Paper Group NANR 36
Matching on Balanced Nonlinear Representations for Treatment Effects Estimation. Proceedings of the Fourth International Conference on Dependency Linguistics (Depling 2017). Syntax-Semantics Interface: A Plea for a Deep Dependency Sentence Structure. Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP. Pushing the Lim …
Matching on Balanced Nonlinear Representations for Treatment Effects Estimation
| Title | Matching on Balanced Nonlinear Representations for Treatment Effects Estimation |
| Authors | Sheng Li, Yun Fu |
| Abstract | Estimating treatment effects from observational data is challenging due to the missing counterfactuals. Matching is an effective strategy to tackle this problem. The widely used matching estimators such as nearest neighbor matching (NNM) pair the treated units with the most similar control units in terms of covariates, and then estimate treatment effects accordingly. However, the existing matching estimators have poor performance when the distributions of control and treatment groups are unbalanced. Moreover, theoretical analysis suggests that the bias of causal effect estimation would increase with the dimension of covariates. In this paper, we aim to address these problems by learning low-dimensional balanced and nonlinear representations (BNR) for observational data. In particular, we convert counterfactual prediction as a classification problem, develop a kernel learning model with domain adaptation constraint, and design a novel matching estimator. The dimension of covariates will be significantly reduced after projecting data to a low-dimensional subspace. Experiments on several synthetic and real-world datasets demonstrate the effectiveness of our approach. |
| Tasks | Domain Adaptation |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6694-matching-on-balanced-nonlinear-representations-for-treatment-effects-estimation |
| http://papers.nips.cc/paper/6694-matching-on-balanced-nonlinear-representations-for-treatment-effects-estimation.pdf | |
| PWC | https://paperswithcode.com/paper/matching-on-balanced-nonlinear |
| Repo | |
| Framework | |
Proceedings of the Fourth International Conference on Dependency Linguistics (Depling 2017)
| Title | Proceedings of the Fourth International Conference on Dependency Linguistics (Depling 2017) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6500/ |
| https://www.aclweb.org/anthology/W17-6500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-fourth-international-3 |
| Repo | |
| Framework | |
Syntax-Semantics Interface: A Plea for a Deep Dependency Sentence Structure
| Title | Syntax-Semantics Interface: A Plea for a Deep Dependency Sentence Structure |
| Authors | Eva Haji{\v{c}}ov{'a} |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6502/ |
| https://www.aclweb.org/anthology/W17-6502 | |
| PWC | https://paperswithcode.com/paper/syntax-semantics-interface-a-plea-for-a-deep |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP
| Title | Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5300/ |
| https://www.aclweb.org/anthology/W17-5300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-evaluating |
| Repo | |
| Framework | |
Pushing the Limits of Translation Quality Estimation
| Title | Pushing the Limits of Translation Quality Estimation |
| Authors | Andr{'e} F. T. Martins, Marcin Junczys-Dowmunt, Fabio N. Kepler, Ram{'o}n Astudillo, Chris Hokamp, Roman Grundkiewicz |
| Abstract | Translation quality estimation is a task of growing importance in NLP, due to its potential to reduce post-editing human effort in disruptive ways. However, this potential is currently limited by the relatively low accuracy of existing systems. In this paper, we achieve remarkable improvements by exploiting synergies between the related tasks of word-level quality estimation and automatic post-editing. First, we stack a new, carefully engineered, neural model into a rich feature-based word-level quality estimation system. Then, we use the output of an automatic post-editing system as an extra feature, obtaining striking results on WMT16: a word-level FMULT1 score of 57.47{%} (an absolute gain of +7.95{%} over the current state of the art), and a Pearson correlation score of 65.56{%} for sentence-level HTER prediction (an absolute gain of +13.36{%}). |
| Tasks | Automatic Post-Editing |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/Q17-1015/ |
| https://www.aclweb.org/anthology/Q17-1015 | |
| PWC | https://paperswithcode.com/paper/pushing-the-limits-of-translation-quality |
| Repo | |
| Framework | |
Findings of the VarDial Evaluation Campaign 2017
| Title | Findings of the VarDial Evaluation Campaign 2017 |
| Authors | Marcos Zampieri, Shervin Malmasi, Nikola Ljube{\v{s}}i{'c}, Preslav Nakov, Ahmed Ali, J{"o}rg Tiedemann, Yves Scherrer, No{"e}mi Aepli |
| Abstract | We present the results of the VarDial Evaluation Campaign on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects, which we organized as part of the fourth edition of the VarDial workshop at EACL{'}2017. This year, we included four shared tasks: Discriminating between Similar Languages (DSL), Arabic Dialect Identification (ADI), German Dialect Identification (GDI), and Cross-lingual Dependency Parsing (CLP). A total of 19 teams submitted runs across the four tasks, and 15 of them wrote system description papers. |
| Tasks | Dependency Parsing, Language Identification |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1201/ |
| https://www.aclweb.org/anthology/W17-1201 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-vardial-evaluation-campaign |
| Repo | |
| Framework | |
The blocking effect and Korean caki
| Title | The blocking effect and Korean caki |
| Authors | Hyunjun Park, Haihua Pan |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1026/ |
| https://www.aclweb.org/anthology/Y17-1026 | |
| PWC | https://paperswithcode.com/paper/the-blocking-effect-and-korean-caki |
| Repo | |
| Framework | |
A Societal Sentiment Analysis: Predicting the Values and Ethics of Individuals by Analysing Social Media Content
| Title | A Societal Sentiment Analysis: Predicting the Values and Ethics of Individuals by Analysing Social Media Content |
| Authors | Tushar Maheshwari, Aishwarya N. Reganti, Samiksha Gupta, Anupam Jamatia, Upendra Kumar, Bj{"o}rn Gamb{"a}ck, Amitava Das |
| Abstract | To find out how users{'} social media behaviour and language are related to their ethical practices, the paper investigates applying Schwartz{'} psycholinguistic model of societal sentiment to social media text. The analysis is based on corpora collected from user essays as well as social media (Facebook and Twitter). Several experiments were carried out on the corpora to classify the ethical values of users, incorporating Linguistic Inquiry Word Count analysis, n-grams, topic models, psycholinguistic lexica, speech-acts, and non-linguistic information, while applying a range of machine learners (Support Vector Machines, Logistic Regression, and Random Forests) to identify the best linguistic and non-linguistic features for automatic classification of values and ethics. |
| Tasks | Sentiment Analysis, Topic Models |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1069/ |
| https://www.aclweb.org/anthology/E17-1069 | |
| PWC | https://paperswithcode.com/paper/a-societal-sentiment-analysis-predicting-the |
| Repo | |
| Framework | |
Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis
| Title | Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis |
| Authors | Amr Mousa, Bj{"o}rn Schuller |
| Abstract | Traditional learning-based approaches to sentiment analysis of written text use the concept of bag-of-words or bag-of-n-grams, where a document is viewed as a set of terms or short combinations of terms disregarding grammar rules or word order. Novel approaches de-emphasize this concept and view the problem as a sequence classification problem. In this context, recurrent neural networks (RNNs) have achieved significant success. The idea is to use RNNs as discriminative binary classifiers to predict a positive or negative sentiment label at every word position then perform a type of pooling to get a sentence-level polarity. Here, we investigate a novel generative approach in which a separate probability distribution is estimated for every sentiment using language models (LMs) based on long short-term memory (LSTM) RNNs. We introduce a novel type of LM using a modified version of bidirectional LSTM (BLSTM) called contextual BLSTM (cBLSTM), where the probability of a word is estimated based on its full left and right contexts. Our approach is compared with a BLSTM binary classifier. Significant improvements are observed in classifying the IMDB movie review dataset. Further improvements are achieved via model combination. |
| Tasks | Decision Making, Dimensionality Reduction, Opinion Mining, Sentiment Analysis, Subjectivity Analysis, Text Classification, Tokenization |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1096/ |
| https://www.aclweb.org/anthology/E17-1096 | |
| PWC | https://paperswithcode.com/paper/contextual-bidirectional-long-short-term |
| Repo | |
| Framework | |
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
| Title | Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-2000/ |
| https://www.aclweb.org/anthology/D17-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2017-conference-on-1 |
| Repo | |
| Framework | |
Enjambment Detection in a Large Diachronic Corpus of Spanish Sonnets
| Title | Enjambment Detection in a Large Diachronic Corpus of Spanish Sonnets |
| Authors | Pablo Ruiz, Clara Mart{'\i}nez Cant{'o}n, Thierry Poibeau, Elena Gonz{'a}lez-Blanco |
| Abstract | Enjambment takes place when a syntactic unit is broken up across two lines of poetry, giving rise to different stylistic effects. In Spanish literary studies, there are unclear points about the types of stylistic effects that can arise, and under which linguistic conditions. To systematically gather evidence about this, we developed a system to automatically identify enjambment (and its type) in Spanish. For evaluation, we manually annotated a reference corpus covering different periods. As a scholarly corpus to apply the tool, from public HTML sources we created a diachronic corpus covering four centuries of sonnets (3750 poems), and we analyzed the occurrence of enjambment across stanzaic boundaries in different periods. Besides, we found examples that highlight limitations in current definitions of enjambment. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2204/ |
| https://www.aclweb.org/anthology/W17-2204 | |
| PWC | https://paperswithcode.com/paper/enjambment-detection-in-a-large-diachronic |
| Repo | |
| Framework | |
Automatic Frankensteining: Creating Complex Ensembles Autonomously
| Title | Automatic Frankensteining: Creating Complex Ensembles Autonomously |
| Authors | Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme |
| Abstract | Automating machine learning by providing techniques that autonomously find the best algorithm, hyperparameter configuration and preprocessing is helpful for both researchers and practitioners. Therefore, it is not surprising that automated machine learning has become a very interesting field of research. While current research is mainly focusing on finding good pairs of algorithms and hyperparameter configurations, we will present an approach that automates the process of creating a top performing ensemble of several layers, different algorithms and hyperparameter configurations. These kinds of ensembles are called jokingly Frankenstein ensembles and proved their benefit on versatile data sets in many machine learning challenges. We compare our approach Automatic Frankensteining with the current state of the art for automated machine learning on 80 different data sets and can show that it outperforms them on the majority using the same training time. Furthermore, we compare Automatic Frankensteining on a large scale data set to more than 3,500 machine learning expert teams and are able to outperform more than 3,000 of them within 12 CPU hours. |
| Tasks | AutoML |
| Published | 2017-01-01 |
| URL | https://epubs.siam.org/doi/abs/10.1137/1.9781611974973.83 |
| https://www.ismll.uni-hildesheim.de/pub/pdfs/wistuba_et_al_SDM_2017.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-frankensteining-creating-complex |
| Repo | |
| Framework | |
探究不同領域文件之可讀性分析 (Exploring Readability Analysis on Multi-Domain Texts) [In Chinese]
| Title | 探究不同領域文件之可讀性分析 (Exploring Readability Analysis on Multi-Domain Texts) [In Chinese] |
| Authors | Hou-Chiang Tseng, Yao-Ting Sung, Berlin Chen |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1011/ |
| https://www.aclweb.org/anthology/O17-1011 | |
| PWC | https://paperswithcode.com/paper/ca-ae-aaa1a-ea-exploring-readability-analysis |
| Repo | |
| Framework | |
Application of deep convolutional neural network for automated detection of myocardial infarction using ecg signals
| Title | Application of deep convolutional neural network for automated detection of myocardial infarction using ecg signals |
| Authors | U Rajendra Acharya. Hamido Fujita, Hamido Fujita, Shu Lih Oh, Yuki Hagiwara, Jen Hong Tan, Muhammad Adam |
| Abstract | The electrocardiogram (ECG) is a useful diagnostic tool to diagnose various cardiovascular diseases (CVDs) such as myocardial infarction (MI). The ECG records the heart’s electrical activity and these signals are able to reflect the abnormal activity of the heart. However, it is challenging to visually interpret the ECG signals due to its small amplitude and duration. Therefore, we propose a novel approach to automatically detect the MI using ECG signals. In this study, we implemented a convolutional neural network (CNN) algorithm for the automated detection of a normal and MI ECG beats (with noise and without noise). We achieved an average accuracy of 93.53% and 95.22% using ECG beats with noise and without noise removal respectively. Further, no feature extraction or selection is performed in this work. Hence, our proposed algorithm can accurately detect the unknown ECG signals even with noise. So, this system can be introduced in clinical settings to aid the clinicians in the diagnosis of MI. |
| Tasks | Electrocardiography (ECG), Myocardial infarction detection |
| Published | 2017-06-01 |
| URL | https://doi.org/10.1016/j.ins.2017.06.027 |
| https://www.researchgate.net/publication/317821702_Application_of_Deep_Convolutional_Neural_Network_for_Automated_Detection_of_Myocardial_Infarction_Using_ECG_Signals | |
| PWC | https://paperswithcode.com/paper/application-of-deep-convolutional-neural-2 |
| Repo | |
| Framework | |
Teaching Machines to Describe Images with Natural Language Feedback
| Title | Teaching Machines to Describe Images with Natural Language Feedback |
| Authors | Huan Ling, Sanja Fidler |
| Abstract | Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a learning agent in the form of natural language. A descriptive sentence can provide a stronger learning signal than a numeric reward in that it can easily point to where the mistakes are and how to correct them. We focus on the problem of image captioning in which the quality of the output can easily be judged by non-experts. We propose a phrase-based captioning model trained with policy gradients, and design a critic that provides reward to the learner by conditioning on the human-provided feedback. We show that by exploiting descriptive feedback our model learns to perform better than when given independently written human captions. |
| Tasks | Image Captioning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7092-teaching-machines-to-describe-images-with-natural-language-feedback |
| http://papers.nips.cc/paper/7092-teaching-machines-to-describe-images-with-natural-language-feedback.pdf | |
| PWC | https://paperswithcode.com/paper/teaching-machines-to-describe-images-with |
| Repo | |
| Framework | |
