October 15, 2019

2084 words 10 mins read

Paper Group NANR 154

Paper Group NANR 154

Dysarthric speech evaluation: automatic and perceptual approaches. Sub-label dependencies for Neural Morphological Tagging – The Joint Submission of University of Colorado and University of Helsinki for VarDial 2018. Normalizing Early English Letters to Present-day English Spelling. A database of German definitory contexts from selected web source …

Dysarthric speech evaluation: automatic and perceptual approaches

Title Dysarthric speech evaluation: automatic and perceptual approaches
Authors Imed Laaridh, Christine Meunier, Corinne Fredouille
Abstract
Tasks Anomaly Detection
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1314/
PDF https://www.aclweb.org/anthology/L18-1314
PWC https://paperswithcode.com/paper/dysarthric-speech-evaluation-automatic-and
Repo
Framework

Sub-label dependencies for Neural Morphological Tagging – The Joint Submission of University of Colorado and University of Helsinki for VarDial 2018

Title Sub-label dependencies for Neural Morphological Tagging – The Joint Submission of University of Colorado and University of Helsinki for VarDial 2018
Authors Miikka Silfverberg, Senka Drobac
Abstract This paper presents the submission of the UH{&}CU team (Joint University of Colorado and University of Helsinki team) for the VarDial 2018 shared task on morphosyntactic tagging of Croatian, Slovenian and Serbian tweets. Our system is a bidirectional LSTM tagger which emits tags as character sequences using an LSTM generator in order to be able to handle unknown tags and combinations of several tags for one token which occur in the shared task data sets. To the best of our knowledge, using an LSTM generator is a novel approach. The system delivers sizable improvements of more than 6{%}-points over a baseline trigram tagger. Overall, the performance of our system is quite even for all three languages.
Tasks Morphological Tagging, Word Embeddings
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-3904/
PDF https://www.aclweb.org/anthology/W18-3904
PWC https://paperswithcode.com/paper/sub-label-dependencies-for-neural
Repo
Framework

Normalizing Early English Letters to Present-day English Spelling

Title Normalizing Early English Letters to Present-day English Spelling
Authors Mika H{"a}m{"a}l{"a}inen, Tanja S{"a}ily, Jack Rueter, J{"o}rg Tiedemann, Eetu M{"a}kel{"a}
Abstract This paper presents multiple methods for normalizing the most deviant and infrequent historical spellings in a corpus consisting of personal correspondence from the 15th to the 19th century. The methods include machine translation (neural and statistical), edit distance and rule-based FST. Different normalization methods are compared and evaluated. All of the methods have their own strengths in word normalization. This calls for finding ways of combining the results from these methods to leverage their individual strengths.
Tasks Machine Translation
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4510/
PDF https://www.aclweb.org/anthology/W18-4510
PWC https://paperswithcode.com/paper/normalizing-early-english-letters-to-present
Repo
Framework

A database of German definitory contexts from selected web sources

Title A database of German definitory contexts from selected web sources
Authors Adrien Barbaresi, Lothar Lemnitzer, Alex Geyken, er
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1485/
PDF https://www.aclweb.org/anthology/L18-1485
PWC https://paperswithcode.com/paper/a-database-of-german-definitory-contexts-from
Repo
Framework

Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with \beta-Divergences

Title Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with \beta-Divergences
Authors Jeremias Knoblauch, Jack E. Jewson, Theodoros Damoulas
Abstract We present the very first robust Bayesian Online Changepoint Detection algorithm through General Bayesian Inference (GBI) with $\beta$-divergences. The resulting inference procedure is doubly robust for both the predictive and the changepoint (CP) posterior, with linear time and constant space complexity. We provide a construction for exponential models and demonstrate it on the Bayesian Linear Regression model. In so doing, we make two additional contributions: Firstly, we make GBI scalable using Structural Variational approximations that are exact as $\beta \to 0$. Secondly, we give a principled way of choosing the divergence parameter $\beta$ by minimizing expected predictive loss on-line. Reducing False Discovery Rates of \CPs from up to 99% to 0% on real world data, this offers the state of the art.
Tasks Bayesian Inference
Published 2018-12-01
URL http://papers.nips.cc/paper/7292-doubly-robust-bayesian-inference-for-non-stationary-streaming-data-with-beta-divergences
PDF http://papers.nips.cc/paper/7292-doubly-robust-bayesian-inference-for-non-stationary-streaming-data-with-beta-divergences.pdf
PWC https://paperswithcode.com/paper/doubly-robust-bayesian-inference-for-non
Repo
Framework

Induction of a Large-Scale Knowledge Graph from the Regesta Imperii

Title Induction of a Large-Scale Knowledge Graph from the Regesta Imperii
Authors Juri Opitz, Leo Born, Vivi Nastase
Abstract We induce and visualize a Knowledge Graph over the Regesta Imperii (RI), an important large-scale resource for medieval history research. The RI comprise more than 150,000 digitized abstracts of medieval charters issued by the Roman-German kings and popes distributed over many European locations and a time span of more than 700 years. Our goal is to provide a resource for historians to visualize and query the RI, possibly aiding medieval history research. The resulting medieval graph and visualization tools are shared publicly.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4518/
PDF https://www.aclweb.org/anthology/W18-4518
PWC https://paperswithcode.com/paper/induction-of-a-large-scale-knowledge-graph
Repo
Framework

Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization

Title Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization
Authors Xiaoxuan Zhang, Mingrui Liu, Xun Zhou, Tianbao Yang
Abstract In this paper, we consider online F-measure optimization (OFO). Unlike traditional performance metrics (e.g., classification error rate), F-measure is non-decomposable over training examples and is a non-convex function of model parameters, making it much more difficult to be optimized in an online fashion. Most existing results of OFO usually suffer from high memory/computational costs and/or lack statistical consistency guarantee for optimizing F-measure at the population level. To advance OFO, we propose an efficient online algorithm based on simultaneously learning a posterior probability of class and learning an optimal threshold by minimizing a stochastic strongly convex function with unknown strong convexity parameter. A key component of the proposed method is a novel stochastic algorithm with low memory and computational costs, which can enjoy a convergence rate of $\widetilde O(1/\sqrt{n})$ for learning the optimal threshold under a mild condition on the convergence of the posterior probability, where $n$ is the number of processed examples. It is provably faster than its predecessor based on a heuristic for updating the threshold. The experiments verify the efficiency of the proposed algorithm in comparison with state-of-the-art OFO algorithms.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7645-faster-online-learning-of-optimal-threshold-for-consistent-f-measure-optimization
PDF http://papers.nips.cc/paper/7645-faster-online-learning-of-optimal-threshold-for-consistent-f-measure-optimization.pdf
PWC https://paperswithcode.com/paper/faster-online-learning-of-optimal-threshold
Repo
Framework

Impact of p-GaN Gate Length on Performance of AlGaN/GaN Normally-off HEMT Devices

Title Impact of p-GaN Gate Length on Performance of AlGaN/GaN Normally-off HEMT Devices
Authors Sanjit Kumar Swain, Sudhansu Mohan Biswal, Umakanta Nanda, D. Siva Patro, Suraj Kumar Nayak and Birendra Biswal
Abstract In this work, we have studied the effect of variation in length of GaN gate with p-type doping concentration on the DC performances of AlGaN/GaN normallyoff HEMT using 2D Atlas TCAD simulator. A comprehensive simulation is undertaken on the proposed device to examine different performance parameters such as drain current, transconductance factor, energy band diagram, and surface potential with respect to change in p-type GaN gate lengths. The gate lengths are varied from 60 to 90 nm, and it is noticed from the simulation results that with a decrease in gate length the drain current increases and transconductance increases. A proper optimization of gate length is indispensable to preserve the normally-off mode operation and at the same time enhancing certain performance parameters.
Tasks
Published 2018-03-31
URL https://www.researchgate.net/publication/328724289_Impact_of_p-GaN_Gate_Length_on_Performance_of_AlGaNGaN_Normally-off_HEMT_Devices_Proceedings_of_the_Fourth_ICMEET_2018
PDF https://www.researchgate.net/publication/328724289_Impact_of_p-GaN_Gate_Length_on_Performance_of_AlGaNGaN_Normally-off_HEMT_Devices_Proceedings_of_the_Fourth_ICMEET_2018
PWC https://paperswithcode.com/paper/impact-of-p-gan-gate-length-on-performance-of
Repo
Framework

Computational Complexity of Natural Languages: A Reasoned Overview

Title Computational Complexity of Natural Languages: A Reasoned Overview
Authors Ant{'o}nio Branco
Abstract There has been an upsurge of research interest in natural language complexity. As this interest will benefit from being informed by established contributions in this area, this paper presents a reasoned overview of central results concerning the computational complexity of natural language parsing. This overview also seeks to help to understand why, contrary to recent and widespread assumptions, it is by no means sufficient that an agent handles sequences of items under a pattern $a^n b^n$ or under a pattern $a^n b^m c^n d^m$ to ascertain ipso facto that this is the result of at least an underlying context-free grammar or an underlying context-sensitive grammar, respectively. In addition, it seeks to help to understand why it is also not sufficient that an agent handles sequences of items under a pattern $a^n b^n$ for it to be deemed as having a cognitive capacity of higher computational complexity.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4602/
PDF https://www.aclweb.org/anthology/W18-4602
PWC https://paperswithcode.com/paper/computational-complexity-of-natural-languages
Repo
Framework

Breaking the Span Assumption Yields Fast Finite-Sum Minimization

Title Breaking the Span Assumption Yields Fast Finite-Sum Minimization
Authors Robert Hannah, Yanli Liu, Daniel O’Connor, Wotao Yin
Abstract In this paper, we show that SVRG and SARAH can be modified to be fundamentally faster than all of the other standard algorithms that minimize the sum of $n$ smooth functions, such as SAGA, SAG, SDCA, and SDCA without duality. Most finite sum algorithms follow what we call the ``span assumption’': Their updates are in the span of a sequence of component gradients chosen in a random IID fashion. In the big data regime, where the condition number $\kappa=O(n)$, the span assumption prevents algorithms from converging to an approximate solution of accuracy $\epsilon$ in less than $n\ln(1/\epsilon)$ iterations. SVRG and SARAH do not follow the span assumption since they are updated with a hybrid of full-gradient and component-gradient information. We show that because of this, they can be up to $\Omega(1+(\ln(n/\kappa))_+)$ times faster. In particular, to obtain an accuracy $\epsilon = 1/n^\alpha$ for $\kappa=n^\beta$ and $\alpha,\beta\in(0,1)$, modified SVRG requires $O(n)$ iterations, whereas algorithms that follow the span assumption require $O(n\ln(n))$ iterations. Moreover, we present lower bound results that show this speedup is optimal, and provide analysis to help explain why this speedup exists. With the understanding that the span assumption is a point of weakness of finite sum algorithms, future work may purposefully exploit this to yield faster algorithms in the big data regime. |
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7499-breaking-the-span-assumption-yields-fast-finite-sum-minimization
PDF http://papers.nips.cc/paper/7499-breaking-the-span-assumption-yields-fast-finite-sum-minimization.pdf
PWC https://paperswithcode.com/paper/breaking-the-span-assumption-yields-fast
Repo
Framework

PD3: Better Low-Resource Cross-Lingual Transfer By Combining Direct Transfer and Annotation Projection

Title PD3: Better Low-Resource Cross-Lingual Transfer By Combining Direct Transfer and Annotation Projection
Authors Steffen Eger, Andreas R{"u}ckl{'e}, Iryna Gurevych
Abstract We consider unsupervised cross-lingual transfer on two tasks, viz., sentence-level argumentation mining and standard POS tagging. We combine direct transfer using bilingual embeddings with annotation projection, which projects labels across unlabeled parallel data. We do so by either merging respective source and target language datasets or alternatively by using multi-task learning. Our combination strategy considerably improves upon both direct transfer and projection with few available parallel sentences, the most realistic scenario for many low-resource target languages.
Tasks Argument Mining, Cross-Lingual Transfer, Multi-Task Learning, Word Alignment
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5216/
PDF https://www.aclweb.org/anthology/W18-5216
PWC https://paperswithcode.com/paper/pd3-better-low-resource-cross-lingual
Repo
Framework

Cross-Lingual Argumentative Relation Identification: from English to Portuguese

Title Cross-Lingual Argumentative Relation Identification: from English to Portuguese
Authors Gil Rocha, Christian Stab, Henrique Lopes Cardoso, Iryna Gurevych
Abstract Argument mining aims to detect and identify argument structures from textual resources. In this paper, we aim to address the task of argumentative relation identification, a subtask of argument mining, for which several approaches have been recently proposed in a monolingual setting. To overcome the lack of annotated resources in less-resourced languages, we present the first attempt to address this subtask in a cross-lingual setting. We compare two standard strategies for cross-language learning, namely: projection and direct-transfer. Experimental results show that by using unsupervised language adaptation the proposed approaches perform at a competitive level when compared with fully-supervised in-language learning settings.
Tasks Argument Mining, Transfer Learning
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5217/
PDF https://www.aclweb.org/anthology/W18-5217
PWC https://paperswithcode.com/paper/cross-lingual-argumentative-relation
Repo
Framework

More or less controlled elicitation of argumentative text: Enlarging a microtext corpus via crowdsourcing

Title More or less controlled elicitation of argumentative text: Enlarging a microtext corpus via crowdsourcing
Authors Maria Skeppstedt, Andreas Peldszus, Manfred Stede
Abstract We present an extension of an annotated corpus of short argumentative texts that had originally been built in a controlled text production experiment. Our extension more than doubles the size of the corpus by means of crowdsourcing. We report on the setup of this experiment and on the consequences that crowdsourcing had for assembling the data, and in particular for annotation. We labeled the argumentative structure by marking claims, premises, and relations between them, following the scheme used in the original corpus, but had to make a few modifications in response to interesting phenomena in the data. Finally, we report on an experiment with the automatic prediction of this argumentation structure: We first replicated the approach of an earlier study on the original corpus, and compare the performance to various settings involving the extension.
Tasks Argument Mining
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5218/
PDF https://www.aclweb.org/anthology/W18-5218
PWC https://paperswithcode.com/paper/more-or-less-controlled-elicitation-of
Repo
Framework

ZAP: An Open-Source Multilingual Annotation Projection Framework

Title ZAP: An Open-Source Multilingual Annotation Projection Framework
Authors Alan Akbik, Rol Vollgraf,
Abstract
Tasks Word Alignment
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1344/
PDF https://www.aclweb.org/anthology/L18-1344
PWC https://paperswithcode.com/paper/zap-an-open-source-multilingual-annotation
Repo
Framework

A Multi-layer Annotated Corpus of Argumentative Text: From Argument Schemes to Discourse Relations

Title A Multi-layer Annotated Corpus of Argumentative Text: From Argument Schemes to Discourse Relations
Authors Elena Musi, Manfred Stede, Leonard Kriese, Smar Muresan, a, Andrea Rocci
Abstract
Tasks Text Generation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1258/
PDF https://www.aclweb.org/anthology/L18-1258
PWC https://paperswithcode.com/paper/a-multi-layer-annotated-corpus-of
Repo
Framework
comments powered by Disqus