October 16, 2019

1334 words 7 mins read

Paper Group NANR 32

Paper Group NANR 32

Creating Lithuanian and Latvian Speech Corpora from Inaccurately Annotated Web Data. Automating Bayesian optimization with Bayesian optimization. High-Order Tensor Regularization With Application to Attribute Ranking. Integrating Question Classification and Deep Learning for improved Answer Selection. An Unsupervised System for Parallel Corpus Filt …

Creating Lithuanian and Latvian Speech Corpora from Inaccurately Annotated Web Data

Title Creating Lithuanian and Latvian Speech Corpora from Inaccurately Annotated Web Data
Authors Askars Salimbajevs
Abstract
Tasks Language Modelling, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1454/
PDF https://www.aclweb.org/anthology/L18-1454
PWC https://paperswithcode.com/paper/creating-lithuanian-and-latvian-speech
Repo
Framework

Automating Bayesian optimization with Bayesian optimization

Title Automating Bayesian optimization with Bayesian optimization
Authors Gustavo Malkomes, Roman Garnett
Abstract Bayesian optimization is a powerful tool for global optimization of expensive functions. One of its key components is the underlying probabilistic model used for the objective function f. In practice, however, it is often unclear how one should appropriately choose a model, especially when gathering data is expensive. In this work, we introduce a novel automated Bayesian optimization approach that dynamically selects promising models for explaining the observed data using Bayesian Optimization in the model space. Crucially, we account for the uncertainty in the choice of model; our method is capable of using multiple models to represent its current belief about f and subsequently using this information for decision making. We argue, and demonstrate empirically, that our approach automatically finds suitable models for the objective function, which ultimately results in more-efficient optimization.
Tasks Decision Making
Published 2018-12-01
URL http://papers.nips.cc/paper/7838-automating-bayesian-optimization-with-bayesian-optimization
PDF http://papers.nips.cc/paper/7838-automating-bayesian-optimization-with-bayesian-optimization.pdf
PWC https://paperswithcode.com/paper/automating-bayesian-optimization-with
Repo
Framework

High-Order Tensor Regularization With Application to Attribute Ranking

Title High-Order Tensor Regularization With Application to Attribute Ranking
Authors Kwang In Kim, Juhyun Park, James Tompkin
Abstract When learning functions on manifolds, we can improve performance by regularizing with respect to the intrinsic manifold geometry rather than the ambient space. However, when regularizing tensor learning, calculating the derivatives along this intrinsic geometry is not possible, and so existing approaches are limited to regularizing in Euclidean space. Our new method for intrinsically regularizing and learning tensors on Riemannian manifolds introduces a surrogate object to encapsulate the geometric characteristic of the tensor. Regularizing this instead allows us to learn non-symmetric and high-order tensors. We apply our approach to the relative attributes problem, and we demonstrate that explicitly regularizing high-order relationships between pairs of data points improves performance.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Kim_High-Order_Tensor_Regularization_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Kim_High-Order_Tensor_Regularization_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/high-order-tensor-regularization-with
Repo
Framework

Integrating Question Classification and Deep Learning for improved Answer Selection

Title Integrating Question Classification and Deep Learning for improved Answer Selection
Authors Harish Tayyar Madabushi, Mark Lee, John Barnden
Abstract We present a system for Answer Selection that integrates fine-grained Question Classification with a Deep Learning model designed for Answer Selection. We detail the necessary changes to the Question Classification taxonomy and system, the creation of a new Entity Identification system and methods of highlighting entities to achieve this objective. Our experiments show that Question Classes are a strong signal to Deep Learning models for Answer Selection, and enable us to outperform the current state of the art in all variations of our experiments except one. In the best configuration, our MRR and MAP scores outperform the current state of the art by between 3 and 5 points on both versions of the TREC Answer Selection test set, a standard dataset for this task.
Tasks Answer Selection, Question Answering
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1278/
PDF https://www.aclweb.org/anthology/C18-1278
PWC https://paperswithcode.com/paper/integrating-question-classification-and-deep
Repo
Framework

An Unsupervised System for Parallel Corpus Filtering

Title An Unsupervised System for Parallel Corpus Filtering
Authors Viktor Hangya, Alex Fraser, er
Abstract In this paper we describe LMU Munich{'}s submission for the \textit{WMT 2018 Parallel Corpus Filtering} shared task which addresses the problem of cleaning noisy parallel corpora. The task of mining and cleaning parallel sentences is important for improving the quality of machine translation systems, especially for low-resource languages. We tackle this problem in a fully unsupervised fashion relying on bilingual word embeddings created without any bilingual signal. After pre-filtering noisy data we rank sentence pairs by calculating bilingual sentence-level similarities and then remove redundant data by employing monolingual similarity as well. Our unsupervised system achieved good performance during the official evaluation of the shared task, scoring only a few BLEU points behind the best systems, while not requiring any parallel training data.
Tasks Domain Adaptation, Language Modelling, Machine Translation, Sentence Embedding, Text Simplification, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6477/
PDF https://www.aclweb.org/anthology/W18-6477
PWC https://paperswithcode.com/paper/an-unsupervised-system-for-parallel-corpus
Repo
Framework

Weather Forecast Voice System

Title Weather Forecast Voice System
Authors Dinh Thanh Do
Abstract
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/O18-1013/
PDF https://www.aclweb.org/anthology/O18-1013
PWC https://paperswithcode.com/paper/weather-forecast-voice-system
Repo
Framework

Annotated Corpus of Scientific Conference’s Homepages for Information Extraction

Title Annotated Corpus of Scientific Conference’s Homepages for Information Extraction
Authors Piotr Andruszkiewicz, Rafa{\l} Hazan
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1587/
PDF https://www.aclweb.org/anthology/L18-1587
PWC https://paperswithcode.com/paper/annotated-corpus-of-scientific-conferences
Repo
Framework

Building a Constraint Grammar Parser for Plains Cree Verbs and Arguments

Title Building a Constraint Grammar Parser for Plains Cree Verbs and Arguments
Authors Katherine Schmirler, Antti Arppe, Trond Trosterud, Lene Antonsen
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1472/
PDF https://www.aclweb.org/anthology/L18-1472
PWC https://paperswithcode.com/paper/building-a-constraint-grammar-parser-for
Repo
Framework

QUEST: A Natural Language Interface to Relational Databases

Title QUEST: A Natural Language Interface to Relational Databases
Authors Vadim Sheinin, Elahe Khorashani, Hangu Yeo, Kun Xu, Ngoc Phuoc An Vo, Octavian Popescu
Abstract
Tasks Relation Extraction, Semantic Parsing
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1469/
PDF https://www.aclweb.org/anthology/L18-1469
PWC https://paperswithcode.com/paper/quest-a-natural-language-interface-to
Repo
Framework

Reference production in human-computer interaction: Issues for Corpus-based Referring Expression Generation

Title Reference production in human-computer interaction: Issues for Corpus-based Referring Expression Generation
Authors Danillo Rocha, Iv Paraboni, r{'e}
Abstract
Tasks Text Generation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1474/
PDF https://www.aclweb.org/anthology/L18-1474
PWC https://paperswithcode.com/paper/reference-production-in-human-computer
Repo
Framework

Definite Description Lexical Choice: taking Speaker’s Personality into account

Title Definite Description Lexical Choice: taking Speaker’s Personality into account
Authors Alex Lan, Iv Paraboni, r{'e}
Abstract
Tasks Text Generation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1475/
PDF https://www.aclweb.org/anthology/L18-1475
PWC https://paperswithcode.com/paper/definite-description-lexical-choice-taking
Repo
Framework

Modeling Temporality of Human Intentions by Domain Adaptation

Title Modeling Temporality of Human Intentions by Domain Adaptation
Authors Xiaolei Huang, Lixing Liu, Kate Carey, Joshua Woolley, Stefan Scherer, Brian Borsari
Abstract Categorizing patient{'}s intentions in conversational assessment can help decision making in clinical treatments. Many conversation corpora span broaden a series of time stages. However, it is not clear that how the themes shift in the conversation impact on the performance of human intention categorization (eg., patients might show different behaviors during the beginning versus the end). This paper proposes a method that models the temporal factor by using domain adaptation on clinical dialogue corpora, Motivational Interviewing (MI). We deploy Bi-LSTM and topic model jointly to learn language usage change across different time sessions. We conduct experiments on the MI corpora to show the promising improvement after considering temporality in the classification task.
Tasks Decision Making, Domain Adaptation, Intent Classification, Topic Models
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1074/
PDF https://www.aclweb.org/anthology/D18-1074
PWC https://paperswithcode.com/paper/modeling-temporality-of-human-intentions-by
Repo
Framework

Referring Expression Generation in time-constrained communication

Title Referring Expression Generation in time-constrained communication
Authors Andr{'e} Mariotti, Iv Paraboni, r{'e}
Abstract
Tasks Text Generation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1476/
PDF https://www.aclweb.org/anthology/L18-1476
PWC https://paperswithcode.com/paper/referring-expression-generation-in-time
Repo
Framework

Optimization for Approximate Submodularity

Title Optimization for Approximate Submodularity
Authors Yaron Singer, Avinatan Hassidim
Abstract We consider the problem of maximizing a submodular function when given access to its approximate version. Submodular functions are heavily studied in a wide variety of disciplines, since they are used to model many real world phenomena, and are amenable to optimization. However, there are many cases in which the phenomena we observe is only approximately submodular and the approximation guarantees cease to hold. We describe a technique which we call the sampled mean approximation that yields strong guarantees for maximization of submodular functions from approximate surrogates under cardinality and intersection of matroid constraints. In particular, we show tight guarantees for maximization under a cardinality constraint and 1/(1+P) approximation under intersection of P matroids.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7322-optimization-for-approximate-submodularity
PDF http://papers.nips.cc/paper/7322-optimization-for-approximate-submodularity.pdf
PWC https://paperswithcode.com/paper/optimization-for-approximate-submodularity
Repo
Framework

Universal Dependencies for Amharic

Title Universal Dependencies for Amharic
Authors Binyam Ephrem Seyoum, Yusuke Miyao, Baye Yimam Mekonnen
Abstract
Tasks Machine Translation, Question Answering
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1350/
PDF https://www.aclweb.org/anthology/L18-1350
PWC https://paperswithcode.com/paper/universal-dependencies-for-amharic
Repo
Framework
comments powered by Disqus