic
| Title | A Layered Language Model based Hybrid Approach to Automatic Full Diacritization of Arabic |
| Authors | Mohamed Al-Badrashiny, Abdelati Hawwari, Mona Diab |
| Abstract | In this paper we present a system for automatic Arabic text diacritization using three levels of analysis granularity in a layered back off manner. We build and exploit diacritized language models (LM) for each of three different levels of granularity: surface form, morphologically segmented into prefix/stem/suffix, and character level. For each of the passes, we use Viterbi search to pick the most probable diacritization per word in the input. We start with the surface form LM, followed by the morphological level, then finally we leverage the character level LM. Our system outperforms all of the published systems evaluated against the same training and test data. It achieves a 10.87{%} WER for complete full diacritization including lexical and syntactic diacritization, and 3.0{%} WER for lexical diacritization, ignoring syntactic diacritization. |
| Tasks | Arabic Text Diacritization, Language Modelling, Machine Translation, Morphological Analysis, Transliteration, Word Sense Disambiguation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1321/ |
| https://www.aclweb.org/anthology/W17-1321 | |
| PWC | https://paperswithcode.com/paper/a-layered-language-model-based-hybrid |
| Repo | |
| Framework | |
The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2017
| Title | The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2017 |
| Authors | Ngoc-Quan Pham, Jan Niehues, Thanh-Le Ha, Eunah Cho, Matthias Sperber, Alex Waibel, er |
| Abstract | |
| Tasks | Domain Adaptation, Machine Translation, Tokenization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4736/ |
| https://www.aclweb.org/anthology/W17-4736 | |
| PWC | https://paperswithcode.com/paper/the-karlsruhe-institute-of-technology-systems-2 |
| Repo | |
| Framework | |
Japanese Sentence Compression with a Large Training Dataset
| Title | Japanese Sentence Compression with a Large Training Dataset |
| Authors | Shun Hasegawa, Yuta Kikuchi, Hiroya Takamura, Manabu Okumura |
| Abstract | In English, high-quality sentence compression models by deleting words have been trained on automatically created large training datasets. We work on Japanese sentence compression by a similar approach. To create a large Japanese training dataset, a method of creating English training dataset is modified based on the characteristics of the Japanese language. The created dataset is used to train Japanese sentence compression models based on the recurrent neural network. |
| Tasks | Sentence Compression |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2044/ |
| https://www.aclweb.org/anthology/P17-2044 | |
| PWC | https://paperswithcode.com/paper/japanese-sentence-compression-with-a-large |
| Repo | |
| Framework | |
Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text
| Title | Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text |
| Authors | Desh Raj, SUNIL SAHU, Ashish Anand |
| Abstract | |
| Tasks | Dependency Parsing, Feature Engineering, Morphological Analysis, Relation Classification, Relation Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/papers/K17-1032/k17-1032 |
| https://www.aclweb.org/anthology/K17-1032 | |
| PWC | https://paperswithcode.com/paper/learning-local-and-global-contexts-using-a |
| Repo | |
| Framework | |
Incorporating Word Reordering Knowledge into Attention-based Neural Machine Translation
| Title | Incorporating Word Reordering Knowledge into Attention-based Neural Machine Translation |
| Authors | Jinchao Zhang, Mingxuan Wang, Qun Liu, Jie Zhou |
| Abstract | This paper proposes three distortion models to explicitly incorporate the word reordering knowledge into attention-based Neural Machine Translation (NMT) for further improving translation performance. Our proposed models enable attention mechanism to attend to source words regarding both the semantic requirement and the word reordering penalty. Experiments on Chinese-English translation show that the approaches can improve word alignment quality and achieve significant translation improvements over a basic attention-based NMT by large margins. Compared with previous works on identical corpora, our system achieves the state-of-the-art performance on translation quality. |
| Tasks | Machine Translation, Word Alignment |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1140/ |
| https://www.aclweb.org/anthology/P17-1140 | |
| PWC | https://paperswithcode.com/paper/incorporating-word-reordering-knowledge-into |
| Repo | |
| Framework | |
A tool for extracting sense-disambiguated example sentences through user feedback
| Title | A tool for extracting sense-disambiguated example sentences through user feedback |
| Authors | Beto Boullosa, Richard Eckart de Castilho, Alex Geyken, er, Lothar Lemnitzer, Iryna Gurevych |
| Abstract | This paper describes an application system aimed to help lexicographers in the extraction of example sentences for a given headword based on its different senses. The tool uses classification and clustering methods and incorporates user feedback to refine its results. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3018/ |
| https://www.aclweb.org/anthology/E17-3018 | |
| PWC | https://paperswithcode.com/paper/a-tool-for-extracting-sense-disambiguated |
| Repo | |
| Framework | |
