Paper Group NAWR 16
Multilingual Semantic Parsing And Code-Switching. MinIE: Minimizing Facts in Open Information Extraction. A Consolidated Open Knowledge Representation for Multiple Texts. Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing. Multichannel sleep spindle detection using sparse low-rank optimization. We Built a Fake News / Cli …
Multilingual Semantic Parsing And Code-Switching
| Title | Multilingual Semantic Parsing And Code-Switching |
| Authors | Long Duong, Hadi Afshar, Dominique Estival, Glen Pink, Philip Cohen, Mark Johnson |
| Abstract | Extending semantic parsing systems to new domains and languages is a highly expensive, time-consuming process, so making effective use of existing resources is critical. In this paper, we describe a transfer learning method using crosslingual word embeddings in a sequence-to-sequence model. On the NLmaps corpus, our approach achieves state-of-the-art accuracy of 85.7{%} for English. Most importantly, we observed a consistent improvement for German compared with several baseline domain adaptation techniques. As a by-product of this approach, our models that are trained on a combination of English and German utterances perform reasonably well on code-switching utterances which contain a mixture of English and German, even though the training data does not contain any such. As far as we know, this is the first study of code-switching in semantic parsing. We manually constructed the set of code-switching test utterances for the NLmaps corpus and achieve 78.3{%} accuracy on this dataset. |
| Tasks | Domain Adaptation, Semantic Parsing, Transfer Learning, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1038/ |
| https://www.aclweb.org/anthology/K17-1038 | |
| PWC | https://paperswithcode.com/paper/multilingual-semantic-parsing-and-code |
| Repo | https://github.com/vbtagitlab/code-switching |
| Framework | none |
MinIE: Minimizing Facts in Open Information Extraction
| Title | MinIE: Minimizing Facts in Open Information Extraction |
| Authors | Kiril Gashteovski, Rainer Gemulla, Luciano del Corro |
| Abstract | The goal of Open Information Extraction (OIE) is to extract surface relations and their arguments from natural-language text in an unsupervised, domain-independent manner. In this paper, we propose MinIE, an OIE system that aims to provide useful, compact extractions with high precision and recall. MinIE approaches these goals by (1) representing information about polarity, modality, attribution, and quantities with semantic annotations instead of in the actual extraction, and (2) identifying and removing parts that are considered overly specific. We conducted an experimental study with several real-world datasets and found that MinIE achieves competitive or higher precision and recall than most prior systems, while at the same time producing shorter, semantically enriched extractions. |
| Tasks | Open Information Extraction, Question Answering, Relation Extraction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1278/ |
| https://www.aclweb.org/anthology/D17-1278 | |
| PWC | https://paperswithcode.com/paper/minie-minimizing-facts-in-open-information |
| Repo | https://github.com/uma-pi1/minie |
| Framework | none |
A Consolidated Open Knowledge Representation for Multiple Texts
| Title | A Consolidated Open Knowledge Representation for Multiple Texts |
| Authors | Rachel Wities, Vered Shwartz, Gabriel Stanovsky, Meni Adler, Ori Shapira, Shyam Upadhyay, Dan Roth, Eugenio Martinez Camara, Iryna Gurevych, Ido Dagan |
| Abstract | We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner. We do so by consolidating OIE extractions using entity and predicate coreference, while modeling information containment between coreferring elements via lexical entailment. We suggest that generating OKR structures can be a useful step in the NLP pipeline, to give semantic applications an easy handle on consolidated information across multiple texts. |
| Tasks | Open Information Extraction |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0902/ |
| https://www.aclweb.org/anthology/W17-0902 | |
| PWC | https://paperswithcode.com/paper/a-consolidated-open-knowledge-representation |
| Repo | https://github.com/vered1986/OKR |
| Framework | none |
Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing
| Title | Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing |
| Authors | Anssi Yli-Jyr{"a}, Carlos G{'o}mez-Rodr{'\i}guez |
| Abstract | We present a simple encoding for unlabeled noncrossing graphs and show how its latent counterpart helps us to represent several families of directed and undirected graphs used in syntactic and semantic parsing of natural language as context-free languages. The families are separated purely on the basis of forbidden patterns in latent encoding, eliminating the need to differentiate the families of non-crossing graphs in inference algorithms: one algorithm works for all when the search space can be controlled in parser input. |
| Tasks | Dependency Parsing, Semantic Parsing |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1160/ |
| https://www.aclweb.org/anthology/P17-1160 | |
| PWC | https://paperswithcode.com/paper/generic-axiomatization-of-families-of |
| Repo | https://github.com/amikael/ncdigraphs |
| Framework | none |
Multichannel sleep spindle detection using sparse low-rank optimization
| Title | Multichannel sleep spindle detection using sparse low-rank optimization |
| Authors | Ankit Parekha, Ivan W. Selesnick, Ricardo S.Osorio, Andrew W. Vargad, David M. Rapoport, Indu Ayappa |
| Abstract | BACKGROUND: Automated single-channel spindle detectors, for human sleep EEG, are blind to the presence of spindles in other recorded channels unlike visual annotation by a human expert. NEW METHOD: We propose a multichannel spindle detection method that aims to detect global and local spindle activity in human sleep EEG. Using a non-linear signal model, which assumes the input EEG to be the sum of a transient and an oscillatory component, we propose a multichannel transient separation algorithm. Consecutive overlapping blocks of the multichannel oscillatory component are assumed to be low-rank whereas the transient component is assumed to be piecewise constant with a zero baseline. The estimated oscillatory component is used in conjunction with a bandpass filter and the Teager operator for detecting sleep spindles. RESULTS AND COMPARISON WITH OTHER METHODS: The proposed method is applied to two publicly available databases and compared with 7 existing single-channel automated detectors. F1 scores for the proposed spindle detection method averaged 0.66 (0.02) and 0.62 (0.06) for the two databases, respectively. For an overnight 6 channel EEG signal, the proposed algorithm takes about 4min to detect sleep spindles simultaneously across all channels with a single setting of corresponding algorithmic parameters. CONCLUSIONS: The proposed method attempts to mimic and utilize, for better spindle detection, a particular human expert behavior where the decision to mark a spindle event may be subconsciously influenced by the presence of a spindle in EEG channels other than the central channel visible on a digital screen. |
| Tasks | EEG, Spindle Detection |
| Published | 2017-08-15 |
| URL | https://doi.org/10.1016/j.jneumeth.2017.06.004 |
| https://www.researchgate.net/publication/317533757_Multichannel_Sleep_Spindle_Detection_using_Sparse_Low-Rank_Optimization | |
| PWC | https://paperswithcode.com/paper/multichannel-sleep-spindle-detection-using |
| Repo | https://github.com/aparek/mcsleep |
| Framework | none |
We Built a Fake News / Click Bait Filter: What Happened Next Will Blow Your Mind!
| Title | We Built a Fake News / Click Bait Filter: What Happened Next Will Blow Your Mind! |
| Authors | Georgi Karadzhov, Pepa Gencheva, Preslav Nakov, Ivan Koychev |
| Abstract | It is completely amazing! Fake news and {``}click baits{''} have totally invaded the cyberspace. Let us face it: everybody hates them for three simple reasons. Reason {#}2 will absolutely amaze you. What these can achieve at the time of election will completely blow your mind! Now, we all agree, this cannot go on, you know, somebody has to stop it. So, we did this research, and trust us, it is totally great research, it really is! Make no mistake. This is the best research ever! Seriously, come have a look, we have it all: neural networks, attention mechanism, sentiment lexicons, author profiling, you name it. Lexical features, semantic features, we absolutely have it all. And we have totally tested it, trust us! We have results, and numbers, really big numbers. The best numbers ever! Oh, and analysis, absolutely top notch analysis. Interested? Come read the shocking truth about fake news and clickbait in the Bulgarian cyberspace. You won{'}t believe what we have found! | |
| Tasks | Clickbait Detection, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1045/ |
| https://doi.org/10.26615/978-954-452-049-6_045 | |
| PWC | https://paperswithcode.com/paper/we-built-a-fake-news-click-bait-filter-what-1 |
| Repo | https://github.com/gkaradzhov/ClickbaitRANLP |
| Framework | none |
Deep Semantic Role Labeling: What Works and What’s Next
| Title | Deep Semantic Role Labeling: What Works and What’s Next |
| Authors | Luheng He, Kenton Lee, Mike Lewis, Luke Zettlemoyer |
| Abstract | We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use a deep highway BiLSTM architecture with constrained decoding, while observing a number of recent best practices for initialization and regularization. Our 8-layer ensemble model achieves 83.2 F1 on theCoNLL 2005 test set and 83.4 F1 on CoNLL 2012, roughly a 10{%} relative error reduction over the previous state of the art. Extensive empirical analysis of these gains show that (1) deep models excel at recovering long-distance dependencies but can still make surprisingly obvious errors, and (2) that there is still room for syntactic parsers to improve these results. |
| Tasks | Predicate Detection, Semantic Role Labeling |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1044/ |
| https://www.aclweb.org/anthology/P17-1044 | |
| PWC | https://paperswithcode.com/paper/deep-semantic-role-labeling-what-works-and |
| Repo | https://github.com/luheng/deep_srl |
| Framework | none |
Intelligent Assistant for People with Low Vision Abilities
| Title | Intelligent Assistant for People with Low Vision Abilities |
| Authors | Oleksandr Bogdan, Oleg Yurchenko, Oleksandr Bailo, Francois Rameau, Donggeun Yoo, In So Kweon |
| Abstract | This paper proposes a wearable system for visually impaired people that can be utilized to obtain an extensive feedback about their surrounding environment. Our system consists of a stereo camera and smartglasses, communicating with a smartphone that is used as an intermediary computational device. Furthermore, the system is connected to a server where all the expensive computations are executed. The whole setup is capable of detecting obstacles in the nearest surrounding, recognizing faces and facial expressions, reading texts, providing a generic description and question answering of a particular input image. In addition , we propose a novel depth question answering system to estimate object size as well as objects relative position in an unconstrained environment in near real-time and in a fully automatic way requiring only stereo image pair and voice request as an input. We have conducted a series of experiments to evaluate the feasibility and practicality of the proposed system which shows promising results to assist visually impaired people. |
| Tasks | Question Answering |
| Published | 2017-11-20 |
| URL | https://bit.ly/2m0GFDp |
| https://bit.ly/2mgk6L7 | |
| PWC | https://paperswithcode.com/paper/intelligent-assistant-for-people-with-low |
| Repo | https://github.com/BAILOOL/Assistant-for-People-with-Low-Vision |
| Framework | tf |
Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG
| Title | Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG |
| Authors | Fernando Andreotti, Oliver Carr, Marco A. F. Pimentel, Adam Mahdi, Maarten De Vos |
| Abstract | The diagnosis of cardiovascular diseases such as atrial fibrillation (AF) is a lengthy and expensive procedure that often requires visual inspection of ECG signals by experts. In order to improve patient management and reduce healthcare costs, automated detection of these pathologies is of utmost importance. In this study, we classify short segments of ECG into four classes (AF, normal, other rhythms or noise) as part of the Physionet/Computing in Cardiology Challenge 2017. We compare a state-of-the-art feature-based classifier with a convolutional neural network approach. Both methods were trained using the challenge data, supplemented with an additional database derived from Physionet. The feature-based classifier obtained an F1 score of 72.0% on the training set (5-fold cross-validation), and 79% on the hidden test set. Similarly, the convolutional neural network scored 72.1% on the augmented database and 83% on the test set. The latter method resulted on a final score of 79% at the competition. Developed routines and pre-trained models are freely available under a GNU GPLv3 license. |
| Tasks | Arrhythmia Detection, Electrocardiography (ECG) |
| Published | 2017-09-24 |
| URL | https://doi.org/10.22489/CinC.2017.360-239 |
| http://prucka.com/2017CinC/pdf/360-239.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-feature-based-classifiers-and |
| Repo | https://github.com/fernandoandreotti/cinc-challenge2017 |
| Framework | none |
Annotating omission in statement pairs
| Title | Annotating omission in statement pairs |
| Authors | H{'e}ctor Mart{'\i}nez Alonso, Amaury Delamaire, Beno{^\i}t Sagot |
| Abstract | We focus on the identification of omission in statement pairs. We compare three annotation schemes, namely two different crowdsourcing schemes and manual expert annotation. We show that the simplest of the two crowdsourcing approaches yields a better annotation quality than the more complex one. We use a dedicated classifier to assess whether the annotators{'} behavior can be explained by straightforward linguistic features. The classifier benefits from a modeling that uses lexical information beyond length and overlap measures. However, for our task, we argue that expert and not crowdsourcing-based annotation is the best compromise between annotation cost and quality. |
| Tasks | Natural Language Inference |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0805/ |
| https://www.aclweb.org/anthology/W17-0805 | |
| PWC | https://paperswithcode.com/paper/annotating-omission-in-statement-pairs |
| Repo | https://github.com/hectormartinez/verdidata |
| Framework | none |
A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark Detection
| Title | A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark Detection |
| Authors | Jiangjing Lv, Xiaohu Shao, Junliang Xing, Cheng Cheng, Xi Zhou |
| Abstract | Regression based facial landmark detection methods usually learns a series of regression functions to update the landmark positions from an initial estimation. Most of existing approaches focus on learning effective mapping functions with robust image features to improve performance. The approach to dealing with the initialization issue, however, receives relatively fewer attentions. In this paper, we present a deep regression architecture with two-stage re-initialization to explicitly deal with the initialization problem. At the global stage, given an image with a rough face detection result, the full face region is firstly re-initialized by a supervised spatial transformer network to a canonical shape state and then trained to regress a coarse landmark estimation. At the local stage, different face parts are further separately re-initialized to their own canonical shape states, followed by another regression subnetwork to get the final estimation. Our proposed deep architecture is trained from end to end and obtains promising results using different kinds of unstable initialization. It also achieves superior performances over many competing algorithms. |
| Tasks | Face Detection, Facial Landmark Detection |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Lv_A_Deep_Regression_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Lv_A_Deep_Regression_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-regression-architecture-with-two-stage |
| Repo | https://github.com/shaoxiaohu/Face_Alignment_Two_Stage_Re-initialization |
| Framework | none |
Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages
| Title | Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages |
| Authors | Michael Schlichtkrull, Anders S{\o}gaard |
| Abstract | In cross-lingual dependency annotation projection, information is often lost during transfer because of early decoding. We present an end-to-end graph-based neural network dependency parser that can be trained to reproduce matrices of edge scores, which can be directly projected across word alignments. We show that our approach to cross-lingual dependency parsing is not only simpler, but also achieves an absolute improvement of 2.25{%} averaged across 10 languages compared to the previous state of the art. |
| Tasks | Dependency Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1021/ |
| https://www.aclweb.org/anthology/E17-1021 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-dependency-parsing-with-late-1 |
| Repo | https://github.com/MichSchli/Tensor-LSTM |
| Framework | none |
Word Ordering as Unsupervised Learning Towards Syntactically Plausible Word Representations
| Title | Word Ordering as Unsupervised Learning Towards Syntactically Plausible Word Representations |
| Authors | Noriki Nishida, Hideki Nakayama |
| Abstract | The research question we explore in this study is how to obtain syntactically plausible word representations without using human annotations. Our underlying hypothesis is that word ordering tests, or linearizations, is suitable for learning syntactic knowledge about words. To verify this hypothesis, we develop a differentiable model called Word Ordering Network (WON) that explicitly learns to recover correct word order while implicitly acquiring word embeddings representing syntactic knowledge. We evaluate the word embeddings produced by the proposed method on downstream syntax-related tasks such as part-of-speech tagging and dependency parsing. The experimental results demonstrate that the WON consistently outperforms both order-insensitive and order-sensitive baselines on these tasks. |
| Tasks | Dependency Parsing, Part-Of-Speech Tagging, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1008/ |
| https://www.aclweb.org/anthology/I17-1008 | |
| PWC | https://paperswithcode.com/paper/word-ordering-as-unsupervised-learning |
| Repo | https://github.com/norikinishida/won |
| Framework | none |
Error Analysis of Cross-lingual Tagging and Parsing
| Title | Error Analysis of Cross-lingual Tagging and Parsing |
| Authors | Rudolf Rosa, Zden{\v{e}}k {\v{Z}}abokrtsk{'y} |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7615/ |
| https://www.aclweb.org/anthology/W17-7615 | |
| PWC | https://paperswithcode.com/paper/error-analysis-of-cross-lingual-tagging-and |
| Repo | https://github.com/ptakopysk/crosssynt |
| Framework | none |
KULeuven-LIIR at SemEval-2017 Task 12: Cross-Domain Temporal Information Extraction from Clinical Records
| Title | KULeuven-LIIR at SemEval-2017 Task 12: Cross-Domain Temporal Information Extraction from Clinical Records |
| Authors | Artuur Leeuwenberg, Marie-Francine Moens |
| Abstract | In this paper, we describe the system of the KULeuven-LIIR submission for Clinical TempEval 2017. We participated in all six subtasks, using a combination of Support Vector Machines (SVM) for event and temporal expression detection, and a structured perceptron for extracting temporal relations. Moreover, we present and analyze the results from our submissions, and verify the effectiveness of several system components. Our system performed above average for all subtasks in both phases. |
| Tasks | Domain Adaptation, Relation Extraction, Temporal Information Extraction, Unsupervised Domain Adaptation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2181/ |
| https://www.aclweb.org/anthology/S17-2181 | |
| PWC | https://paperswithcode.com/paper/kuleuven-liir-at-semeval-2017-task-12-cross |
| Repo | https://github.com/tuur/ClinicalTempEval2017 |
| Framework | none |
