Paper Group NANR 45
Named Entity Recognition - Is There a Glass Ceiling?. Mobile Robot Navigation Using Fuzzy-GA Approaches Along with Three Path Concept. Adding Linguistic Knowledge to NLP Tasks for Bulgarian: The Verb Paradigm Patterns. BSNLP2019 Shared Task Submission: Multisource Neural NER Transfer. Synthnet: Learning synthesizers end-to-end. CAMOU: Learning Phys …
Named Entity Recognition - Is There a Glass Ceiling?
| Title | Named Entity Recognition - Is There a Glass Ceiling? |
| Authors | Tomasz Stanislawek, Anna Wr{'o}blewska, Alicja W{'o}jcicka, Daniel Ziembicki, Przemyslaw Biecek |
| Abstract | Recent developments in Named Entity Recognition (NER) have resulted in better and better models. However, is there a glass ceiling? Do we know which types of errors are still hard or even impossible to correct? In this paper, we present a detailed analysis of the types of errors in state-of-the-art machine learning (ML) methods. Our study illustrates weak and strong points of the Stanford, CMU, FLAIR, ELMO and BERT models, as well as their shared limitations. We also introduce new techniques for improving annotation, training process, and for checking model quality and stability. |
| Tasks | Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1058/ |
| https://www.aclweb.org/anthology/K19-1058 | |
| PWC | https://paperswithcode.com/paper/named-entity-recognition-is-there-a-glass-1 |
| Repo | |
| Framework | |
Mobile Robot Navigation Using Fuzzy-GA Approaches Along with Three Path Concept
| Title | Mobile Robot Navigation Using Fuzzy-GA Approaches Along with Three Path Concept |
| Authors | Ngangbam Herojit Singh1 • Khelchandra Thongam1 |
| Abstract | This paper presents a technique of navigation of a mobile robot using fuzzy computing and genetic algorithm along with three path concept. The information about the distances and angles of obstacles from the robot is acquired by using the concept of three paths. Fuzzy system is used to avoid obstacles when all the three paths are blocked by obstacles; otherwise, the collision-free path is selected by using three path method. Genetic algorithm is used to find optimal range of the linguistic values of the variables for the membership functions. Results show that the method of using fuzzy-GA along with the three path concept is computationally efficient as compared to other hybrid methods. |
| Tasks | Robot Navigation |
| Published | 2019-06-01 |
| URL | https://doi.org/10.1007/s40998-018-0112-2 |
| https://doi.org/10.1007/s40998-018-0112-2 | |
| PWC | https://paperswithcode.com/paper/mobile-robot-navigation-using-fuzzy-ga |
| Repo | |
| Framework | |
Adding Linguistic Knowledge to NLP Tasks for Bulgarian: The Verb Paradigm Patterns
| Title | Adding Linguistic Knowledge to NLP Tasks for Bulgarian: The Verb Paradigm Patterns |
| Authors | Ivaylo Radev |
| Abstract | This paper discusses some possible usages of one unexplored lexical language resource containing Bulgarian verb paradigms and their English translations. This type of data can be used for machine translation, generation of pseudo corpora/language exercises, and evaluation of parsers. Upon completion, the resource will be linked with other existing resources such as the morphological lexicon, valency lexicon, as well as BTB-WordNet. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2012/ |
| https://www.aclweb.org/anthology/R19-2012 | |
| PWC | https://paperswithcode.com/paper/adding-linguistic-knowledge-to-nlp-tasks-for |
| Repo | |
| Framework | |
BSNLP2019 Shared Task Submission: Multisource Neural NER Transfer
| Title | BSNLP2019 Shared Task Submission: Multisource Neural NER Transfer |
| Authors | Tatiana Tsygankova, Stephen Mayhew, Dan Roth |
| Abstract | This paper describes the Cognitive Computation (CogComp) Group{'}s submissions to the multilingual named entity recognition shared task at the Balto-Slavic Natural Language Processing (BSNLP) Workshop. The final model submitted is a multi-source neural NER system with multilingual BERT embeddings, trained on the concatenation of training data in various Slavic languages (as well as English). The performance of our system on the official testing data suggests that multi-source approaches consistently outperform single-source approaches for this task, even with the noise of mismatching tagsets. |
| Tasks | Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3710/ |
| https://www.aclweb.org/anthology/W19-3710 | |
| PWC | https://paperswithcode.com/paper/bsnlp2019-shared-task-submission-multisource |
| Repo | |
| Framework | |
Synthnet: Learning synthesizers end-to-end
| Title | Synthnet: Learning synthesizers end-to-end |
| Authors | Florin Schimbinschi, Christian Walder, Sarah Erfani, James Bailey |
| Abstract | Learning synthesizers and generating music in the raw audio domain is a challenging task. We investigate the learned representations of convolutional autoregressive generative models. Consequently, we show that mappings between musical notes and the harmonic style (instrument timbre) can be learned based on the raw audio music recording and the musical score (in binary piano roll format). Our proposed architecture, SynthNet uses minimal training data (9 minutes), is substantially better in quality and converges 6 times faster than the baselines. The quality of the generated waveforms (generation accuracy) is sufficiently high that they are almost identical to the ground truth. Therefore, we are able to directly measure generation error during training, based on the RMSE of the Constant-Q transform. Mean opinion scores are also provided. We validate our work using 7 distinct harmonic styles and also provide visualizations and links to all generated audio. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1lUOsA9Fm |
| https://openreview.net/pdf?id=H1lUOsA9Fm | |
| PWC | https://paperswithcode.com/paper/synthnet-learning-synthesizers-end-to-end |
| Repo | |
| Framework | |
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild
| Title | CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild |
| Authors | Yang Zhang, Hassan Foroosh, Philip David, Boqing Gong |
| Abstract | In this paper, we conduct an intriguing experimental study about the physical adversarial attack on object detectors in the wild. In particular, we learn a camouflage pattern to hide vehicles from being detected by state-of-the-art convolutional neural network based detectors. Our approach alternates between two threads. In the first, we train a neural approximation function to imitate how a simulator applies a camouflage to vehicles and how a vehicle detector performs given images of the camouflaged vehicles. In the second, we minimize the approximated detection score by searching for the optimal camouflage. Experiments show that the learned camouflage can not only hide a vehicle from the image-based detectors under many test cases but also generalizes to different environments, vehicles, and object detectors. |
| Tasks | Adversarial Attack |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJgEl3A5tm |
| https://openreview.net/pdf?id=SJgEl3A5tm | |
| PWC | https://paperswithcode.com/paper/camou-learning-physical-vehicle-camouflages |
| Repo | |
| Framework | |
Extracting relevant information from physician-patient dialogues for automated clinical note taking
| Title | Extracting relevant information from physician-patient dialogues for automated clinical note taking |
| Authors | Serena Jeblee, Faiza Khan Khattak, Noah Crampton, Muhammad Mamdani, Frank Rudzicz |
| Abstract | We present a system for automatically extracting pertinent medical information from dialogues between clinicians and patients. The system parses each dialogue and extracts entities such as medications and symptoms, using context to predict which entities are relevant. We also classify the primary diagnosis for each conversation. In addition, we extract topic information and identify relevant utterances. This serves as a baseline for a system that extracts information from dialogues and automatically generates a patient note, which can be reviewed and edited by the clinician. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6209/ |
| https://www.aclweb.org/anthology/D19-6209 | |
| PWC | https://paperswithcode.com/paper/extracting-relevant-information-from |
| Repo | |
| Framework | |
How to account for mispellings: Quantifying the benefit of character representations in neural content scoring models
| Title | How to account for mispellings: Quantifying the benefit of character representations in neural content scoring models |
| Authors | Brian Riordan, Michael Flor, Robert Pugh |
| Abstract | Character-based representations in neural models have been claimed to be a tool to overcome spelling variation in in word token-based input. We examine this claim in neural models for content scoring. We formulate precise hypotheses about the possible effects of adding character representations to word-based models and test these hypotheses on large-scale real world content scoring datasets. We find that, while character representations may provide small performance gains in general, their effectiveness in accounting for spelling variation may be limited. We show that spelling correction can provide larger gains than character representations, and that spelling correction improves the performance of models with character representations. With these insights, we report a new state of the art on the ASAP-SAS content scoring dataset. |
| Tasks | Spelling Correction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4411/ |
| https://www.aclweb.org/anthology/W19-4411 | |
| PWC | https://paperswithcode.com/paper/how-to-account-for-mispellings-quantifying |
| Repo | |
| Framework | |
Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in head and neck cancer
| Title | Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in head and neck cancer |
| Authors | Liyuan Chen, Zhiguo Zhou, David Sher, Qiongwen Zhang, Jennifer Shah, Nhat-Long Pham, Steve Jiang, Jing Wang |
| Abstract | Lymph node metastasis (LNM) is a significant prognostic factor in patients with head and neck cancer, and the ability to predict it accurately is essential to optimizing treatment. Positron emission tomography (PET) and computed tomography (CT) imaging are routinely used to identify LNM. Although large or highly active lymph nodes (LNs) have a high probability of being positive, identifying small or less reactive LNs is challenging. The accuracy of LNM identification strongly depends on the physician’s experience, so an automatic prediction model for LNM based on CT and PET images is warranted to assist LMN identification across care providers and facilities. Radiomics and deep learning are the two promising imaging-based strategies for node malignancy prediction. Radiomics models are built based on handcrafted features, while deep learning learns the features automatically. To build a more reliable model, we proposed a hybrid predictive model that takes advantages of both radiomics and deep learning based strategies. We designed a new many-objective radiomics (MaO-radiomics) model and a 3D convolutional neural network (3D-CNN) that fully utilizes spatial contextual information, and we fused their outputs through an evidential reasoning (ER) approach. We evaluated the performance of the hybrid method for classifying normal, suspicious and involved LNs. The hybrid method achieves an accuracy (ACC) of 0.88 while XmasNet and Radiomics methods achieve 0.81 and 0.75, respectively. The hybrid method provides a more accurate way for predicting LNM using PET and CT. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-03-29 |
| URL | https://iopscience.iop.org/article/10.1088/1361-6560/ab083a |
| https://iopscience.iop.org/article/10.1088/1361-6560/ab083a/pdf | |
| PWC | https://paperswithcode.com/paper/combining-many-objective-radiomics-and-3d |
| Repo | |
| Framework | |
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method
| Title | Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method |
| Authors | Qingkai Zeng, Mengxia Yu, Wenhao Yu, JinJun Xiong, Yiyu Shi, Meng Jiang |
| Abstract | On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts. We call these attributes facets: classification has a few facets such as application (e.g., face recognition), model (e.g., svm, knn), and metric (e.g., precision). In this work, we aim at building faceted concept hierarchies from scientific literature. Hierarchy construction methods heavily rely on hypernym detection, however, the faceted relations are parent-to-child links but the hypernym relation is a multi-hop, i.e., ancestor-to-descendent link with a specific facet {``}type-of{''}. We use information extraction techniques to find synonyms, sibling concepts, and ancestor-descendent relations from a data science corpus. And we propose a hierarchy growth algorithm to infer the parent-child links from the three types of relationships. It resolves conflicts by maintaining the acyclic structure of a hierarchy. | |
| Tasks | Face Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5317/ |
| https://www.aclweb.org/anthology/D19-5317 | |
| PWC | https://paperswithcode.com/paper/faceted-hierarchy-a-new-graph-type-to |
| Repo | |
| Framework | |
Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019
| Title | Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019 |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2700/ |
| https://www.aclweb.org/anthology/W19-2700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-discourse |
| Repo | |
| Framework | |
Learning Channel-Wise Interactions for Binary Convolutional Neural Networks
| Title | Learning Channel-Wise Interactions for Binary Convolutional Neural Networks |
| Authors | Ziwei Wang, Jiwen Lu, Chenxin Tao, Jie Zhou, Qi Tian |
| Abstract | In this paper, we propose a channel-wise interaction based binary convolutional neural network learning method (CI-BCNN) for efficient inference. Conventional methods apply xnor and bitcount operations in binary convolution with notable quantization error, which usually obtains inconsistent signs in binary feature maps compared with their full-precision counterpart and leads to significant information loss. In contrast, our CI-BCNN mines the channel-wise interactions, through which prior knowledge is provided to alleviate inconsistency of signs in binary feature maps and preserves the information of input samples during inference. Specifically, we mine the channel-wise interactions by a reinforcement learning model, and impose channel-wise priors on the intermediate feature maps through the interacted bitcount function. Extensive experiments on the CIFAR-10 and ImageNet datasets show that our method outperforms the state-of-the-art binary convolutional neural networks with less computational and storage cost. |
| Tasks | Quantization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Learning_Channel-Wise_Interactions_for_Binary_Convolutional_Neural_Networks_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Learning_Channel-Wise_Interactions_for_Binary_Convolutional_Neural_Networks_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-channel-wise-interactions-for-binary |
| Repo | |
| Framework | |
Computationally Modeling the Impact of Task-Appropriate Language Complexity and Accuracy on Human Grading of German Essays
| Title | Computationally Modeling the Impact of Task-Appropriate Language Complexity and Accuracy on Human Grading of German Essays |
| Authors | Zarah Weiss, Anja Riemenschneider, Pauline Schr{"o}ter, Detmar Meurers |
| Abstract | Computational linguistic research on the language complexity of student writing typically involves human ratings as a gold standard. However, educational science shows that teachers find it difficult to identify and cleanly separate accuracy, different aspects of complexity, contents, and structure. In this paper, we therefore explore the use of computational linguistic methods to investigate how task-appropriate complexity and accuracy relate to the grading of overall performance, content performance, and language performance as assigned by teachers. Based on texts written by students for the official school-leaving state examination (Abitur), we show that teachers successfully assign higher language performance grades to essays with higher task-appropriate language complexity and properly separate this from content scores. Yet, accuracy impacts teacher assessment for all grading rubrics, also the content score, overemphasizing the role of accuracy. Our analysis is based on broad computational linguistic modeling of German language complexity and an innovative theory- and data-driven feature aggregation method inferring task-appropriate language complexity. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4404/ |
| https://www.aclweb.org/anthology/W19-4404 | |
| PWC | https://paperswithcode.com/paper/computationally-modeling-the-impact-of-task |
| Repo | |
| Framework | |
Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing
| Title | Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3700/ |
| https://www.aclweb.org/anthology/W19-3700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-7th-workshop-on-balto |
| Repo | |
| Framework | |
Equalizing Gender Bias in Neural Machine Translation with Word Embeddings Techniques
| Title | Equalizing Gender Bias in Neural Machine Translation with Word Embeddings Techniques |
| Authors | Joel Escud{'e} Font, Marta R. Costa-juss{`a} |
| Abstract | Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large text corpora which contain biases and stereotypes. As a consequence, models inherit these social biases. Recent methods have shown results in reducing gender bias in other natural language processing tools such as word embeddings. We take advantage of the fact that word embeddings are used in neural machine translation to propose a method to equalize gender biases in neural machine translation using these representations. Specifically, we propose, experiment and analyze the integration of two debiasing techniques over GloVe embeddings in the Transformer translation architecture. We evaluate our proposed system on the WMT English-Spanish benchmark task, showing gains up to one BLEU point. As for the gender bias evaluation, we generate a test set of occupations and we show that our proposed system learns to equalize existing biases from the baseline system. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3821/ |
| https://www.aclweb.org/anthology/W19-3821 | |
| PWC | https://paperswithcode.com/paper/equalizing-gender-bias-in-neural-machine |
| Repo | |
| Framework | |
