Paper Group NANR 18
SHAKKIL: An Automatic Diacritization System for Modern Standard Arabic Texts. Integrating Order Information and Event Relation for Script Event Prediction. Using NLP for Enhancing Second Language Acquisition. Rational Distortions of Learners’ Linguistic Input. A data-driven model of explanations for a chatbot that helps to practice conversation in …
SHAKKIL: An Automatic Diacritization System for Modern Standard Arabic Texts
| Title | SHAKKIL: An Automatic Diacritization System for Modern Standard Arabic Texts |
| Authors | Amany Fashwan, Sameh Alansary |
| Abstract | This paper sheds light on a system that would be able to diacritize Arabic texts automatically (SHAKKIL). In this system, the diacritization problem will be handled through two levels; morphological and syntactic processing levels. The adopted morphological disambiguation algorithm depends on four layers; Uni-morphological form layer, rule-based morphological disambiguation layer, statistical-based disambiguation layer and Out Of Vocabulary (OOV) layer. The adopted syntactic disambiguation algorithms is concerned with detecting the case ending diacritics depending on a rule based approach simulating the shallow parsing technique. This will be achieved using an annotated corpus for extracting the Arabic linguistic rules, building the language models and testing the system output. This system is considered as a good trial of the interaction between rule-based approach and statistical approach, where the rules can help the statistics in detecting the right diacritization and vice versa. At this point, the morphological Word Error Rate (WER) is 4.56{%} while the morphological Diacritic Error Rate (DER) is 1.88{%} and the syntactic WER is 9.36{%}. The best WER is 14.78{%} compared to the best-published results, of (Abandah, 2015); 11.68{%}, (Rashwan, et al., 2015); 12.90{%} and (Metwally, Rashwan, {&} Atiya, 2016); 13.70{%}. |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1311/ |
| https://www.aclweb.org/anthology/W17-1311 | |
| PWC | https://paperswithcode.com/paper/shakkil-an-automatic-diacritization-system |
| Repo | |
| Framework | |
Integrating Order Information and Event Relation for Script Event Prediction
| Title | Integrating Order Information and Event Relation for Script Event Prediction |
| Authors | Zhongqing Wang, Yue Zhang, Ching-Yun Chang |
| Abstract | There has been a recent line of work automatically learning scripts from unstructured texts, by modeling narrative event chains. While the dominant approach group events using event pair relations, LSTMs have been used to encode full chains of narrative events. The latter has the advantage of learning long-range temporal orders, yet the former is more adaptive to partial orders. We propose a neural model that leverages the advantages of both methods, by using LSTM hidden states as features for event pair modelling. A dynamic memory network is utilized to automatically induce weights on existing events for inferring a subsequent event. Standard evaluation shows that our method significantly outperforms both methods above, giving the best results reported so far. |
| Tasks | Language Modelling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1006/ |
| https://www.aclweb.org/anthology/D17-1006 | |
| PWC | https://paperswithcode.com/paper/integrating-order-information-and-event |
| Repo | |
| Framework | |
Using NLP for Enhancing Second Language Acquisition
| Title | Using NLP for Enhancing Second Language Acquisition |
| Authors | Leonardo Zilio, Rodrigo Wilkens, C{'e}drick Fairon |
| Abstract | This study presents SMILLE, a system that draws on the Noticing Hypothesis and on input enhancements, addressing the lack of salience of grammatical infor mation in online documents chosen by a given user. By means of input enhancements, the system can draw the user{'}s attention to grammar, which could possibly lead to a higher intake per input ratio for metalinguistic information. The system receives as input an online document and submits it to a combined processing of parser and hand-written rules for detecting its grammatical structures. The input text can be freely chosen by the user, providing a more engaging experience and reflecting the user{'}s interests. The system can enhance a total of 107 fine-grained types of grammatical structures that are based on the CEFR. An evaluation of some of those structures resulted in an overall precision of 87{%}. |
| Tasks | Language Acquisition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1107/ |
| https://doi.org/10.26615/978-954-452-049-6_107 | |
| PWC | https://paperswithcode.com/paper/using-nlp-for-enhancing-second-language |
| Repo | |
| Framework | |
Rational Distortions of Learners’ Linguistic Input
| Title | Rational Distortions of Learners’ Linguistic Input |
| Authors | Naomi Feldman |
| Abstract | Language acquisition can be modeled as a statistical inference problem: children use sentences and sounds in their input to infer linguistic structure. However, in many cases, children learn from data whose statistical structure is distorted relative to the language they are learning. Such distortions can arise either in the input itself, or as a result of children{'}s immature strategies for encoding their input. This work examines several cases in which the statistical structure of children{'}s input differs from the language being learned. Analyses show that these distortions of the input can be accounted for with a statistical learning framework by carefully considering the inference problems that learners solve during language acquisition |
| Tasks | Language Acquisition |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1002/ |
| https://www.aclweb.org/anthology/K17-1002 | |
| PWC | https://paperswithcode.com/paper/rational-distortions-of-learners-linguistic |
| Repo | |
| Framework | |
A data-driven model of explanations for a chatbot that helps to practice conversation in a foreign language
| Title | A data-driven model of explanations for a chatbot that helps to practice conversation in a foreign language |
| Authors | Sviatlana H{"o}hn |
| Abstract | This article describes a model of other-initiated self-repair for a chatbot that helps to practice conversation in a foreign language. The model was developed using a corpus of instant messaging conversations between German native and non-native speakers. Conversation Analysis helped to create computational models from a small number of examples. The model has been validated in an AIML-based chatbot. Unlike typical retrieval-based dialogue systems, the explanations are generated at run-time from a linguistic database. |
| Tasks | Chatbot, Language Acquisition |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5547/ |
| https://www.aclweb.org/anthology/W17-5547 | |
| PWC | https://paperswithcode.com/paper/a-data-driven-model-of-explanations-for-a |
| Repo | |
| Framework | |
Neoveille, a Web Platform for Neologism Tracking
| Title | Neoveille, a Web Platform for Neologism Tracking |
| Authors | Emmanuel Cartier |
| Abstract | This paper details a software designed to track neologisms in seven languages through newspapers monitor corpora. The platform combines state-of-the-art processes to track linguistic changes and a web platform for linguists to create and manage their corpora, accept or reject automatically identified neologisms, describe linguistically the accepted neologisms and follow their lifecycle on the monitor corpora. In the following, after a short state-of-the-art in Neologism Retrieval, Analysis and Life-tracking, we describe the overall architecture of the system. The platform can be freely browsed at \url{www.neoveille.org} where detailed presentation is given. Access tothe editing modules is available upon request. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3024/ |
| https://www.aclweb.org/anthology/E17-3024 | |
| PWC | https://paperswithcode.com/paper/neoveille-a-web-platform-for-neologism |
| Repo | |
| Framework | |
Learning Deep Architectures via Generalized Whitened Neural Networks
| Title | Learning Deep Architectures via Generalized Whitened Neural Networks |
| Authors | Ping Luo |
| Abstract | Whitened Neural Network (WNN) is a recent advanced deep architecture, which improves convergence and generalization of canonical neural networks by whitening their internal hidden representation. However, the whitening transformation increases computation time. Unlike WNN that reduced runtime by performing whitening every thousand iterations, which degenerates convergence due to the ill conditioning, we present generalized WNN (GWNN), which has three appealing properties. First, GWNN is able to learn compact representation to reduce computations. Second, it enables whitening transformation to be performed in a short period, preserving good conditioning. Third, we propose a data-independent estimation of the covariance matrix to further improve computational efficiency. Extensive experiments on various datasets demonstrate the benefits of GWNN. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=488 |
| http://proceedings.mlr.press/v70/luo17a/luo17a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-architectures-via-generalized |
| Repo | |
| Framework | |
End to End Dialog System for Telugu
| Title | End to End Dialog System for Telugu |
| Authors | D, Prathyusha a, Prathyusha Jwalapuram, Manish Shrivastava |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7533/ |
| https://www.aclweb.org/anthology/W17-7533 | |
| PWC | https://paperswithcode.com/paper/end-to-end-dialog-system-for-telugu |
| Repo | |
| Framework | |
Language Modeling with Recurrent Highway Hypernetworks
| Title | Language Modeling with Recurrent Highway Hypernetworks |
| Authors | Joseph Suarez |
| Abstract | We present extensive experimental and theoretical support for the efficacy of recurrent highway networks (RHNs) and recurrent hypernetworks complimentary to the original works. Where the original RHN work primarily provides theoretical treatment of the subject, we demonstrate experimentally that RHNs benefit from far better gradient flow than LSTMs in addition to their improved task accuracy. The original hypernetworks work presents detailed experimental results but leaves several theoretical issues unresolved–we consider these in depth and frame several feasible solutions that we believe will yield further gains in the future. We demonstrate that these approaches are complementary: by combining RHNs and hypernetworks, we make a significant improvement over current state-of-the-art character-level language modeling performance on Penn Treebank while relying on much simpler regularization. Finally, we argue for RHNs as a drop-in replacement for LSTMs (analogous to LSTMs for vanilla RNNs) and for hypernetworks as a de-facto augmentation (analogous to attention) for recurrent architectures. |
| Tasks | Language Modelling |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6919-language-modeling-with-recurrent-highway-hypernetworks |
| http://papers.nips.cc/paper/6919-language-modeling-with-recurrent-highway-hypernetworks.pdf | |
| PWC | https://paperswithcode.com/paper/language-modeling-with-recurrent-highway |
| Repo | |
| Framework | |
High-Precision Automated Reconstruction of Neurons with Flood-filling Networks
| Title | High-Precision Automated Reconstruction of Neurons with Flood-filling Networks |
| Authors | Michał Januszewski, Jörgen Kornfeld, Peter H. Li, Art Pope, Tim Blakely, Larry Lindsey, Jeremy Maitin-Shepard, Mike Tyka, Winfried Denk, Viren Jain |
| Abstract | Reconstruction of neural circuits from volume electron microscopy data requires the tracing of complete cells including all their neurites. Automated approaches have been developed to perform the tracing, but without costly human proofreading their error rates are too high to obtain reliable circuit diagrams. We present a method for automated segmentation that, like the majority of previous efforts, employs convolutional neural networks, but contains in addition a recurrent pathway that allows the iterative optimization and extension of the reconstructed shape of individual neural processes. We used this technique, which we call flood-filling networks, to trace neurons in a data set obtained by serial block-face electron microscopy from a male zebra finch brain. Our method achieved a mean error-free neurite path length of 1.1 mm, an order of magnitude better than previously published approaches applied to the same dataset. Only 4 mergers were observed in a neurite test set of 97 mm path length. |
| Tasks | Electron Microscopy Image Segmentation, Image Reconstruction |
| Published | 2017-10-09 |
| URL | https://doi.org/10.1038/s41592-018-0049-4 |
| https://www.biorxiv.org/content/biorxiv/early/2017/10/09/200675.full-text.pdf | |
| PWC | https://paperswithcode.com/paper/high-precision-automated-reconstruction-of |
| Repo | |
| Framework | |
以知識表徵方法建構台語聲調群剖析器 (A Knowledge Representation Method to Implement A Taiwanese Tone Group Parser) [In Chinese]
| Title | 以知識表徵方法建構台語聲調群剖析器 (A Knowledge Representation Method to Implement A Taiwanese Tone Group Parser) [In Chinese] |
| Authors | Yu-Chu Chang |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1001/ |
| https://www.aclweb.org/anthology/O17-1001 | |
| PWC | https://paperswithcode.com/paper/acee-a3413aoaeae2eac34aa-a-knowledge-1 |
| Repo | |
| Framework | |
Recycling Privileged Learning and Distribution Matching for Fairness
| Title | Recycling Privileged Learning and Distribution Matching for Fairness |
| Authors | Novi Quadrianto, Viktoriia Sharmanska |
| Abstract | Equipping machine learning models with ethical and legal constraints is a serious issue; without this, the future of machine learning is at risk. This paper takes a step forward in this direction and focuses on ensuring machine learning models deliver fair decisions. In legal scholarships, the notion of fairness itself is evolving and multi-faceted. We set an overarching goal to develop a unified machine learning framework that is able to handle any definitions of fairness, their combinations, and also new definitions that might be stipulated in the future. To achieve our goal, we recycle two well-established machine learning techniques, privileged learning and distribution matching, and harmonize them for satisfying multi-faceted fairness definitions. We consider protected characteristics such as race and gender as privileged information that is available at training but not at test time; this accelerates model training and delivers fairness through unawareness. Further, we cast demographic parity, equalized odds, and equality of opportunity as a classical two-sample problem of conditional distributions, which can be solved in a general form by using distance measures in Hilbert Space. We show several existing models are special cases of ours. Finally, we advocate returning the Pareto frontier of multi-objective minimization of error and unfairness in predictions. This will facilitate decision makers to select an operating point and to be accountable for it. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6670-recycling-privileged-learning-and-distribution-matching-for-fairness |
| http://papers.nips.cc/paper/6670-recycling-privileged-learning-and-distribution-matching-for-fairness.pdf | |
| PWC | https://paperswithcode.com/paper/recycling-privileged-learning-and |
| Repo | |
| Framework | |
BUSEM at SemEval-2017 Task 4A Sentiment Analysis with Word Embedding and Long Short Term Memory RNN Approaches
| Title | BUSEM at SemEval-2017 Task 4A Sentiment Analysis with Word Embedding and Long Short Term Memory RNN Approaches |
| Authors | Deger Ayata, Murat Saraclar, Arzucan Ozgur |
| Abstract | This paper describes our approach for SemEval-2017 Task 4: Sentiment Analysis in Twitter. We have participated in Subtask A: Message Polarity Classification subtask and developed two systems. The first system uses word embeddings for feature representation and Support Vector Machine, Random Forest and Naive Bayes algorithms for classification of Twitter messages into negative, neutral and positive polarity. The second system is based on Long Short Term Memory Recurrent Neural Networks and uses word indexes as sequence of inputs for feature representation. |
| Tasks | Opinion Mining, Sentiment Analysis, Subjectivity Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2131/ |
| https://www.aclweb.org/anthology/S17-2131 | |
| PWC | https://paperswithcode.com/paper/busem-at-semeval-2017-task-4a-sentiment |
| Repo | |
| Framework | |
Enhancing Drug-Drug Interaction Classification with Corpus-level Feature and Classifier Ensemble
| Title | Enhancing Drug-Drug Interaction Classification with Corpus-level Feature and Classifier Ensemble |
| Authors | Jing Cyun Tu, Po-Ting Lai, Richard Tzong-Han Tsai |
| Abstract | The study of drug-drug interaction (DDI) is important in the drug discovering. Both PubMed and DrugBank are rich resources to retrieve DDI information which is usually represented in plain text. Automatically extracting DDI pairs from text improves the quality of drug discov-ering. In this paper, we presented a study that focuses on the DDI classification. We normalized the drug names, and developed both sentence-level and corpus-level features for DDI classification. A classifier ensemble approach is used for the unbalance DDI labels problem. Our approach achieved an F-score of 65.4{%} on SemEval 2013 DDI test set. The experimental results also show the effects of proposed corpus-level features in the DDI task. |
| Tasks | Feature Engineering, Named Entity Recognition |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5808/ |
| https://www.aclweb.org/anthology/W17-5808 | |
| PWC | https://paperswithcode.com/paper/enhancing-drug-drug-interaction |
| Repo | |
| Framework | |
Classifying Frames at the Sentence Level in News Articles
| Title | Classifying Frames at the Sentence Level in News Articles |
| Authors | Nona Naderi, Graeme Hirst |
| Abstract | Previous approaches to generic frame classification analyze frames at the document level. Here, we propose a supervised based approach based on deep neural networks and distributional representations for classifying frames at the sentence level in news articles. We conduct our experiments on the publicly available Media Frames Corpus compiled from the U.S. Newspapers. Using (B)LSTMs and GRU networks to represent the meaning of frames, we demonstrate that our approach yields at least 14-point improvement over several baseline methods. |
| Tasks | Semantic Textual Similarity, Time Series, Topic Models |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1070/ |
| https://doi.org/10.26615/978-954-452-049-6_070 | |
| PWC | https://paperswithcode.com/paper/classifying-frames-at-the-sentence-level-in |
| Repo | |
| Framework | |
