Paper Group NANR 1
Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes. NULI at SemEval-2019 Task 6: Transfer Learning for Offensive Language Detection using Bidirectional Transformers. Mental Health Surveillance over Social Media with Digital Cohorts. Building a Morphological Analyser for Laz. Proceedings of the Fourth …
Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes
| Title | Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes |
| Authors | Marina Sedinkina, Nikolas Breitkopf, Hinrich Sch{"u}tze |
| Abstract | In this paper, we automatically create sentiment dictionaries for predicting financial outcomes. We compare three approaches: (i) manual adaptation of the domain-general dictionary H4N, (ii) automatic adaptation of H4N and (iii) a combination consisting of first manual, then automatic adaptation. In our experiments, we demonstrate that the automatically adapted sentiment dictionary outperforms the previous state of the art in predicting the financial outcomes excess return and volatility. In particular, automatic adaptation performs better than manual adaptation. In our analysis, we find that annotation based on an expert{'}s a priori belief about a word{'}s meaning can be incorrect {–} annotation should be performed based on the word{'}s contexts in the target domain instead. |
| Tasks | Domain Adaptation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1034/ |
| https://www.aclweb.org/anthology/P19-1034 | |
| PWC | https://paperswithcode.com/paper/automatic-domain-adaptation-outperforms |
| Repo | |
| Framework | |
NULI at SemEval-2019 Task 6: Transfer Learning for Offensive Language Detection using Bidirectional Transformers
| Title | NULI at SemEval-2019 Task 6: Transfer Learning for Offensive Language Detection using Bidirectional Transformers |
| Authors | Ping Liu, Wen Li, Liang Zou |
| Abstract | Transfer learning and domain adaptive learning have been applied to various fields including computer vision (e.g., image recognition) and natural language processing (e.g., text classification). One of the benefits of transfer learning is to learn effectively and efficiently from limited labeled data with a pre-trained model. In the shared task of identifying and categorizing offensive language in social media, we preprocess the dataset according to the language behaviors on social media, and then adapt and fine-tune the Bidirectional Encoder Representation from Transformer (BERT) pre-trained by Google AI Language team. Our team NULI wins the first place (1st) in Sub-task A - Offensive Language Identification and is ranked 4th and 18th in Sub-task B - Automatic Categorization of Offense Types and Sub-task C - Offense Target Identification respectively. |
| Tasks | Language Identification, Text Classification, Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2011/ |
| https://www.aclweb.org/anthology/S19-2011 | |
| PWC | https://paperswithcode.com/paper/nuli-at-semeval-2019-task-6-transfer-learning |
| Repo | |
| Framework | |
Mental Health Surveillance over Social Media with Digital Cohorts
| Title | Mental Health Surveillance over Social Media with Digital Cohorts |
| Authors | Silvio Amir, Mark Dredze, John W. Ayers |
| Abstract | The ability to track mental health conditions via social media opened the doors for large-scale, automated, mental health surveillance. However, inferring accurate population-level trends requires representative samples of the underlying population, which can be challenging given the biases inherent in social media data. While previous work has adjusted samples based on demographic estimates, the populations were selected based on specific outcomes, e.g. specific mental health conditions. We depart from these methods, by conducting analyses over demographically representative digital cohorts of social media users. To validated this approach, we constructed a cohort of US based Twitter users to measure the prevalence of depression and PTSD, and investigate how these illnesses manifest across demographic subpopulations. The analysis demonstrates that cohort-based studies can help control for sampling biases, contextualize outcomes, and provide deeper insights into the data. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3013/ |
| https://www.aclweb.org/anthology/W19-3013 | |
| PWC | https://paperswithcode.com/paper/mental-health-surveillance-over-social-media |
| Repo | |
| Framework | |
Building a Morphological Analyser for Laz
| Title | Building a Morphological Analyser for Laz |
| Authors | Esra Onal, Francis Tyers |
| Abstract | This study is an attempt to contribute to documentation and revitalization efforts of endangered Laz language, a member of South Caucasian language family mainly spoken on northeastern coastline of Turkey. It constitutes the first steps to create a general computational model for word form recognition and production for Laz by building a rule-based morphological analyser using Helsinki Finite-State Toolkit (HFST). The evaluation results show that the analyser has a 64.9{%} coverage over a corpus collected for this study with 111,365 tokens. We have also performed an error analysis on randomly selected 100 tokens from the corpus which are not covered by the analyser, and these results show that the errors mostly result from Turkish words in the corpus and missing stems in our lexicon. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1101/ |
| https://www.aclweb.org/anthology/R19-1101 | |
| PWC | https://paperswithcode.com/paper/building-a-morphological-analyser-for-laz |
| Repo | |
| Framework | |
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
| Title | Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2) |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5400/ |
| https://www.aclweb.org/anthology/W19-5400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-fourth-conference-on-3 |
| Repo | |
| Framework | |
Emerald 110k: A Multidisciplinary Dataset for Abstract Sentence Classification
| Title | Emerald 110k: A Multidisciplinary Dataset for Abstract Sentence Classification |
| Authors | Connor Stead, Stephen Smith, Peter Busch, Savanid Vatanasakdakul |
| Abstract | |
| Tasks | Sentence Classification |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1016/ |
| https://www.aclweb.org/anthology/U19-1016 | |
| PWC | https://paperswithcode.com/paper/emerald-110k-a-multidisciplinary-dataset-for |
| Repo | |
| Framework | |
Orwellian-times at SemEval-2019 Task 4: A Stylistic and Content-based Classifier
| Title | Orwellian-times at SemEval-2019 Task 4: A Stylistic and Content-based Classifier |
| Authors | J{"u}rgen Knauth |
| Abstract | While fake news detection received quite a bit of attention in recent years, hyperpartisan news detection is still an underresearched topic. This paper presents our work towards building a classification system for hyperpartisan news detection in the context of the SemEval2019 shared task 4. We experiment with two different approaches - a more stylistic one, and a more content related one - achieving average results. |
| Tasks | Fake News Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2168/ |
| https://www.aclweb.org/anthology/S19-2168 | |
| PWC | https://paperswithcode.com/paper/orwellian-times-at-semeval-2019-task-4-a |
| Repo | |
| Framework | |
Stochastic Tokenization with a Language Model for Neural Text Classification
| Title | Stochastic Tokenization with a Language Model for Neural Text Classification |
| Authors | Tatsuya Hiraoka, Hiroyuki Shindo, Yuji Matsumoto |
| Abstract | For unsegmented languages such as Japanese and Chinese, tokenization of a sentence has a significant impact on the performance of text classification. Sentences are usually segmented with words or subwords by a morphological analyzer or byte pair encoding and then encoded with word (or subword) representations for neural networks. However, segmentation is potentially ambiguous, and it is unclear whether the segmented tokens achieve the best performance for the target task. In this paper, we propose a method to simultaneously learn tokenization and text classification to address these problems. Our model incorporates a language model for unsupervised tokenization into a text classifier and then trains both models simultaneously. To make the model robust against infrequent tokens, we sampled segmentation for each sentence stochastically during training, which resulted in improved performance of text classification. We conducted experiments on sentiment analysis as a text classification task and show that our method achieves better performance than previous methods. |
| Tasks | Language Modelling, Sentiment Analysis, Text Classification, Tokenization |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1158/ |
| https://www.aclweb.org/anthology/P19-1158 | |
| PWC | https://paperswithcode.com/paper/stochastic-tokenization-with-a-language-model |
| Repo | |
| Framework | |
Does an LSTM forget more than a CNN? An empirical study of catastrophic forgetting in NLP
| Title | Does an LSTM forget more than a CNN? An empirical study of catastrophic forgetting in NLP |
| Authors | Gaurav Arora, Afshin Rahimi, Timothy Baldwin |
| Abstract | Catastrophic forgetting {—} whereby a model trained on one task is fine-tuned on a second, and in doing so, suffers a {``}catastrophic{''} drop in performance over the first task {—} is a hurdle in the development of better transfer learning techniques. Despite impressive progress in reducing catastrophic forgetting, we have limited understanding of how different architectures and hyper-parameters affect forgetting in a network. With this study, we aim to understand factors which cause forgetting during sequential training. Our primary finding is that CNNs forget less than LSTMs. We show that max-pooling is the underlying operation which helps CNNs alleviate forgetting compared to LSTMs. We also found that curriculum learning, placing a hard task towards the end of task sequence, reduces forgetting. We analysed the effect of fine-tuning contextual embeddings on catastrophic forgetting and found that using embeddings as feature extractor is preferable to fine-tuning in continual learning setup. | |
| Tasks | Continual Learning, Transfer Learning |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1011/ |
| https://www.aclweb.org/anthology/U19-1011 | |
| PWC | https://paperswithcode.com/paper/does-an-lstm-forget-more-than-a-cnn-an |
| Repo | |
| Framework | |
Hilbert-Based Generative Defense for Adversarial Examples
| Title | Hilbert-Based Generative Defense for Adversarial Examples |
| Authors | Yang Bai, Yan Feng, Yisen Wang, Tao Dai, Shu-Tao Xia, Yong Jiang |
| Abstract | Adversarial perturbations of clean images are usually imperceptible for human eyes, but can confidently fool deep neural networks (DNNs) to make incorrect predictions. Such vulnerability of DNNs raises serious security concerns about their practicability in security-sensitive applications. To defend against such adversarial perturbations, recently developed PixelDefend purifies a perturbed image based on PixelCNN in a raster scan order (row/column by row/column). However, such scan mode insufficiently exploits the correlations between pixels, which further limits its robustness performance. Therefore, we propose a more advanced Hilbert curve scan order to model the pixel dependencies in this paper. Hilbert curve could well preserve local consistency when mapping from 2-D image to 1-D vector, thus the local features in neighboring pixels can be more effectively modeled. Moreover, the defensive power can be further improved via ensembles of Hilbert curve with different orientations. Experimental results demonstrate the superiority of our method over the state-of-the-art defenses against various adversarial attacks. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Bai_Hilbert-Based_Generative_Defense_for_Adversarial_Examples_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Bai_Hilbert-Based_Generative_Defense_for_Adversarial_Examples_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hilbert-based-generative-defense-for |
| Repo | |
| Framework | |
Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection
| Title | Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection |
| Authors | Junran Peng, Ming Sun, Zhao-Xiang Zhang, Tieniu Tan, Junjie Yan |
| Abstract | Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on architecture search for object detection, mainly because the costly ImageNet pretraining is always required for detectors. Training from scratch, as a substitute, demands more epochs to converge and brings no computation saving. To overcome this obstacle, we introduce a practical neural architecture transformation search(NATS) algorithm for object detection in this paper. Instead of searching and constructing an entire network, NATS explores the architecture space on the base of existing network and reusing its weights. We propose a novel neural architecture search strategy in channel-level instead of path-level and devise a search space specially targeting at object detection. With the combination of these two designs, an architecture transformation scheme could be discovered to adapt a network designed for image classification to task of object detection. Since our method is gradient-based and only searches for a transformation scheme, the weights of models pretrained in ImageNet could be utilized in both searching and retraining stage, which makes the whole process very efficient. The transformed network requires no extra parameters and FLOPs, and is friendly to hardware optimization, which is practical to use in real-time application. In experiments, we demonstrate the effectiveness of NATS on networks like {\em ResNet} and {\em ResNeXt}. Our transformed networks, combined with various detection frameworks, achieve significant improvements on the COCO dataset while keeping fast. |
| Tasks | Image Classification, Neural Architecture Search, Object Detection |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9576-efficient-neural-architecture-transformation-search-in-channel-level-for-object-detection |
| http://papers.nips.cc/paper/9576-efficient-neural-architecture-transformation-search-in-channel-level-for-object-detection.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-neural-architecture-transformation-1 |
| Repo | |
| Framework | |
Transfer Anomaly Detection by Inferring Latent Domain Representations
| Title | Transfer Anomaly Detection by Inferring Latent Domain Representations |
| Authors | Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara |
| Abstract | We propose a method to improve the anomaly detection performance on target domains by transferring knowledge on related domains. Although anomaly labels are valuable to learn anomaly detectors, they are difficult to obtain due to their rarity. To alleviate this problem, existing methods use anomalous and normal instances in the related domains as well as target normal instances. These methods require training on each target domain. However, this requirement can be problematic in some situations due to the high computational cost of training. The proposed method can infer the anomaly detectors for target domains without re-training by introducing the concept of latent domain vectors, which are latent representations of the domains and are used for inferring the anomaly detectors. The latent domain vector for each domain is inferred from the set of normal instances in the domain. The anomaly score function for each domain is modeled on the basis of autoencoders, and its domain-specific property is controlled by the latent domain vector. The anomaly score function for each domain is trained so that the scores of normal instances become low and the scores of anomalies become higher than those of the normal instances, while considering the uncertainty of the latent domain vectors. When target normal instances can be used during training, the proposed method can also use them for training in a unified framework. The effectiveness of the proposed method is demonstrated through experiments using one synthetic and four real-world datasets. Especially, the proposed method without re-training outperforms existing methods with target specific training. |
| Tasks | Anomaly Detection |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8517-transfer-anomaly-detection-by-inferring-latent-domain-representations |
| http://papers.nips.cc/paper/8517-transfer-anomaly-detection-by-inferring-latent-domain-representations.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-anomaly-detection-by-inferring |
| Repo | |
| Framework | |
Distinguishing Distributions When Samples Are Strategically Transformed
| Title | Distinguishing Distributions When Samples Are Strategically Transformed |
| Authors | Hanrui Zhang, Yu Cheng, Vincent Conitzer |
| Abstract | Often, a principal must make a decision based on data provided by an agent. Moreover, typically, that agent has an interest in the decision that is not perfectly aligned with that of the principal. Thus, the agent may have an incentive to select from or modify the samples he obtains before sending them to the principal. In other settings, the principal may not even be able to observe samples directly; instead, she must rely on signals that the agent is able to send based on the samples that he obtains, and he will choose these signals strategically. In this paper, we give necessary and sufficient conditions for when the principal can distinguish between agents of good'' and bad’’ types, when the type affects the distribution of samples that the agent has access to. We also study the computational complexity of checking these conditions. Finally, we study how many samples are needed. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8582-distinguishing-distributions-when-samples-are-strategically-transformed |
| http://papers.nips.cc/paper/8582-distinguishing-distributions-when-samples-are-strategically-transformed.pdf | |
| PWC | https://paperswithcode.com/paper/distinguishing-distributions-when-samples-are |
| Repo | |
| Framework | |
Revisit Automatic Error Detection for Wrong and Missing Translation – A Supervised Approach
| Title | Revisit Automatic Error Detection for Wrong and Missing Translation – A Supervised Approach |
| Authors | Wenqiang Lei, Weiwen Xu, Ai Ti Aw, Yuanxin Xiang, Tat Seng Chua |
| Abstract | While achieving great fluency, current machine translation (MT) techniques are bottle-necked by adequacy issues. To have a closer study of these issues and accelerate model development, we propose automatic detecting adequacy errors in MT hypothesis for MT model evaluation. To do that, we annotate missing and wrong translations, the two most prevalent issues for current neural machine translation model, in 15000 Chinese-English translation pairs. We build a supervised alignment model for translation error detection (AlignDet) based on a simple Alignment Triangle strategy to set the benchmark for automatic error detection task. We also discuss the difficulties of this task and the benefits of this task for existing evaluation metrics. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1087/ |
| https://www.aclweb.org/anthology/D19-1087 | |
| PWC | https://paperswithcode.com/paper/revisit-automatic-error-detection-for-wrong |
| Repo | |
| Framework | |
SJTU at MRP 2019: A Transition-Based Multi-Task Parser for Cross-Framework Meaning Representation Parsing
| Title | SJTU at MRP 2019: A Transition-Based Multi-Task Parser for Cross-Framework Meaning Representation Parsing |
| Authors | Hongxiao Bai, Hai Zhao |
| Abstract | This paper describes the system of our team SJTU for our participation in the CoNLL 2019 Shared Task: Cross-Framework Meaning Representation Parsing. The goal of the task is to advance data-driven parsing into graph-structured representations of sentence meaning. This task includes five meaning representation frameworks: DM, PSD, EDS, UCCA, and AMR. These frameworks have different properties and structures. To tackle all the frameworks in one model, it is needed to find out the commonality of them. In our work, we define a set of the transition actions to once-for-all tackle all the frameworks and train a transition-based model to parse the meaning representation. The adopted multi-task model also can allow learning for one framework to benefit the others. In the final official evaluation of the shared task, our system achieves 42{%} F1 unified MRP metric score. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2008/ |
| https://www.aclweb.org/anthology/K19-2008 | |
| PWC | https://paperswithcode.com/paper/sjtu-at-mrp-2019-a-transition-based-multi |
| Repo | |
| Framework | |
