Paper Group NANR 88
![Paper Group NANR 88](/2016/images/pwc/paper-all_hu5eb227011acad6b922a57ded5f50b7dc_25576_900x500_fit_q75_box.jpg)
CoastalCPH at SemEval-2016 Task 11: The importance of designing your Neural Networks right. VCU-TSA at Semeval-2016 Task 4: Sentiment Analysis in Twitter. NRU-HSE at SemEval-2016 Task 4: Comparative Analysis of Two Iterative Methods Using Quantification Library. Using Context to Predict the Purpose of Argumentative Writing Revisions. Statistical In …
CoastalCPH at SemEval-2016 Task 11: The importance of designing your Neural Networks right
Title | CoastalCPH at SemEval-2016 Task 11: The importance of designing your Neural Networks right |
Authors | Joachim Bingel, Natalie Schluter, H{'e}ctor Mart{'\i}nez Alonso |
Abstract | |
Tasks | Complex Word Identification, Lexical Simplification, Sentence Compression, Text Simplification |
Published | 2016-06-01 |
URL | https://www.aclweb.org/anthology/S16-1160/ |
https://www.aclweb.org/anthology/S16-1160 | |
PWC | https://paperswithcode.com/paper/coastalcph-at-semeval-2016-task-11-the |
Repo | |
Framework | |
VCU-TSA at Semeval-2016 Task 4: Sentiment Analysis in Twitter
Title | VCU-TSA at Semeval-2016 Task 4: Sentiment Analysis in Twitter |
Authors | Gerard Briones, Kasun Amarasinghe, Bridget McInnes |
Abstract | |
Tasks | Sentiment Analysis |
Published | 2016-06-01 |
URL | https://www.aclweb.org/anthology/S16-1032/ |
https://www.aclweb.org/anthology/S16-1032 | |
PWC | https://paperswithcode.com/paper/vcu-tsa-at-semeval-2016-task-4-sentiment |
Repo | |
Framework | |
NRU-HSE at SemEval-2016 Task 4: Comparative Analysis of Two Iterative Methods Using Quantification Library
Title | NRU-HSE at SemEval-2016 Task 4: Comparative Analysis of Two Iterative Methods Using Quantification Library |
Authors | Nikolay Karpov, Alex Porshnev, er, Kirill Rudakov |
Abstract | |
Tasks | Document Classification, Opinion Mining, Sentiment Analysis, Word Sense Disambiguation |
Published | 2016-06-01 |
URL | https://www.aclweb.org/anthology/S16-1025/ |
https://www.aclweb.org/anthology/S16-1025 | |
PWC | https://paperswithcode.com/paper/nru-hse-at-semeval-2016-task-4-comparative |
Repo | |
Framework | |
Using Context to Predict the Purpose of Argumentative Writing Revisions
Title | Using Context to Predict the Purpose of Argumentative Writing Revisions |
Authors | Fan Zhang, Diane Litman |
Abstract | |
Tasks | Structured Prediction |
Published | 2016-06-01 |
URL | https://www.aclweb.org/anthology/N16-1168/ |
https://www.aclweb.org/anthology/N16-1168 | |
PWC | https://paperswithcode.com/paper/using-context-to-predict-the-purpose-of |
Repo | |
Framework | |
Statistical Inference for Pairwise Graphical Models Using Score Matching
Title | Statistical Inference for Pairwise Graphical Models Using Score Matching |
Authors | Ming Yu, Mladen Kolar, Varun Gupta |
Abstract | Probabilistic graphical models have been widely used to model complex systems and aid scientific discoveries. As a result, there is a large body of literature focused on consistent model selection. However, scientists are often interested in understanding uncertainty associated with the estimated parameters, which current literature has not addressed thoroughly. In this paper, we propose a novel estimator for edge parameters for pairwise graphical models based on Hyv"arinen scoring rule. Hyv"arinen scoring rule is especially useful in cases where the normalizing constant cannot be obtained efficiently in a closed form. We prove that the estimator is $\sqrt{n}$-consistent and asymptotically Normal. This result allows us to construct confidence intervals for edge parameters, as well as, hypothesis tests. We establish our results under conditions that are typically assumed in the literature for consistent estimation. However, we do not require that the estimator consistently recovers the graph structure. In particular, we prove that the asymptotic distribution of the estimator is robust to model selection mistakes and uniformly valid for a large number of data-generating processes. We illustrate validity of our estimator through extensive simulation studies. |
Tasks | Model Selection |
Published | 2016-12-01 |
URL | http://papers.nips.cc/paper/6530-statistical-inference-for-pairwise-graphical-models-using-score-matching |
http://papers.nips.cc/paper/6530-statistical-inference-for-pairwise-graphical-models-using-score-matching.pdf | |
PWC | https://paperswithcode.com/paper/statistical-inference-for-pairwise-graphical |
Repo | |
Framework | |
Machine Learning for Metrical Analysis of English Poetry
Title | Machine Learning for Metrical Analysis of English Poetry |
Authors | Manex Agirrezabal, I{~n}aki Alegria, Mans Hulden |
Abstract | In this work we tackle the challenge of identifying rhythmic patterns in poetry written in English. Although poetry is a literary form that makes use standard meters usually repeated among different authors, we will see in this paper how performing such analyses is a difficult task in machine learning due to the unexpected deviations from such standard patterns. After breaking down some examples of classical poetry, we apply a number of NLP techniques for the scansion of poetry, training and testing our systems against a human-annotated corpus. With these experiments, our purpose is establish a baseline of automatic scansion of poetry using NLP tools in a straightforward manner and to raise awareness of the difficulties of this task. |
Tasks | Structured Prediction |
Published | 2016-12-01 |
URL | https://www.aclweb.org/anthology/C16-1074/ |
https://www.aclweb.org/anthology/C16-1074 | |
PWC | https://paperswithcode.com/paper/machine-learning-for-metrical-analysis-of |
Repo | |
Framework | |
Selective Co-occurrences for Word-Emotion Association
Title | Selective Co-occurrences for Word-Emotion Association |
Authors | Ameeta Agrawal, Aijun An |
Abstract | Emotion classification from text typically requires some degree of word-emotion association, either gathered from pre-existing emotion lexicons or calculated using some measure of semantic relatedness. Most emotion lexicons contain a fixed number of emotion categories and provide a rather limited coverage. Current measures of computing semantic relatedness, on the other hand, do not adapt well to the specific task of word-emotion association and therefore, yield average results. In this work, we propose an unsupervised method of learning word-emotion association from large text corpora, called Selective Co-occurrences (SECO), by leveraging the property of mutual exclusivity generally exhibited by emotions. Extensive evaluation, using just one seed word per emotion category, indicates the effectiveness of the proposed approach over three emotion lexicons and two state-of-the-art models of word embeddings on three datasets from different domains. |
Tasks | Emotion Classification, Emotion Recognition, Word Embeddings |
Published | 2016-12-01 |
URL | https://www.aclweb.org/anthology/C16-1149/ |
https://www.aclweb.org/anthology/C16-1149 | |
PWC | https://paperswithcode.com/paper/selective-co-occurrences-for-word-emotion |
Repo | |
Framework | |
Verb Phrase Ellipsis Resolution Using Discriminative and Margin-Infused Algorithms
Title | Verb Phrase Ellipsis Resolution Using Discriminative and Margin-Infused Algorithms |
Authors | Kian Kenyon-Dean, Jackie Chi Kit Cheung, Doina Precup |
Abstract | |
Tasks | Coreference Resolution |
Published | 2016-11-01 |
URL | https://www.aclweb.org/anthology/D16-1179/ |
https://www.aclweb.org/anthology/D16-1179 | |
PWC | https://paperswithcode.com/paper/verb-phrase-ellipsis-resolution-using |
Repo | |
Framework | |
Data Management Plans and Data Centers
Title | Data Management Plans and Data Centers |
Authors | Denise DiPersio, Christopher Cieri, Daniel Jaquette |
Abstract | Data management plans, data sharing plans and the like are now required by funders worldwide as part of research proposals. Concerned with promoting the notion of open scientific data, funders view such plans as the framework for satisfying the generally accepted requirements for data generated in funded research projects, among them that it be accessible, usable, standardized to the degree possible, secure and stable. This paper examines the origins of data management plans, their requirements and issues they raise for data centers and HLT resource development in general. |
Tasks | |
Published | 2016-05-01 |
URL | https://www.aclweb.org/anthology/L16-1396/ |
https://www.aclweb.org/anthology/L16-1396 | |
PWC | https://paperswithcode.com/paper/data-management-plans-and-data-centers |
Repo | |
Framework | |
Improving Users’ Demographic Prediction via the Videos They Talk about
Title | Improving Users’ Demographic Prediction via the Videos They Talk about |
Authors | Yuan Wang, Yang Xiao, Chao Ma, Zhen Xiao |
Abstract | |
Tasks | Topic Models |
Published | 2016-11-01 |
URL | https://www.aclweb.org/anthology/D16-1143/ |
https://www.aclweb.org/anthology/D16-1143 | |
PWC | https://paperswithcode.com/paper/improving-users-demographic-prediction-via |
Repo | |
Framework | |
Find the word that does not belong: A Framework for an Intrinsic Evaluation of Word Vector Representations
Title | Find the word that does not belong: A Framework for an Intrinsic Evaluation of Word Vector Representations |
Authors | Jos{'e} Camacho-Collados, Roberto Navigli |
Abstract | |
Tasks | Machine Translation, Outlier Detection, Question Answering, Semantic Role Labeling, Spelling Correction, Word Sense Disambiguation |
Published | 2016-08-01 |
URL | https://www.aclweb.org/anthology/W16-2508/ |
https://www.aclweb.org/anthology/W16-2508 | |
PWC | https://paperswithcode.com/paper/find-the-word-that-does-not-belong-a |
Repo | |
Framework | |
Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning
Title | Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning |
Authors | Taiji Suzuki, Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami |
Abstract | We investigate the statistical performance and computational efficiency of the alternating minimization procedure for nonparametric tensor learning. Tensor modeling has been widely used for capturing the higher order relations between multimodal data sources. In addition to a linear model, a nonlinear tensor model has been received much attention recently because of its high flexibility. We consider an alternating minimization procedure for a general nonlinear model where the true function consists of components in a reproducing kernel Hilbert space (RKHS). In this paper, we show that the alternating minimization method achieves linear convergence as an optimization algorithm and that the generalization error of the resultant estimator yields the minimax optimality. We apply our algorithm to some multitask learning problems and show that the method actually shows favorable performances. |
Tasks | |
Published | 2016-12-01 |
URL | http://papers.nips.cc/paper/6419-minimax-optimal-alternating-minimization-for-kernel-nonparametric-tensor-learning |
http://papers.nips.cc/paper/6419-minimax-optimal-alternating-minimization-for-kernel-nonparametric-tensor-learning.pdf | |
PWC | https://paperswithcode.com/paper/minimax-optimal-alternating-minimization-for |
Repo | |
Framework | |
Integrating Optical Character Recognition and Machine Translation of Historical Documents
Title | Integrating Optical Character Recognition and Machine Translation of Historical Documents |
Authors | Haithem Afli, Andy Way |
Abstract | Machine Translation (MT) plays a critical role in expanding capacity in the translation industry. However, many valuable documents, including digital documents, are encoded in non-accessible formats for machine processing (e.g., Historical or Legal documents). Such documents must be passed through a process of Optical Character Recognition (OCR) to render the text suitable for MT. No matter how good the OCR is, this process introduces recognition errors, which often renders MT ineffective. In this paper, we propose a new OCR to MT framework based on adding a new OCR error correction module to enhance the overall quality of translation. Experimentation shows that our new system correction based on the combination of Language Modeling and Translation methods outperforms the baseline system by nearly 30{%} relative improvement. |
Tasks | Language Modelling, Machine Translation, Optical Character Recognition |
Published | 2016-12-01 |
URL | https://www.aclweb.org/anthology/W16-4015/ |
https://www.aclweb.org/anthology/W16-4015 | |
PWC | https://paperswithcode.com/paper/integrating-optical-character-recognition-and |
Repo | |
Framework | |
POS-tagging of Historical Dutch
Title | POS-tagging of Historical Dutch |
Authors | Dieuwke Hupkes, Rens Bod |
Abstract | We present a study of the adequacy of current methods that are used for POS-tagging historical Dutch texts, as well as an exploration of the influence of employing different techniques to improve upon the current practice. The main focus of this paper is on (unsupervised) methods that are easily adaptable for different domains without requiring extensive manual input. It was found that modernising the spelling of corpora prior to tagging them with a tagger trained on contemporary Dutch results in a large increase in accuracy, but that spelling normalisation alone is not sufficient to obtain state-of-the-art results. The best results were achieved by training a POS-tagger on a corpus automatically annotated by projecting (automatically assigned) POS-tags via word alignments from a contemporary corpus. This result is promising, as it was reached without including any domain knowledge or context dependencies. We argue that the insights of this study combined with semi-supervised learning techniques for domain adaptation can be used to develop a general-purpose diachronic tagger for Dutch. |
Tasks | Domain Adaptation |
Published | 2016-05-01 |
URL | https://www.aclweb.org/anthology/L16-1012/ |
https://www.aclweb.org/anthology/L16-1012 | |
PWC | https://paperswithcode.com/paper/pos-tagging-of-historical-dutch |
Repo | |
Framework | |
Inferring Methodological Meta-knowledge from Large Biomedical Corpora
Title | Inferring Methodological Meta-knowledge from Large Biomedical Corpora |
Authors | Goran Nenadic |
Abstract | |
Tasks | Temporal Information Extraction |
Published | 2016-10-01 |
URL | https://www.aclweb.org/anthology/Y16-1002/ |
https://www.aclweb.org/anthology/Y16-1002 | |
PWC | https://paperswithcode.com/paper/inferring-methodological-meta-knowledge-from |
Repo | |
Framework | |