Paper Group NANR 212
E2GAN: End-to-End Generative Adversarial Network or Multivariate Time Series Imputation. Contextualized context2vec. The Myth of Double-Blind Review Revisited: ACL vs. EMNLP. Interpretability Analysis of Heartbeat Classification Based on Heartbeat Activity’s Global Sequence Features and BiLSTM-Attention Neural Network. Stance Detection in Code-Mixe …
E2GAN: End-to-End Generative Adversarial Network or Multivariate Time Series Imputation
| Title | E2GAN: End-to-End Generative Adversarial Network or Multivariate Time Series Imputation |
| Authors | Yonghong Luo, Ying Zhang, Xiangrui Cai, Xiaojie Yuan |
| Abstract | The missing values, appear in most of multivariate time series, prevent advanced analysis of multivariate time series data. Existing imputation approaches try to deal with missing values by deletion, statistical imputation, machine learning based imputation and generative imputation. However, these methods are either incapable of dealing with temporal information or multi-stage. This paper proposes an end-to-end generative model E2GAN to impute missing values in multivariate time series. With the help of the discriminative loss and the squared error loss, E2GAN can imputethe incomplete time series by the nearest generated complete time series at one stage. Experiments on multiple real-world datasets show that our model outperforms the baselines on the imputation accuracy and achieves state-of-the-art classification/regression results on the downstream applications. Additionally, our method also gains better time efficiency than multi-stage method on the training of neural networks. |
| Tasks | Imputation, Multivariate Time Series Imputation, Time Series |
| Published | 2019-08-10 |
| URL | https://doi.org/10.24963/ijcai.2019/429 |
| https://www.ijcai.org/proceedings/2019/0429.pdf | |
| PWC | https://paperswithcode.com/paper/e2gan-end-to-end-generative-adversarial |
| Repo | |
| Framework | |
Contextualized context2vec
| Title | Contextualized context2vec |
| Authors | Kazuki Ashihara, Tomoyuki Kajiwara, Yuki Arase, Satoru Uchida |
| Abstract | Lexical substitution ranks substitution candidates from the viewpoint of paraphrasability for a target word in a given sentence. There are two major approaches for lexical substitution: (1) generating contextualized word embeddings by assigning multiple embeddings to one word and (2) generating context embeddings using the sentence. Herein we propose a method that combines these two approaches to contextualize word embeddings for lexical substitution. Experiments demonstrate that our method outperforms the current state-of-the-art method. We also create CEFR-LP, a new evaluation dataset for the lexical substitution task. It has a wider coverage of substitution candidates than previous datasets and assigns English proficiency levels to all target words and substitution candidates. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5552/ |
| https://www.aclweb.org/anthology/D19-5552 | |
| PWC | https://paperswithcode.com/paper/contextualized-context2vec |
| Repo | |
| Framework | |
The Myth of Double-Blind Review Revisited: ACL vs. EMNLP
| Title | The Myth of Double-Blind Review Revisited: ACL vs. EMNLP |
| Authors | Cornelia Caragea, Ana Uban, Liviu P. Dinu |
| Abstract | The review and selection process for scientific paper publication is essential for the quality of scholarly publications in a scientific field. The double-blind review system, which enforces author anonymity during the review period, is widely used by prestigious conferences and journals to ensure the integrity of this process. Although the notion of anonymity in the double-blind review has been questioned before, the availability of full text paper collections brings new opportunities for exploring the question: Is the double-blind review process really double-blind? We study this question on the ACL and EMNLP paper collections and present an analysis on how well deep learning techniques can infer the authors of a paper. Specifically, we explore Convolutional Neural Networks trained on various aspects of a paper, e.g., content, style features, and references, to understand the extent to which we can infer the authors of a paper and what aspects contribute the most. Our results show that the authors of a paper can be inferred with accuracy as high as 87{%} on ACL and 78{%} on EMNLP for the top 100 most prolific authors. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1236/ |
| https://www.aclweb.org/anthology/D19-1236 | |
| PWC | https://paperswithcode.com/paper/the-myth-of-double-blind-review-revisited-acl |
| Repo | |
| Framework | |
Interpretability Analysis of Heartbeat Classification Based on Heartbeat Activity’s Global Sequence Features and BiLSTM-Attention Neural Network
| Title | Interpretability Analysis of Heartbeat Classification Based on Heartbeat Activity’s Global Sequence Features and BiLSTM-Attention Neural Network |
| Authors | Runchuan Li, Xingjin Zhang, Honghua Dai, Bing Zhou, Zongmin Wang |
| Abstract | Arrhythmia is a disease that threatens human life. Therefore, timely diagnosis of arrhythmia is of great significance in preventing heart disease and sudden cardiac death. The BiLSTM-Attention neural network model with heartbeat activity’s global sequence features can effectively improve the accuracy of heartbeat classification. Firstly, the noise is removed by the continuous wavelet transform method. Secondly, the peak of the R wave is detected by the tagged database, and then the P-QRS-T wave morphology and the RR interval are extracted. This feature set is heartbeat activity’s global sequence features, which combines single heartbeat morphology and 21 consecutive RR intervals. Finally, the Bi-LSTM algorithm and the BiLSTM-Attention algorithm are used to identify heartbeat category respectively, and the MIT-BIH arrhythmia database is used to verify the algorithm. The results show that the BiLSTM-Attention model combined with heartbeat activity’s global sequence features has higher interpretability than other methods discussed in this paper. |
| Tasks | Arrhythmia Detection, Electrocardiography (ECG), Heartbeat Classification |
| Published | 2019-08-07 |
| URL | https://doi.org/10.1109/ACCESS.2019.2933473 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8790681 | |
| PWC | https://paperswithcode.com/paper/interpretability-analysis-of-heartbeat |
| Repo | |
| Framework | |
Stance Detection in Code-Mixed Hindi-English Social Media Data using Multi-Task Learning
| Title | Stance Detection in Code-Mixed Hindi-English Social Media Data using Multi-Task Learning |
| Authors | Sushmitha Reddy Sane, Suraj Tripathi, Koushik Reddy Sane, Radhika Mamidi |
| Abstract | Social media sites like Facebook, Twitter, and other microblogging forums have emerged as a platform for people to express their opinions and views on different issues and events. It is often observed that people tend to take a stance; in favor, against or neutral towards a particular topic. The task of assessing the stance taken by the individual became significantly important with the emergence in the usage of online social platforms. Automatic stance detection system understands the user{'}s stance by analyzing the standalone texts against a target entity. Due to the limited contextual information a single sentence provides, it is challenging to solve this task effectively. In this paper, we introduce a Multi-Task Learning (MTL) based deep neural network architecture for automatically detecting stance present in the code-mixed corpus. We apply our approach on Hindi-English code-mixed corpus against the target entity - {``}Demonetisation.{''} Our best model achieved the result with a stance prediction accuracy of 63.2{%} which is a 4.5{%} overall accuracy improvement compared to the current supervised classification systems developed using the benchmark dataset for code-mixed data stance detection. | |
| Tasks | Multi-Task Learning, Stance Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1301/ |
| https://www.aclweb.org/anthology/W19-1301 | |
| PWC | https://paperswithcode.com/paper/stance-detection-in-code-mixed-hindi-english |
| Repo | |
| Framework | |
Semantic descriptions of French derivational relations in a families-and-paradigms framework
| Title | Semantic descriptions of French derivational relations in a families-and-paradigms framework |
| Authors | Daniele Sanacore, Nabil Hathout, Fiammetta Namer |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8503/ |
| https://www.aclweb.org/anthology/W19-8503 | |
| PWC | https://paperswithcode.com/paper/semantic-descriptions-of-french-derivational |
| Repo | |
| Framework | |
Comprehensive Multi-Dataset Evaluation of Reading Comprehension
| Title | Comprehensive Multi-Dataset Evaluation of Reading Comprehension |
| Authors | Dheeru Dua, Ananth Gottumukkala, Alon Talmor, Sameer Singh, Matt Gardner |
| Abstract | Reading comprehension is one of the crucial tasks for furthering research in natural language understanding. A lot of diverse reading comprehension datasets have recently been introduced to study various phenomena in natural language, ranging from simple paraphrase matching and entity typing to entity tracking and understanding the implications of the context. Given the availability of many such datasets, comprehensive and reliable evaluation is tedious and time-consuming for researchers working on this problem. We present an evaluation server, ORB, that reports performance on seven diverse reading comprehension datasets, encouraging and facilitating testing a single model{'}s capability in understanding a wide variety of reading phenomena. The evaluation server places no restrictions on how models are trained, so it is a suitable test bed for exploring training paradigms and representation learning for general reading facility. As more suitable datasets are released, they will be added to the evaluation server. We also collect and include synthetic augmentations for these datasets, testing how well models can handle out-of-domain questions. |
| Tasks | Entity Typing, Reading Comprehension, Representation Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5820/ |
| https://www.aclweb.org/anthology/D19-5820 | |
| PWC | https://paperswithcode.com/paper/comprehensive-multi-dataset-evaluation-of |
| Repo | |
| Framework | |
Enhancing Unsupervised Sentence Similarity Methods with Deep Contextualised Word Representations
| Title | Enhancing Unsupervised Sentence Similarity Methods with Deep Contextualised Word Representations |
| Authors | Tharindu Ranasinghe, Constantin Orasan, Ruslan Mitkov |
| Abstract | Calculating Semantic Textual Similarity (STS) plays a significant role in many applications such as question answering, document summarisation, information retrieval and information extraction. All modern state of the art STS methods rely on word embeddings one way or another. The recently introduced contextualised word embeddings have proved more effective than standard word embeddings in many natural language processing tasks. This paper evaluates the impact of several contextualised word embeddings on unsupervised STS methods and compares it with the existing supervised/unsupervised STS methods for different datasets in different languages and different domains |
| Tasks | Information Retrieval, Question Answering, Semantic Textual Similarity, Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1115/ |
| https://www.aclweb.org/anthology/R19-1115 | |
| PWC | https://paperswithcode.com/paper/enhancing-unsupervised-sentence-similarity |
| Repo | |
| Framework | |
Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior
| Title | Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior |
| Authors | Lizhi Wang, Chen Sun, Ying Fu, Min H. Kim, Hua Huang |
| Abstract | Regularization is a fundamental technique to solve an ill-posed optimization problem robustly and is essential to reconstruct compressive hyperspectral images. Various hand-crafted priors have been employed as a regularizer but are often insufficient to handle the wide variety of spectra of natural hyperspectral images, resulting in poor reconstruction quality. Moreover, the prior-regularized optimization requires manual tweaking of its weight parameters to achieve a balance between the spatial and spectral fidelity of result images. In this paper, we present a novel hyperspectral image reconstruction algorithm that substitutes the traditional hand-crafted prior with a data-driven prior, based on an optimization-inspired network. Our method consists of two main parts: First, we learn a novel data-driven prior that regularizes the optimization problem with a goal to boost the spatial-spectral fidelity. Our data-driven prior learns both local coherence and dynamic characteristics of natural hyperspectral images. Second, we combine our regularizer with an optimization-inspired network to overcome the heavy computation problem in the traditional iterative optimization methods. We learn the complete parameters in the network through end-to-end training, enabling robust performance with high accuracy. Extensive simulation and hardware experiments validate the superior performance of our method over the state-of-the-art methods. |
| Tasks | Image Reconstruction |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Hyperspectral_Image_Reconstruction_Using_a_Deep_Spatial-Spectral_Prior_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Hyperspectral_Image_Reconstruction_Using_a_Deep_Spatial-Spectral_Prior_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-image-reconstruction-using-a |
| Repo | |
| Framework | |
Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models
| Title | Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models |
| Authors | Yiben Yang, Ji-Ping Wang, Doug Downey |
| Abstract | Recurrent neural network language models (RNNLM) form a valuable foundation for many NLP systems, but training the models can be computationally expensive, and may take days to train on a large corpus. We explore a technique that uses large corpus n-gram statistics as a regularizer for training a neural network LM on a smaller corpus. In experiments with the Billion-Word and Wikitext corpora, we show that the technique is effective, and more time-efficient than simply training on a larger sequential corpus. We also introduce new strategies for selecting the most informative n-grams, and show that these boost efficiency. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1330/ |
| https://www.aclweb.org/anthology/N19-1330 | |
| PWC | https://paperswithcode.com/paper/using-large-corpus-n-gram-statistics-to |
| Repo | |
| Framework | |
Revisiting Reweighted Wake-Sleep
| Title | Revisiting Reweighted Wake-Sleep |
| Authors | Tuan Anh Le, Adam R. Kosiorek, N. Siddharth, Yee Whye Teh, Frank Wood |
| Abstract | Discrete latent-variable models, while applicable in a variety of settings, can often be difficult to learn. Sampling discrete latent variables can result in high-variance gradient estimators for two primary reasons: 1) branching on the samples within the model, and 2) the lack of a pathwise derivative for the samples. While current state-of-the-art methods employ control-variate schemes for the former and continuous-relaxation methods for the latter, their utility is limited by the complexities of implementing and training effective control-variate schemes and the necessity of evaluating (potentially exponentially) many branch paths in the model. Here, we revisit the Reweighted Wake Sleep (RWS; Bornschein and Bengio, 2015) algorithm, and through extensive evaluations, show that it circumvents both these issues, outperforming current state-of-the-art methods in learning discrete latent-variable models. Moreover, we observe that, unlike the Importance-weighted Autoencoder, RWS learns better models and inference networks with increasing numbers of particles, and that its benefits extend to continuous latent-variable models as well. Our results suggest that RWS is a competitive, often preferable, alternative for learning deep generative models. |
| Tasks | Latent Variable Models |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJzuKiC9KX |
| https://openreview.net/pdf?id=BJzuKiC9KX | |
| PWC | https://paperswithcode.com/paper/revisiting-reweighted-wake-sleep-1 |
| Repo | |
| Framework | |
Question Answering in the Biomedical Domain
| Title | Question Answering in the Biomedical Domain |
| Authors | Vincent Nguyen |
| Abstract | Question answering techniques have mainly been investigated in open domains. However, there are particular challenges in extending these open-domain techniques to extend into the biomedical domain. Question answering focusing on patients is less studied. We find that there are some challenges in patient question answering such as limited annotated data, lexical gap and quality of answer spans. We aim to address some of these gaps by extending and developing upon the literature to design a question answering system that can decide on the most appropriate answers for patients attempting to self-diagnose while including the ability to abstain from answering when confidence is low. |
| Tasks | Question Answering |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2008/ |
| https://www.aclweb.org/anthology/P19-2008 | |
| PWC | https://paperswithcode.com/paper/question-answering-in-the-biomedical-domain |
| Repo | |
| Framework | |
Interpretable Relevant Emotion Ranking with Event-Driven Attention
| Title | Interpretable Relevant Emotion Ranking with Event-Driven Attention |
| Authors | Yang Yang, Deyu Zhou, Yulan He, Meng Zhang |
| Abstract | Multiple emotions with different intensities are often evoked by events described in documents. Oftentimes, such event information is hidden and needs to be discovered from texts. Unveiling the hidden event information can help to understand how the emotions are evoked and provide explainable results. However, existing studies often ignore the latent event information. In this paper, we proposed a novel interpretable relevant emotion ranking model with the event information incorporated into a deep learning architecture using the event-driven attentions. Moreover, corpus-level event embeddings and document-level event distributions are introduced respectively to consider the global events in corpus and the document-specific events simultaneously. Experimental results on three real-world corpora show that the proposed approach performs remarkably better than the state-of-the-art emotion detection approaches and multi-label approaches. Moreover, interpretable results can be obtained to shed light on the events which trigger certain emotions. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1017/ |
| https://www.aclweb.org/anthology/D19-1017 | |
| PWC | https://paperswithcode.com/paper/interpretable-relevant-emotion-ranking-with |
| Repo | |
| Framework | |
A Multilingual Topic Model for Learning Weighted Topic Links Across Corpora with Low Comparability
| Title | A Multilingual Topic Model for Learning Weighted Topic Links Across Corpora with Low Comparability |
| Authors | Weiwei Yang, Jordan Boyd-Graber, Philip Resnik |
| Abstract | Multilingual topic models (MTMs) learn topics on documents in multiple languages. Past models align topics across languages by implicitly assuming the documents in different languages are highly comparable, often a false assumption. We introduce a new model that does not rely on this assumption, particularly useful in important low-resource language scenarios. Our MTM learns weighted topic links and connects cross-lingual topics only when the dominant words defining them are similar, outperforming LDA and previous MTMs in classification tasks using documents{'} topic posteriors as features. It also learns coherent topics on documents with low comparability. |
| Tasks | Topic Models |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1120/ |
| https://www.aclweb.org/anthology/D19-1120 | |
| PWC | https://paperswithcode.com/paper/a-multilingual-topic-model-for-learning |
| Repo | |
| Framework | |
Coreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering
| Title | Coreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering |
| Authors | Hai-Long Trieu, Anh-Khoa Duong Nguyen, Nhung Nguyen, Makoto Miwa, Hiroya Takamura, Sophia Ananiadou |
| Abstract | This paper describes our system developed for the coreference resolution task of the CRAFT Shared Tasks 2019. The CRAFT corpus is more challenging than other existing corpora because it contains full text articles. We have employed an existing span-based state-of-theart neural coreference resolution system as a baseline system. We enhance the system with two different techniques to capture longdistance coreferent pairs. Firstly, we filter noisy mentions based on parse trees with increasing the number of antecedent candidates. Secondly, instead of relying on the LSTMs, we integrate the highly expressive language model{–}BERT into our model. Experimental results show that our proposed systems significantly outperform the baseline. The best performing system obtained F-scores of 44{%}, 48{%}, 39{%}, 49{%}, 40{%}, and 57{%} on the test set with B3, BLANC, CEAFE, CEAFM, LEA, and MUC metrics, respectively. Additionally, the proposed model is able to detect coreferent pairs in long distances, even with a distance of more than 200 sentences. |
| Tasks | Coreference Resolution, Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5727/ |
| https://www.aclweb.org/anthology/D19-5727 | |
| PWC | https://paperswithcode.com/paper/coreference-resolution-in-full-text-articles |
| Repo | |
| Framework | |
