Paper Group NANR 232
Discriminating between Mandarin Chinese and Swiss-German varieties using adaptive language models. Detecting Target of Sarcasm using Ensemble Methods. Overview of the 6th Workshop on Asian Translation. A Stylometry Toolkit for Latin Literature. Learning the Dyck Language with Attention-based Seq2Seq Models. Learning With Unsure Data for Medical Ima …
Discriminating between Mandarin Chinese and Swiss-German varieties using adaptive language models
| Title | Discriminating between Mandarin Chinese and Swiss-German varieties using adaptive language models |
| Authors | Tommi Jauhiainen, Krister Lind{'e}n, Heidi Jauhiainen |
| Abstract | This paper describes the language identification systems used by the SUKI team in the Discriminating between the Mainland and Taiwan variation of Mandarin Chinese (DMT) and the German Dialect Identification (GDI) shared tasks which were held as part of the third VarDial Evaluation Campaign. The DMT shared task included two separate tracks, one for the simplified Chinese script and one for the traditional Chinese script. We submitted three runs on both tracks of the DMT task as well as on the GDI task. We won the traditional Chinese track using Naive Bayes with language model adaptation, came second on GDI with an adaptive version of the HeLI 2.0 method, and third on the simplified Chinese track using again the adaptive Naive Bayes. |
| Tasks | Language Identification, Language Modelling |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1419/ |
| https://www.aclweb.org/anthology/W19-1419 | |
| PWC | https://paperswithcode.com/paper/discriminating-between-mandarin-chinese-and |
| Repo | |
| Framework | |
Detecting Target of Sarcasm using Ensemble Methods
| Title | Detecting Target of Sarcasm using Ensemble Methods |
| Authors | Pradeesh Parameswaran, Andrew Trotman, Veronica Liesaputra, David Eyers |
| Abstract | We describe our methods in trying to detect the target of sarcasm as part of ALTA 2019 shared task. We use combination of ensemble of clas- sifiers and a rule-based system. Our team ob- tained a Dice-Sorensen Coefficient score of 0.37150, which placed 2nd in the public leader- board. Despite no team beating the baseline score for the private dataset, we present our findings and also some of the challenges and future improvements which can be used in or- der to tackle the problem. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1027/ |
| https://www.aclweb.org/anthology/U19-1027 | |
| PWC | https://paperswithcode.com/paper/detecting-target-of-sarcasm-using-ensemble |
| Repo | |
| Framework | |
Overview of the 6th Workshop on Asian Translation
| Title | Overview of the 6th Workshop on Asian Translation |
| Authors | Toshiaki Nakazawa, Nobushige Doi, Shohei Higashiyama, Chenchen Ding, Raj Dabre, Hideya Mino, Isao Goto, Win Pa Pa, Anoop Kunchukuttan, Shantipriya Parida, Ond{\v{r}}ej Bojar, Sadao Kurohashi |
| Abstract | This paper presents the results of the shared tasks from the 6th workshop on Asian translation (WAT2019) including Ja↔En, Ja↔Zh scientific paper translation subtasks, Ja↔En, Ja↔Ko, Ja↔En patent translation subtasks, Hi↔En, My↔En, Km↔En, Ta↔En mixed domain subtasks and Ru↔Ja news commentary translation task. For the WAT2019, 25 teams participated in the shared tasks. We also received 10 research paper submissions out of which 61 were accepted. About 400 translation results were submitted to the automatic evaluation server, and selected submis- sions were manually evaluated. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5201/ |
| https://www.aclweb.org/anthology/D19-5201 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-6th-workshop-on-asian |
| Repo | |
| Framework | |
A Stylometry Toolkit for Latin Literature
| Title | A Stylometry Toolkit for Latin Literature |
| Authors | Thomas J. Bolt, Jeffrey H. Flynt, Pramit Chaudhuri, Joseph P. Dexter |
| Abstract | Computational stylometry has become an increasingly important aspect of literary criticism, but many humanists lack the technical expertise or language-specific NLP resources required to exploit computational methods. We demonstrate a stylometry toolkit for analysis of Latin literary texts, which is freely available at www.qcrit.org/stylometry. Our toolkit generates data for a diverse range of literary features and has an intuitive point-and-click interface. The features included have proven effective for multiple literary studies and are calculated using custom heuristics without the need for syntactic parsing. As such, the toolkit models one approach to the user-friendly generation of stylometric data, which could be extended to other premodern and non-English languages underserved by standard NLP resources. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3035/ |
| https://www.aclweb.org/anthology/D19-3035 | |
| PWC | https://paperswithcode.com/paper/a-stylometry-toolkit-for-latin-literature |
| Repo | |
| Framework | |
Learning the Dyck Language with Attention-based Seq2Seq Models
| Title | Learning the Dyck Language with Attention-based Seq2Seq Models |
| Authors | Xiang Yu, Ngoc Thang Vu, Jonas Kuhn |
| Abstract | The generalized Dyck language has been used to analyze the ability of Recurrent Neural Networks (RNNs) to learn context-free grammars (CFGs). Recent studies draw conflicting conclusions on their performance, especially regarding the generalizability of the models with respect to the depth of recursion. In this paper, we revisit several common models and experimental settings, discuss the potential problems of the tasks and analyses. Furthermore, we explore the use of attention mechanisms within the seq2seq framework to learn the Dyck language, which could compensate for the limited encoding ability of RNNs. Our findings reveal that attention mechanisms still cannot truly generalize over the recursion depth, although they perform much better than other models on the closing bracket tagging task. Moreover, this also suggests that this commonly used task is not sufficient to test a model{'}s understanding of CFGs. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4815/ |
| https://www.aclweb.org/anthology/W19-4815 | |
| PWC | https://paperswithcode.com/paper/learning-the-dyck-language-with-attention |
| Repo | |
| Framework | |
Learning With Unsure Data for Medical Image Diagnosis
| Title | Learning With Unsure Data for Medical Image Diagnosis |
| Authors | Botong Wu, Xinwei Sun, Lingjing Hu, Yizhou Wang |
| Abstract | In image-based disease prediction, it can be hard to give certain cases a deterministic “disease/normal” label due to lack of enough information, e.g., at its early stage. We call such cases “unsure” data. Labeling such data as unsure suggests follow-up examinations so as to avoid irreversible medical accident/loss in contrast to incautious prediction. This is a common practice in clinical diagnosis, however, mostly neglected by existing methods. Learning with unsure data also interweaves with two other practical issues: (i) data imbalance issue that may incur model-bias towards the majority class, and (ii) conservative/aggressive strategy consideration, i.e., the negative (normal) samples and positive (disease) samples should NOT be treated equally -- the former should be detected with a high precision (conservativeness) and the latter should be detected with a high recall (aggression) to avoid missing opportunity for treatment. Mixed with these issues, learning with unsure data becomes particularly challenging. In this paper, we raise “learning with unsure data” problem and formulate it as an ordinal regression and propose a unified end-to-end learning framework, which also considers the aforementioned two issues: (i) incorporate cost-sensitive parameters to alleviate the data imbalance problem, and (ii) execute the conservative and aggressive strategies by introducing two parameters in the training procedure. The benefits of learning with unsure data and validity of our models are demonstrated on the prediction of Alzheimer’s Disease and lung nodules. |
| Tasks | Disease Prediction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Learning_With_Unsure_Data_for_Medical_Image_Diagnosis_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wu_Learning_With_Unsure_Data_for_Medical_Image_Diagnosis_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-with-unsure-data-for-medical-image |
| Repo | |
| Framework | |
TellMeWhy: Learning to Explain Corrective Feedback for Second Language Learners
| Title | TellMeWhy: Learning to Explain Corrective Feedback for Second Language Learners |
| Authors | Yi-Huei Lai, Jason Chang |
| Abstract | We present a writing prototype feedback system, TellMeWhy, to provide explanations of errors in submitted essays. In our approach, the sentence with corrections is analyzed to identify error types and problem words, aimed at customizing explanations based on the context of the error. The method involves learning the relation of errors and problem words, generating common feedback patterns, and extracting grammar patterns, collocations and example sentences. At run-time, a sentence with corrections is classified, and the problem word and template are identified to provide detailed explanations. Preliminary evaluation shows that the method has potential to improve existing commercial writing services. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3040/ |
| https://www.aclweb.org/anthology/D19-3040 | |
| PWC | https://paperswithcode.com/paper/tellmewhy-learning-to-explain-corrective |
| Repo | |
| Framework | |
A Deep Learning Approach for Dynamic Survival Analysis with Competing Risks
| Title | A Deep Learning Approach for Dynamic Survival Analysis with Competing Risks |
| Authors | Changhee Lee, Mihaela van der Schaar |
| Abstract | Currently available survival analysis methods are limited in their ability to deal with complex, heterogeneous, and longitudinal data such as that available in primary care records, or in their ability to deal with multiple competing risks. This paper develops a novel deep learning architecture that flexibly incorporates the available longitudinal data comprising various repeated measurements (rather than only the last available measurements) in order to issue dynamically updated survival predictions for one or multiple competing risk(s). Unlike existing works in the survival analysis on the basis of longitudinal data, the proposed method learns the time-to-event distributions without specifying underlying stochastic assumptions of the longitudinal or the time-to-event processes. Thus, our method is able to learn associations between the longitudinal data and the various associated risks in a fully data-driven fashion. We demonstrate the power of our method by applying it to real-world longitudinal datasets and show a drastic improvement over state-of-the-art methods in discriminative performance. Furthermore, our analysis of the variable importance and dynamic survival predictions will yield a better understanding of the predicted risks which will result in more effective health care. |
| Tasks | Survival Analysis |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJG8asRqKX |
| https://openreview.net/pdf?id=rJG8asRqKX | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-for-dynamic-survival |
| Repo | |
| Framework | |
Extraction of Lactation Frames from Drug Labels and LactMed
| Title | Extraction of Lactation Frames from Drug Labels and LactMed |
| Authors | Heath Goodrum, Meghana Gudala, Ankita Misra, Kirk Roberts |
| Abstract | This paper describes a natural language processing (NLP) approach to extracting lactation-specific drug information from two sources: FDA-mandated drug labels and the NLM Drugs and Lactation Database (LactMed). A frame semantic approach is utilized, and the paper describes the selected frames, their annotation on a set of 900 sections from drug labels and LactMed articles, and the NLP system to extract such frame instances automatically. The ultimate goal of the project is to use such a system to identify discrepancies in lactation-related drug information between these resources. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5020/ |
| https://www.aclweb.org/anthology/W19-5020 | |
| PWC | https://paperswithcode.com/paper/extraction-of-lactation-frames-from-drug |
| Repo | |
| Framework | |
LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories
| Title | LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories |
| Authors | Ignacio Iacobacci, Roberto Navigli |
| Abstract | While word embeddings are now a de facto standard representation of words in most NLP tasks, recently the attention has been shifting towards vector representations which capture the different meanings, i.e., senses, of words. In this paper we explore the capabilities of a bidirectional LSTM model to learn representations of word senses from semantically annotated corpora. We show that the utilization of an architecture that is aware of word order, like an LSTM, enables us to create better representations. We assess our proposed model on various standard benchmarks for evaluating semantic representations, reaching state-of-the-art performance on the SemEval-2014 word-to-sense similarity task. We release the code and the resulting word and sense embeddings at http://lcl.uniroma1.it/LSTMEmbed. |
| Tasks | Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1165/ |
| https://www.aclweb.org/anthology/P19-1165 | |
| PWC | https://paperswithcode.com/paper/lstmembed-learning-word-and-sense |
| Repo | |
| Framework | |
A System for Diacritizing Four Varieties of Arabic
| Title | A System for Diacritizing Four Varieties of Arabic |
| Authors | Hamdy Mubarak, Ahmed Abdelali, Kareem Darwish, Mohamed Eldesouki, Younes Samih, Hassan Sajjad |
| Abstract | Short vowels, aka diacritics, are more often omitted when writing different varieties of Arabic including Modern Standard Arabic (MSA), Classical Arabic (CA), and Dialectal Arabic (DA). However, diacritics are required to properly pronounce words, which makes diacritic restoration (a.k.a. diacritization) essential for language learning and text-to-speech applications. In this paper, we present a system for diacritizing MSA, CA, and two varieties of DA, namely Moroccan and Tunisian. The system uses a character level sequence-to-sequence deep learning model that requires no feature engineering and beats all previous SOTA systems for all the Arabic varieties that we test on. |
| Tasks | Feature Engineering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3037/ |
| https://www.aclweb.org/anthology/D19-3037 | |
| PWC | https://paperswithcode.com/paper/a-system-for-diacritizing-four-varieties-of |
| Repo | |
| Framework | |
Maximum Likelihood Estimation of Factored Regular Deterministic Stochastic Languages
| Title | Maximum Likelihood Estimation of Factored Regular Deterministic Stochastic Languages |
| Authors | Chihiro Shibata, Jeffrey Heinz |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5709/ |
| https://www.aclweb.org/anthology/W19-5709 | |
| PWC | https://paperswithcode.com/paper/maximum-likelihood-estimation-of-factored |
| Repo | |
| Framework | |
Hint-based Training for Non-Autoregressive Translation
| Title | Hint-based Training for Non-Autoregressive Translation |
| Authors | Zhuohan Li, Di He, Fei Tian, Tao Qin, Liwei Wang, Tie-Yan Liu |
| Abstract | Machine translation is an important real-world application, and neural network-based AutoRegressive Translation (ART) models have achieved very promising accuracy. Due to the unparallelizable nature of the autoregressive factorization, ART models have to generate tokens one by one during decoding and thus suffer from high inference latency. Recently, Non-AutoRegressive Translation (NART) models were proposed to reduce the inference time. However, they could only achieve inferior accuracy compared with ART models. To improve the accuracy of NART models, in this paper, we propose to leverage the hints from a well-trained ART model to train the NART model. We define two hints for the machine translation task: hints from hidden states and hints from word alignments, and use such hints to regularize the optimization of NART models. Experimental results show that the NART model trained with hints could achieve significantly better translation performance than previous NART models on several tasks. In particular, for the WMT14 En-De and De-En task, we obtain BLEU scores of 25.20 and 29.52 respectively, which largely outperforms the previous non-autoregressive baselines. It is even comparable to a strong LSTM-based ART model (24.60 on WMT14 En-De), but one order of magnitude faster in inference. |
| Tasks | Machine Translation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1gGpjActQ |
| https://openreview.net/pdf?id=r1gGpjActQ | |
| PWC | https://paperswithcode.com/paper/hint-based-training-for-non-autoregressive |
| Repo | |
| Framework | |
Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification
| Title | Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification |
| Authors | Zimo Liu, Jingya Wang, Shaogang Gong, Huchuan Lu, Dacheng Tao |
| Abstract | Most existing person re-identification(Re-ID) approaches achieve superior results based on the assumption that a large amount of pre-labelled data is usually available and can be put into training phrase all at once. However, this assumption is not applicable to most real-world deployment of the Re-ID task. In this work, we propose an alternative reinforcement learning based human-in-the-loop model which releases the restriction of pre-labelling and keeps model upgrading with progressively collected data. The goal is to minimize human annotation efforts while maximizing Re-ID performance. It works in an iteratively updating framework by refining the RL policy and CNN parameters alternately. In particular, we formulate a Deep Reinforcement Active Learning (DRAL) method to guide an agent (a model in a reinforcement learning process) in selecting training samples on-the-fly by a human user/annotator. The reinforcement learning reward is the uncertainty value of each human selected sample. A binary feedback (positive or negative) labelled by the human annotator is used to select the samples of which are used to fine-tune a pre-trained CNN Re-ID model. Extensive experiments demonstrate the superiority of our DRAL method for deep reinforcement learning based human-in-the-loop person Re-ID when compared to existing unsupervised and transfer learning models as well as active learning models. |
| Tasks | Active Learning, Person Re-Identification, Transfer Learning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Deep_Reinforcement_Active_Learning_for_Human-in-the-Loop_Person_Re-Identification_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Deep_Reinforcement_Active_Learning_for_Human-in-the-Loop_Person_Re-Identification_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-active-learning-for-human |
| Repo | |
| Framework | |
Social IQa: Commonsense Reasoning about Social Interactions
| Title | Social IQa: Commonsense Reasoning about Social Interactions |
| Authors | Maarten Sap, Hannah Rashkin, Derek Chen, Ronan Le Bras, Yejin Choi |
| Abstract | We introduce Social IQa, the first large-scale benchmark for commonsense reasoning about social situations. Social IQa contains 38,000 multiple choice questions for probing emotional and social intelligence in a variety of everyday situations (e.g., Q: {}Jordan wanted to tell Tracy a secret, so Jordan leaned towards Tracy. Why did Jordan do this?{''} A: {}Make sure no one else could hear{''}). Through crowdsourcing, we collect commonsense questions along with correct and incorrect answers about social interactions, using a new framework that mitigates stylistic artifacts in incorrect answers by asking workers to provide the right answer to a different but related question. Empirical results show that our benchmark is challenging for existing question-answering models based on pretrained language models, compared to human performance ({\textgreater}20{%} gap). Notably, we further establish Social IQa as a resource for transfer learning of commonsense knowledge, achieving state-of-the-art performance on multiple commonsense reasoning tasks (Winograd Schemas, COPA). |
| Tasks | Question Answering, Transfer Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1454/ |
| https://www.aclweb.org/anthology/D19-1454 | |
| PWC | https://paperswithcode.com/paper/social-iqa-commonsense-reasoning-about-social |
| Repo | |
| Framework | |
