Paper Group NANR 119
YUN-HPCC at SemEval-2019 Task 3: Multi-Step Ensemble Neural Network for Sentiment Analysis in Textual Conversation. Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors. Automated Cross-language Intelligibility Analysis of Parkinson’s Disease Patients Using Speech Recognition Technologies. A Little Linguistics Goes …
YUN-HPCC at SemEval-2019 Task 3: Multi-Step Ensemble Neural Network for Sentiment Analysis in Textual Conversation
| Title | YUN-HPCC at SemEval-2019 Task 3: Multi-Step Ensemble Neural Network for Sentiment Analysis in Textual Conversation |
| Authors | Dawei Li, Jin Wang, Xuejie Zhang |
| Abstract | This paper describes our approach to the sentiment analysis of Twitter textual conversations based on deep learning. We analyze the syntax, abbreviations, and informal-writing of Twitter; and perform perfect data preprocessing on the data to convert them to normative text. We apply a multi-step ensemble strategy to solve the problem of extremely unbalanced data in the training set. This is achieved by taking the GloVe and Elmo word vectors as input into a combination model with four different deep neural networks. The experimental results from the development dataset demonstrate that the proposed model exhibits a strong generalization ability. For evaluation on the best dataset, we integrated the results using the stacking ensemble learning approach and achieved competitive results. According to the final official review, the results of our model ranked 10th out of 165 teams. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2063/ |
| https://www.aclweb.org/anthology/S19-2063 | |
| PWC | https://paperswithcode.com/paper/yun-hpcc-at-semeval-2019-task-3-multi-step |
| Repo | |
| Framework | |
Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors
| Title | Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors |
| Authors | Danijar Hafner, Dustin Tran, Timothy Lillicrap, Alex Irpan, James Davidson |
| Abstract | Obtaining reliable uncertainty estimates of neural network predictions is a long standing challenge. Bayesian neural networks have been proposed as a solution, but it remains open how to specify their prior. In particular, the common practice of a standard normal prior in weight space imposes only weak regularities, causing the function posterior to possibly generalize in unforeseen ways on inputs outside of the training distribution. We propose noise contrastive priors (NCPs) to obtain reliable uncertainty estimates. The key idea is to train the model to output high uncertainty for data points outside of the training distribution. NCPs do so using an input prior, which adds noise to the inputs of the current mini batch, and an output prior, which is a wide distribution given these inputs. NCPs are compatible with any model that can output uncertainty estimates, are easy to scale, and yield reliable uncertainty estimates throughout training. Empirically, we show that NCPs prevent overfitting outside of the training distribution and result in uncertainty estimates that are useful for active learning. We demonstrate the scalability of our method on the flight delays data set, where we significantly improve upon previously published results. |
| Tasks | Active Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkgxasA5Ym |
| https://openreview.net/pdf?id=HkgxasA5Ym | |
| PWC | https://paperswithcode.com/paper/reliable-uncertainty-estimates-in-deep-neural-1 |
| Repo | |
| Framework | |
Automated Cross-language Intelligibility Analysis of Parkinson’s Disease Patients Using Speech Recognition Technologies
| Title | Automated Cross-language Intelligibility Analysis of Parkinson’s Disease Patients Using Speech Recognition Technologies |
| Authors | Nina Hosseini-Kivanani, Juan Camilo V{'a}squez-Correa, Manfred Stede, Elmar N{"o}th |
| Abstract | Speech deficits are common symptoms amongParkinson{'}s Disease (PD) patients. The automatic assessment of speech signals is promising for the evaluation of the neurological state and the speech quality of the patients. Recently, progress has been made in applying machine learning and computational methods to automatically evaluate the speech of PD patients. In the present study, we plan to analyze the speech signals of PD patients and healthy control (HC) subjects in three different languages: German, Spanish, and Czech, with the aim to identify biomarkers to discriminate between PD patients and HC subjects and to evaluate the neurological state of the patients. Therefore, the main contribution of this study is the automatic classification of PD patients and HC subjects in different languages with focusing on phonation, articulation, and prosody. We will focus on an intelligibility analysis based on automatic speech recognition systems trained on these three languages. This is one of the first studies done that considers the evaluation of the speech of PD patients in different languages. The purpose of this research proposal is to build a model that can discriminate PD and HC subjects even when the language used for train and test is different. |
| Tasks | Speech Recognition |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2010/ |
| https://www.aclweb.org/anthology/P19-2010 | |
| PWC | https://paperswithcode.com/paper/automated-cross-language-intelligibility |
| Repo | |
| Framework | |
A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance
| Title | A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance |
| Authors | Alex Erdmann, er, Salam Khalifa, Mai Oudah, Nizar Habash, Houda Bouamor |
| Abstract | We present de-lexical segmentation, a linguistically motivated alternative to greedy or other unsupervised methods, requiring only minimal language specific input. Our technique involves creating a small grammar of closed-class affixes which can be written in a few hours. The grammar over generates analyses for word forms attested in a raw corpus which are disambiguated based on features of the linguistic base proposed for each form. Extending the grammar to cover orthographic, morpho-syntactic or lexical variation is simple, making it an ideal solution for challenging corpora with noisy, dialect-inconsistent, or otherwise non-standard content. In two evaluations, we consistently outperform competitive unsupervised baselines and approach the performance of state-of-the-art supervised models trained on large amounts of data, providing evidence for the value of linguistic input during preprocessing. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4214/ |
| https://www.aclweb.org/anthology/W19-4214 | |
| PWC | https://paperswithcode.com/paper/a-little-linguistics-goes-a-long-way |
| Repo | |
| Framework | |
A Probabilistic Approach for Confidence Scoring in Speech Recognition
| Title | A Probabilistic Approach for Confidence Scoring in Speech Recognition |
| Authors | Punnoose Kuriakose |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7410/ |
| https://www.aclweb.org/anthology/W19-7410 | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-approach-for-confidence |
| Repo | |
| Framework | |
The Success Story of Mitra Translations
| Title | The Success Story of Mitra Translations |
| Authors | Mina Ilieva, Mariya Kancheva |
| Abstract | Technologies and their constant updates and innovative nature drastically and irreversibly transformed this small business into a leading brand on the translation market, along with just few other LSPs integrating translation software solutions. Now, we are constantly following the new developments in software updates and online platforms and we are successfully keeping up with any new trend in the field of translation, localization, transcreation, revision, post-editing, etc. Ultimately, we are positive that proper implementation of technology (with focus on quality, cost and time) and hard work are the stepping stones in the way to become a trusted translation services provider. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8716/ |
| https://www.aclweb.org/anthology/W19-8716 | |
| PWC | https://paperswithcode.com/paper/the-success-story-of-mitra-translations |
| Repo | |
| Framework | |
ANU-CSIRO at MEDIQA 2019: Question Answering Using Deep Contextual Knowledge
| Title | ANU-CSIRO at MEDIQA 2019: Question Answering Using Deep Contextual Knowledge |
| Authors | Vincent Nguyen, Sarvnaz Karimi, Zhenchang Xing |
| Abstract | We report on our system for textual inference and question entailment in the medical domain for the ACL BioNLP 2019 Shared Task, MEDIQA. Textual inference is the task of finding the semantic relationships between pairs of text. Question entailment involves identifying pairs of questions which have similar semantic content. To improve upon medical natural language inference and question entailment approaches to further medical question answering, we propose a system that incorporates open-domain and biomedical domain approaches to improve semantic understanding and ambiguity resolution. Our models achieve 80{%} accuracy on medical natural language inference (6.5{%} absolute improvement over the original baseline), 48.9{%} accuracy on recognising medical question entailment, 0.248 Spearman{'}s rho for question answering ranking and 68.6{%} accuracy for question answering classification. |
| Tasks | Natural Language Inference, Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5051/ |
| https://www.aclweb.org/anthology/W19-5051 | |
| PWC | https://paperswithcode.com/paper/anu-csiro-at-mediqa-2019-question-answering |
| Repo | |
| Framework | |
Foundations of Collaborative Task-Oriented Dialogue: What’s in a Slot?
| Title | Foundations of Collaborative Task-Oriented Dialogue: What’s in a Slot? |
| Authors | Philip Cohen |
| Abstract | In this paper, we examine the foundations of task-oriented dialogues, in which systems are requested to perform tasks for humans. We argue that the way this dialogue task has been framed has limited its applicability to processing simple requests with atomic {}slot-fillers{''}. However, real task-oriented dialogues can contain more complex utterances that provide non-atomic constraints on slot values. For example, in response to the system{'}s question {}What time do you want me to reserve the restaurant?{''}, a user should be able to say {}the earliest time available,{''} which cannot be handled by classic {}intent + slots{''} approaches that do not incorporate expressive logical form meaning representations. Furthermore, situations for which it would be desirable to build task-oriented dialogue systems, e.g., to engage in mixed-initiative, collaborative or multiparty dialogues, will require a more general approach. In order to overcome these limitations and to provide such an approach, we give a logical analysis of the {}intent+slot{''} dialogue setting using a modal logic of intention and including a more expansive notion of {}dialogue state{''}. Finally, we briefly discuss our program of research to build a next generation of plan-based dialogue systems that goes beyond {``}intent + slots{''}. | |
| Tasks | Task-Oriented Dialogue Systems |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5924/ |
| https://www.aclweb.org/anthology/W19-5924 | |
| PWC | https://paperswithcode.com/paper/foundations-of-collaborative-task-oriented |
| Repo | |
| Framework | |
Abstract Text Summarization: A Low Resource Challenge
| Title | Abstract Text Summarization: A Low Resource Challenge |
| Authors | Shantipriya Parida, Petr Motlicek |
| Abstract | Text summarization is considered as a challenging task in the NLP community. The availability of datasets for the task of multilingual text summarization is rare, and such datasets are difficult to construct. In this work, we build an abstract text summarizer for the German language text using the state-of-the-art {``}Transformer{''} model. We propose an iterative data augmentation approach which uses synthetic data along with the real summarization data for the German language. To generate synthetic data, the Common Crawl (German) dataset is exploited, which covers different domains. The synthetic data is effective for the low resource condition and is particularly helpful for our multilingual scenario where availability of summarizing data is still a challenging issue. The data are also useful in deep learning scenarios where the neural models require a large amount of training data for utilization of its capacity. The obtained summarization performance is measured in terms of ROUGE and BLEU score. We achieve an absolute improvement of +1.5 and +16.0 in ROUGE1 F1 (R1{_}F1) on the development and test sets, respectively, compared to the system which does not rely on data augmentation. | |
| Tasks | Data Augmentation, Text Summarization |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1616/ |
| https://www.aclweb.org/anthology/D19-1616 | |
| PWC | https://paperswithcode.com/paper/abstract-text-summarization-a-low-resource |
| Repo | |
| Framework | |
CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets
| Title | CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets |
| Authors | Guy Aglionby, Chris Davis, Pushkar Mishra, Andrew Caines, Helen Yannakoudakis, Marek Rei, Ekaterina Shutova, Paula Buttery |
| Abstract | We describe the CAMsterdam team entry to the SemEval-2019 Shared Task 6 on offensive language identification in Twitter data. Our proposed model learns to extract textual features using a multi-layer recurrent network, and then performs text classification using gradient-boosted decision trees (GBDT). A self-attention architecture enables the model to focus on the most relevant areas in the text. In order to enrich input representations, we use node2vec to learn globally optimised embeddings for hashtags, which are then given as additional features to the GBDT classifier. Our best model obtains 78.79{%} macro F1-score on detecting offensive language (subtask A), 66.32{%} on categorising offence types (targeted/untargeted; subtask B), and 55.36{%} on identifying the target of offence (subtask C). |
| Tasks | Language Identification, Text Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2100/ |
| https://www.aclweb.org/anthology/S19-2100 | |
| PWC | https://paperswithcode.com/paper/camsterdam-at-semeval-2019-task-6-neural-and |
| Repo | |
| Framework | |
Multi-way Encoding for Robustness to Adversarial Attacks
| Title | Multi-way Encoding for Robustness to Adversarial Attacks |
| Authors | Donghyun Kim, Sarah Adel Bargal, Jianming Zhang, Stan Sclaroff |
| Abstract | Deep models are state-of-the-art for many computer vision tasks including image classification and object detection. However, it has been shown that deep models are vulnerable to adversarial examples. We highlight how one-hot encoding directly contributes to this vulnerability and propose breaking away from this widely-used, but highly-vulnerable mapping. We demonstrate that by leveraging a different output encoding, multi-way encoding, we can make models more robust. Our approach makes it more difficult for adversaries to find useful gradients for generating adversarial attacks. We present state-of-the-art robustness results for black-box, white-box attacks, and achieve higher clean accuracy on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN when combined with adversarial training. The strength of our approach is also presented in the form of an attack for model watermarking, raising challenges in detecting stolen models. |
| Tasks | Image Classification, Object Detection |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1xOYoA5tQ |
| https://openreview.net/pdf?id=B1xOYoA5tQ | |
| PWC | https://paperswithcode.com/paper/multi-way-encoding-for-robustness-to |
| Repo | |
| Framework | |
Predicting the Outcome of Deliberative Democracy: A Research Proposal
| Title | Predicting the Outcome of Deliberative Democracy: A Research Proposal |
| Authors | Conor McKillop |
| Abstract | As liberal states across the world face a decline in political participation by citizens, deliberative democracy is a promising solution for the public{'}s decreasing confidence and apathy towards the democratic process. Deliberative dialogue is method of public interaction that is fundamental to the concept of deliberative democracy. The ability to identify and predict consensus in the dialogues could bring greater accessibility and transparency to the face-to-face participatory process. The paper sets out a research plan for the first steps at automatically identifying and predicting consensus in a corpus of German language debates on hydraulic fracking. It proposes the use of a unique combination of lexical, sentiment, durational and further {`}derivative{'} features of adjacency pairs to train traditional classification models. In addition to this, the use of deep learning techniques to improve the accuracy of the classification and prediction tasks is also discussed. Preliminary results at the classification of utterances are also presented, with an F1 between 0.61 and 0.64 demonstrating that the task of recognising agreement is demanding but possible. | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2013/ |
| https://www.aclweb.org/anthology/P19-2013 | |
| PWC | https://paperswithcode.com/paper/predicting-the-outcome-of-deliberative |
| Repo | |
| Framework | |
Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle
| Title | Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle |
| Authors | Simon S. Du, Yuping Luo, Ruosong Wang, Hanrui Zhang |
| Abstract | Q-learning with function approximation is one of the most popular methods in reinforcement learning. Though the idea of using function approximation was proposed at least 60 years ago, even in the simplest setup, i.e, approximating Q-functions with linear functions, it is still an open problem how to design a provably efficient algorithm that learns a near-optimal policy. The key challenges are how to efficiently explore the state space and how to decide when to stop exploring in conjunction with the function approximation scheme. The current paper presents a provably efficient algorithm for Q-learning with linear function approximation. Under certain regularity assumptions, our algorithm, Difference Maximization Q-learning, combined with linear function approximation, returns a near-optimal policy using polynomial number of trajectories. Our algorithm introduces a new notion, the Distribution Shift Error Checking (DSEC) oracle. This oracle tests whether there exists a function in the function class that predicts well on a distribution $\mathcal{D}_1$, but predicts poorly on another distribution $\mathcal{D}_2$, where $\mathcal{D}_1$ and $\mathcal{D}_2$ are distributions over states induced by two different exploration policies. For the linear function class, this oracle is equivalent to solving a top eigenvalue problem. We believe our algorithmic insights, especially the DSEC oracle, are also useful in designing and analyzing reinforcement learning algorithms with general function approximation. |
| Tasks | Q-Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9018-provably-efficient-q-learning-with-function-approximation-via-distribution-shift-error-checking-oracle |
| http://papers.nips.cc/paper/9018-provably-efficient-q-learning-with-function-approximation-via-distribution-shift-error-checking-oracle.pdf | |
| PWC | https://paperswithcode.com/paper/provably-efficient-q-learning-with-function-1 |
| Repo | |
| Framework | |
Motion feature augmented network for dynamic hand gesture recognition from skeletal data
| Title | Motion feature augmented network for dynamic hand gesture recognition from skeletal data |
| Authors | Xinghao Chen, 1 Guijin Wang, Hengkai Guo, Cairong Zhang, Hang Wang, and Li Zhang |
| Abstract | Dynamic hand gesture recognition has attracted increasing attention because of its importance for human–computer interaction. In this paper, we propose a novel motion feature augmented network (MFA-Net) for dynamic hand gesture recognition from skeletal data. MFA-Net exploits motion features of finger and global movements to augment features of deep network for gesture recognition. To describe finger articulated movements, finger motion features are extracted from the hand skeleton sequence via a variational autoencoder. Global motion features are utilized to represent the global movements of hand skeleton. These motion features along with the skeleton sequence are then fed into three branches of a recurrent neural network (RNN), which augment the motion features for RNN and improve the classification performance. The proposed MFA-Net is evaluated on two challenging skeleton-based dynamic hand gesture datasets, including DHG-14/28 dataset and SHREC’17 dataset. Experimental results demonstrate that our proposed method achieves comparable performance on DHG-14/28 dataset and better performance on SHREC’17 dataset when compared with start-of-the-art methods. |
| Tasks | Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition, Skeleton Based Action Recognition |
| Published | 2019-01-10 |
| URL | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6359639/ |
| https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6359639/ | |
| PWC | https://paperswithcode.com/paper/motion-feature-augmented-network-for-dynamic |
| Repo | |
| Framework | |
Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise
| Title | Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise |
| Authors | Yatu Ji, Hongxu Hou, Chen Junjie, Nier Wu |
| Abstract | For the translation of agglutinative language such as typical Mongolian, unknown (UNK) words not only come from the quite restricted vocabulary, but also mostly from misunderstanding of the translation model to the morphological changes. In this study, we introduce a new adversarial training model to alleviate the UNK problem in Mongolian-Chinese machine translation. The training process can be described as three adversarial sub models (generator, value screener and discriminator), playing a win-win game. In this game, the added screener plays the role of emphasizing that the discriminator pays attention to the added Mongolian morphological noise in the form of pseudo-data and improving the training efficiency. The experimental results show that the newly emerged Mongolian-Chinese task is state-of-the-art. Under this premise, the training time is greatly shortened. |
| Tasks | Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2016/ |
| https://www.aclweb.org/anthology/P19-2016 | |
| PWC | https://paperswithcode.com/paper/improving-mongolian-chinese-neural-machine |
| Repo | |
| Framework | |
