Paper Group NANR 74
Profiling Medical Journal Articles Using a Gene Ontology Semantic Tagger. Turku Neural Parser Pipeline: An End-to-End System for the CoNLL 2018 Shared Task. A Morphological Analyzer for Shipibo-Konibo. UZH@SMM4H: System Descriptions. An Evaluation of Lexicon-based Sentiment Analysis Techniques for the Plays of Gotthold Ephraim Lessing. Knowledge as …
Profiling Medical Journal Articles Using a Gene Ontology Semantic Tagger
| Title | Profiling Medical Journal Articles Using a Gene Ontology Semantic Tagger |
| Authors | Mahmoud El-Haj, Paul Rayson, Scott Piao, Jo Knight |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1726/ |
| https://www.aclweb.org/anthology/L18-1726 | |
| PWC | https://paperswithcode.com/paper/profiling-medical-journal-articles-using-a |
| Repo | |
| Framework | |
Turku Neural Parser Pipeline: An End-to-End System for the CoNLL 2018 Shared Task
| Title | Turku Neural Parser Pipeline: An End-to-End System for the CoNLL 2018 Shared Task |
| Authors | Jenna Kanerva, Filip Ginter, Niko Miekka, Akseli Leino, Tapio Salakoski |
| Abstract | In this paper we describe the TurkuNLP entry at the CoNLL 2018 Shared Task on Multilingual Parsing from Raw Text to Universal Dependencies. Compared to the last year, this year the shared task includes two new main metrics to measure the morphological tagging and lemmatization accuracies in addition to syntactic trees. Basing our motivation into these new metrics, we developed an end-to-end parsing pipeline especially focusing on developing a novel and state-of-the-art component for lemmatization. Our system reached the highest aggregate ranking on three main metrics out of 26 teams by achieving 1st place on metric involving lemmatization, and 2nd on both morphological tagging and parsing. |
| Tasks | Lemmatization, Machine Translation, Morphological Tagging, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-2013/ |
| https://www.aclweb.org/anthology/K18-2013 | |
| PWC | https://paperswithcode.com/paper/turku-neural-parser-pipeline-an-end-to-end |
| Repo | |
| Framework | |
A Morphological Analyzer for Shipibo-Konibo
| Title | A Morphological Analyzer for Shipibo-Konibo |
| Authors | Ronald Cardenas, Daniel Zeman |
| Abstract | We present a fairly complete morphological analyzer for Shipibo-Konibo, a low-resourced native language spoken in the Amazonian region of Peru. We resort to the robustness of finite-state systems in order to model the complex morphosyntax of the language. Evaluation over raw corpora shows promising coverage of grammatical phenomena, limited only by the scarce lexicon. We make this tool freely available so as to aid the production of annotated corpora and impulse further research in native languages of Peru. |
| Tasks | Lemmatization, Machine Translation, Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5815/ |
| https://www.aclweb.org/anthology/W18-5815 | |
| PWC | https://paperswithcode.com/paper/a-morphological-analyzer-for-shipibo-konibo |
| Repo | |
| Framework | |
UZH@SMM4H: System Descriptions
| Title | UZH@SMM4H: System Descriptions |
| Authors | Tilia Ellendorff, Joseph Cornelius, Heath Gordon, Nicola Colic, Fabio Rinaldi |
| Abstract | Our team at the University of Z{"u}rich participated in the first 3 of the 4 sub-tasks at the Social Media Mining for Health Applications (SMM4H) shared task. We experimented with different approaches for text classification, namely traditional feature-based classifiers (Logistic Regression and Support Vector Machines), shallow neural networks, RCNNs, and CNNs. This system description paper provides details regarding the different system architectures and the achieved results. |
| Tasks | Document Classification, Lemmatization, Part-Of-Speech Tagging, Text Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5916/ |
| https://www.aclweb.org/anthology/W18-5916 | |
| PWC | https://paperswithcode.com/paper/uzhsmm4h-system-descriptions |
| Repo | |
| Framework | |
An Evaluation of Lexicon-based Sentiment Analysis Techniques for the Plays of Gotthold Ephraim Lessing
| Title | An Evaluation of Lexicon-based Sentiment Analysis Techniques for the Plays of Gotthold Ephraim Lessing |
| Authors | Thomas Schmidt, Manuel Burghardt |
| Abstract | We present results from a project in the research area of sentiment analysis of drama texts, more concretely the plays of Gotthold Ephraim Lessing. We conducted an annotation study to create a gold standard for a systematic evaluation. The gold standard consists of 200 speeches of Lessing{'}s plays manually annotated with sentiment information. We explore the performance of different German sentiment lexicons and processing configurations like lemmatization, the extension of lexicons with historical linguistic variants or stop words elimination to explore the influence of these parameters and find best practices for our domain of application. The best performing configuration accomplishes an accuracy of 70{%}. We discuss the problems and challenges for sentiment analysis in this area and describe our next steps toward further research. |
| Tasks | Lemmatization, Sentiment Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4516/ |
| https://www.aclweb.org/anthology/W18-4516 | |
| PWC | https://paperswithcode.com/paper/an-evaluation-of-lexicon-based-sentiment |
| Repo | |
| Framework | |
Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge
| Title | Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge |
| Authors | Yang Deng, Ying Shen, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei |
| Abstract | Answer selection is an important but challenging task. Significant progresses have been made in domains where a large amount of labeled training data is available. However, obtaining rich annotated data is a time-consuming and expensive process, creating a substantial barrier for applying answer selection models to a new domain which has limited labeled data. In this paper, we propose Knowledge-aware Attentive Network (KAN), a transfer learning framework for cross-domain answer selection, which uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domains. Specifically, we design a knowledge module to integrate the knowledge-based representational learning into answer selection models. The learned knowledge-based representations are shared by source and target domains, which not only leverages large amounts of cross-domain data, but also benefits from a regularization effect that leads to more general representations to help tasks in new domains. To verify the effectiveness of our model, we use SQuAD-T dataset as the source domain and three other datasets (i.e., Yahoo QA, TREC QA and InsuranceQA) as the target domains. The experimental results demonstrate that KAN has remarkable applicability and generality, and consistently outperforms the strong competitors by a noticeable margin for cross-domain answer selection. |
| Tasks | Answer Selection, Information Retrieval, Question Answering, Reading Comprehension, Transfer Learning |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1279/ |
| https://www.aclweb.org/anthology/C18-1279 | |
| PWC | https://paperswithcode.com/paper/knowledge-as-a-bridge-improving-cross-domain |
| Repo | |
| Framework | |
Local String Transduction as Sequence Labeling
| Title | Local String Transduction as Sequence Labeling |
| Authors | Joana Ribeiro, Shashi Narayan, Shay B. Cohen, Xavier Carreras |
| Abstract | We show that the general problem of string transduction can be reduced to the problem of sequence labeling. While character deletion and insertions are allowed in string transduction, they do not exist in sequence labeling. We show how to overcome this difference. Our approach can be used with any sequence labeling algorithm and it works best for problems in which string transduction imposes a strong notion of locality (no long range dependencies). We experiment with spelling correction for social media, OCR correction, and morphological inflection, and we see that it behaves better than seq2seq models and yields state-of-the-art results in several cases. |
| Tasks | Lemmatization, Machine Translation, Morphological Inflection, Named Entity Recognition, Optical Character Recognition, Part-Of-Speech Tagging, Semantic Role Labeling, Spelling Correction |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1115/ |
| https://www.aclweb.org/anthology/C18-1115 | |
| PWC | https://paperswithcode.com/paper/local-string-transduction-as-sequence |
| Repo | |
| Framework | |
Semi-Supervised Deep Learning with Memory
| Title | Semi-Supervised Deep Learning with Memory |
| Authors | Yanbei Chen, Xiatian Zhu, Shaogang Gong |
| Abstract | We consider the semi-supervised multi-class classification problem of learning from sparse labelled and abundant unlabelled training data. To address this problem, existing semi-supervised deep learning methods often rely on the up-to-date ânetwork-in-trainingâ to formulate the semi-supervised learning objective. This ignores both the discriminative feature representation and the model inference uncertainty revealed by the network in the preceding learning iterations, referred to as the memory of model learning. In this work, we propose a novel Memory-Assisted Deep Neural Network (MA-DNN) capable of exploiting the memory of model learning to enable semi-supervised learning. Specifically, we introduce a memory mechanism into the network training process as an assimilation-accommodation interaction between the network and an external memory module. Experiments demonstrate the advantages of the proposed MA-DNN model over the state-of-the-art semi-supervised deep learning methods on three image classification benchmark datasets: SVHN, CIFAR10, and CIFAR100. |
| Tasks | Image Classification |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yanbei_Chen_Semi-Supervised_Deep_Learning_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yanbei_Chen_Semi-Supervised_Deep_Learning_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-deep-learning-with-memory |
| Repo | |
| Framework | |
Linguistic representations in multi-task neural networks for ellipsis resolution
| Title | Linguistic representations in multi-task neural networks for ellipsis resolution |
| Authors | Ola R{\o}nning, Daniel Hardt, Anders S{\o}gaard |
| Abstract | Sluicing resolution is the task of identifying the antecedent to a question ellipsis. Antecedents are often sentential constituents, and previous work has therefore relied on syntactic parsing, together with complex linguistic features. A recent model instead used partial parsing as an auxiliary task in sequential neural network architectures to inject syntactic information. We explore the linguistic information being brought to bear by such networks, both by defining subsets of the data exhibiting relevant linguistic characteristics, and by examining the internal representations of the network. Both perspectives provide evidence for substantial linguistic knowledge being deployed by the neural networks. |
| Tasks | Multi-Task Learning |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5409/ |
| https://www.aclweb.org/anthology/W18-5409 | |
| PWC | https://paperswithcode.com/paper/linguistic-representations-in-multi-task |
| Repo | |
| Framework | |
A Simple End-to-End Question Answering Model for Product Information
| Title | A Simple End-to-End Question Answering Model for Product Information |
| Authors | Tuan Lai, Trung Bui, Sheng Li, Nedim Lipka |
| Abstract | When evaluating a potential product purchase, customers may have many questions in mind. They want to get adequate information to determine whether the product of interest is worth their money. In this paper we present a simple deep learning model for answering questions regarding product facts and specifications. Given a question and a product specification, the model outputs a score indicating their relevance. To train and evaluate our proposed model, we collected a dataset of 7,119 questions that are related to 153 different products. Experimental results demonstrate that {–}despite its simplicity{–} the performance of our model is shown to be comparable to a more complex state-of-the-art baseline. |
| Tasks | Answer Selection, Question Answering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3105/ |
| https://www.aclweb.org/anthology/W18-3105 | |
| PWC | https://paperswithcode.com/paper/a-simple-end-to-end-question-answering-model |
| Repo | |
| Framework | |
Deep Boosting for Image Denoising
| Title | Deep Boosting for Image Denoising |
| Authors | Chang Chen, Zhiwei Xiong, Xinmei Tian, Feng Wu |
| Abstract | Boosting is a classic algorithm which has been successfully applied to diverse computer vision tasks. In the scenario of image denoising, however, the existing boosting algorithms are surpassed by the emerging learning-based models. In this paper, we propose a novel deep boosting framework (DBF) for denoising, which integrates several convolutional networks in a feed-forward fashion. Along with the integrated networks, however, the depth of the boosting framework is substantially increased, which brings difficulty to training. To solve this problem, we introduce the concept of dense connection that overcomes the vanishing of gradients during training. Furthermore, we propose a path-widening fusion scheme cooperated with the dilated convolution to derive a lightweight yet efficient convolutional network as the boosting unit, named Dilated Dense Fusion Network (DDFN). Comprehensive experiments demonstrate that our DBF outperforms existing methods on widely used benchmarks, in terms of different denoising tasks. |
| Tasks | Denoising, Image Denoising |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Chang_Chen_Deep_Boosting_for_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Chang_Chen_Deep_Boosting_for_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-boosting-for-image-denoising |
| Repo | |
| Framework | |
CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
| Title | CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies |
| Authors | Daniel Zeman, Jan Haji{\v{c}}, Martin Popel, Martin Potthast, Milan Straka, Filip Ginter, Joakim Nivre, Slav Petrov |
| Abstract | Every year, the Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets. In 2018, one of two tasks was devoted to learning dependency parsers for a large number of languages, in a real-world setting without any gold-standard annotation on test input. All test sets followed a unified annotation scheme, namely that of Universal Dependencies. This shared task constitutes a 2nd edition{—}the first one took place in 2017 (Zeman et al., 2017); the main metric from 2017 has been kept, allowing for easy comparison, also in 2018, and two new main metrics have been used. New datasets added to the Universal Dependencies collection between mid-2017 and the spring of 2018 have contributed to increased difficulty of the task this year. In this overview paper, we define the task and the updated evaluation methodology, describe data preparation, report and analyze the main results, and provide a brief categorization of the different approaches of the participating systems. |
| Tasks | Dependency Parsing, Morphological Analysis, Part-Of-Speech Tagging, Tokenization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-2001/ |
| https://www.aclweb.org/anthology/K18-2001 | |
| PWC | https://paperswithcode.com/paper/conll-2018-shared-task-multilingual-parsing |
| Repo | |
| Framework | |
Beyond Grobner Bases: Basis Selection for Minimal Solvers
| Title | Beyond Grobner Bases: Basis Selection for Minimal Solvers |
| Authors | Viktor Larsson, Magnus Oskarsson, Kalle Astrom, Alge Wallis, Zuzana Kukelova, Tomas Pajdla |
| Abstract | Many computer vision applications require robust estimation of the underlying geometry, in terms of camera motion and 3D structure of the scene. These robust methods often rely on running minimal solvers in a RANSAC framework. In this paper we show how we can make polynomial solvers based on the action matrix method faster, by careful selection of the monomial bases. These monomial bases have traditionally been based on a Grobner basis for the polynomial ideal. Here we describe how we can enumerate all such bases in an efficient way. We also show that going beyond Grobner bases leads to more efficient solvers in many cases. We present a novel basis sampling scheme that we evaluate on a number of problems. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Larsson_Beyond_Grobner_Bases_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Larsson_Beyond_Grobner_Bases_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-grobner-bases-basis-selection-for |
| Repo | |
| Framework | |
Movie recommender system with metaheuristic artificial bee
| Title | Movie recommender system with metaheuristic artificial bee |
| Authors | Rahul Katarya |
| Abstract | Recommender systems are information retrieval tool that allocates accurate recommendations to the specific users. Collaborative movie recommender systems support users in accessing their popular movies by suggesting similar users or movies from their past common ratings. In this research work, a hybrid recommender system has been proposed which utilized k-means clustering algorithm with bio-inspired artificial bee colony (ABC) optimization technique and applied to the Movielens dataset. Our proposed system has been described systematic manner, and the subsequent results have been demonstrated. The proposed system (ABC-KM) is also compared with existing approaches, and the consequences have been examined. Estimation procedures such as precision, mean absolute error, recall, and accuracy for the movie recommender system delivered improved results for ABC-KM collaborative movie recommender system. The experiment outcomes on Movielens dataset established that the projected system provides immense achievement regarding scalability, performance and delivers accurate personalized movie recommendations by reducing cold start problem. As far as our best research knowledge, our proposed recommender system is novel and delivers effective fallouts when compared with already existing systems. |
| Tasks | Information Retrieval, Recommendation Systems |
| Published | 2018-01-06 |
| URL | https://doi.org/10.1007/s0051-017-3338-4 |
| https://doi.org/10.1007/s0051-017-3338-4 | |
| PWC | https://paperswithcode.com/paper/movie-recommender-system-with-metaheuristic |
| Repo | |
| Framework | |
Countering Position Bias in Instructor Interventions in MOOC Discussion Forums
| Title | Countering Position Bias in Instructor Interventions in MOOC Discussion Forums |
| Authors | Muthu Kumar Chandrasekaran, Min-Yen Kan |
| Abstract | |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/papers/W18-3720/w18-3720 |
| https://www.aclweb.org/anthology/W18-3720v2 | |
| PWC | https://paperswithcode.com/paper/countering-position-bias-in-instructor |
| Repo | |
| Framework | |
