October 16, 2019

1362 words 7 mins read

Paper Group NANR 18

Paper Group NANR 18

Using relative entropy for detection and analysis of periods of diachronic linguistic change. English-Basque Statistical and Neural Machine Translation. A corpus of German political speeches from the 21st century. Automatic Enrichment of Terminological Resources: the IATE RDF Example. A Comparative Study of Extremely Low-Resource Transliteration of …

Using relative entropy for detection and analysis of periods of diachronic linguistic change

Title Using relative entropy for detection and analysis of periods of diachronic linguistic change
Authors Stefania Degaetano-Ortlieb, Elke Teich
Abstract We present a data-driven approach to detect periods of linguistic change and the lexical and grammatical features contributing to change. We focus on the development of scientific English in the late modern period. Our approach is based on relative entropy (Kullback-Leibler Divergence) comparing temporally adjacent periods and sliding over the time line from past to present. Using a diachronic corpus of scientific publications of the Royal Society of London, we show how periods of change reflect the interplay between lexis and grammar, where periods of lexical expansion are typically followed by periods of grammatical consolidation resulting in a balance between expressivity and communicative efficiency. Our method is generic and can be applied to other data sets, languages and time ranges.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4503/
PDF https://www.aclweb.org/anthology/W18-4503
PWC https://paperswithcode.com/paper/using-relative-entropy-for-detection-and
Repo
Framework

English-Basque Statistical and Neural Machine Translation

Title English-Basque Statistical and Neural Machine Translation
Authors Inigo Jauregi Unanue, Lierni Garmendia Arratibel, Ehsan Zare Borzeshi, Massimo Piccardi
Abstract
Tasks Machine Translation, Named Entity Recognition, Natural Language Inference, Transfer Learning
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1141/
PDF https://www.aclweb.org/anthology/L18-1141
PWC https://paperswithcode.com/paper/english-basque-statistical-and-neural-machine
Repo
Framework

A corpus of German political speeches from the 21st century

Title A corpus of German political speeches from the 21st century
Authors Adrien Barbaresi
Abstract
Tasks Keyword Extraction, Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1127/
PDF https://www.aclweb.org/anthology/L18-1127
PWC https://paperswithcode.com/paper/a-corpus-of-german-political-speeches-from
Repo
Framework

Automatic Enrichment of Terminological Resources: the IATE RDF Example

Title Automatic Enrichment of Terminological Resources: the IATE RDF Example
Authors Mihael Arcan, Elena Montiel-Ponsoda, John P. McCrae, Paul Buitelaar
Abstract
Tasks Machine Translation, Word Sense Disambiguation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1149/
PDF https://www.aclweb.org/anthology/L18-1149
PWC https://paperswithcode.com/paper/automatic-enrichment-of-terminological
Repo
Framework

A Comparative Study of Extremely Low-Resource Transliteration of the World’s Languages

Title A Comparative Study of Extremely Low-Resource Transliteration of the World’s Languages
Authors Winston Wu, David Yarowsky
Abstract
Tasks Machine Translation, Speech Recognition, Transliteration
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1150/
PDF https://www.aclweb.org/anthology/L18-1150
PWC https://paperswithcode.com/paper/a-comparative-study-of-extremely-low-resource
Repo
Framework

All-words Word Sense Disambiguation Using Concept Embeddings

Title All-words Word Sense Disambiguation Using Concept Embeddings
Authors Rui Suzuki, Kanako Komiya, Masayuki Asahara, Minoru Sasaki, Hiroyuki Shinnou
Abstract
Tasks Word Embeddings, Word Sense Disambiguation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1162/
PDF https://www.aclweb.org/anthology/L18-1162
PWC https://paperswithcode.com/paper/all-words-word-sense-disambiguation-using
Repo
Framework

Persian Discourse Treebank and coreference corpus

Title Persian Discourse Treebank and coreference corpus
Authors Azadeh Mirzaei, Pegah Safari
Abstract
Tasks Coreference Resolution, Semantic Role Labeling
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1638/
PDF https://www.aclweb.org/anthology/L18-1638
PWC https://paperswithcode.com/paper/persian-discourse-treebank-and-coreference
Repo
Framework

Spline Error Weighting for Robust Visual-Inertial Fusion

Title Spline Error Weighting for Robust Visual-Inertial Fusion
Authors Hannes Ovrén, Per-Erik Forssén
Abstract In this paper we derive and test a probability-based weighting that can balance residuals of different types in spline fitting. In contrast to previous formulations, the proposed spline error weighting scheme also incorporates a prediction of the approximation error of the spline fit. We demonstrate the effectiveness of the prediction in a synthetic experiment, and apply it to visual-inertial fusion on rolling shutter cameras. This results in a method that can estimate 3D structure with metric scale on generic first-person videos. We also propose a quality measure for spline fitting, that can be used to automatically select the knot spacing. Experiments verify that the obtained trajectory quality corresponds well with the requested quality. Finally, by linearly scaling the weights, we show that the proposed spline error weighting minimizes the estimation errors on real sequences, in terms of scale and end-point errors.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Ovren_Spline_Error_Weighting_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Ovren_Spline_Error_Weighting_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/spline-error-weighting-for-robust-visual
Repo
Framework

Parser combinators for Tigrinya and Oromo morphology

Title Parser combinators for Tigrinya and Oromo morphology
Authors Patrick Littell, Tom McCoy, Na-Rae Han, Shruti Rijhwani, Zaid Sheikh, David Mortensen, Teruko Mitamura, Lori Levin
Abstract
Tasks Lemmatization, Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1611/
PDF https://www.aclweb.org/anthology/L18-1611
PWC https://paperswithcode.com/paper/parser-combinators-for-tigrinya-and-oromo
Repo
Framework

Using a Corpus of English and Chinese Political Speeches for Metaphor Analysis

Title Using a Corpus of English and Chinese Political Speeches for Metaphor Analysis
Authors Kathleen Ahrens, Huiheng Zeng, Shun-han Rebekah Wong
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1160/
PDF https://www.aclweb.org/anthology/L18-1160
PWC https://paperswithcode.com/paper/using-a-corpus-of-english-and-chinese
Repo
Framework

Interpersonal Relationship Labels for the CALLHOME Corpus

Title Interpersonal Relationship Labels for the CALLHOME Corpus
Authors Denys Katerenchuk, David Guy Brizan, Andrew Rosenberg
Abstract
Tasks Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1592/
PDF https://www.aclweb.org/anthology/L18-1592
PWC https://paperswithcode.com/paper/interpersonal-relationship-labels-for-the
Repo
Framework

Semantic Linking in Convolutional Neural Networks for Answer Sentence Selection

Title Semantic Linking in Convolutional Neural Networks for Answer Sentence Selection
Authors Massimo Nicosia, Aless Moschitti, ro
Abstract State-of-the-art networks that model relations between two pieces of text often use complex architectures and attention. In this paper, instead of focusing on architecture engineering, we take advantage of small amounts of labelled data that model semantic phenomena in text to encode matching features directly in the word representations. This greatly boosts the accuracy of our reference network, while keeping the model simple and fast to train. Our approach also beats a tree kernel model that uses similar input encodings, and neural models which use advanced attention and compare-aggregate mechanisms.
Tasks Feature Engineering, Question Answering
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1133/
PDF https://www.aclweb.org/anthology/D18-1133
PWC https://paperswithcode.com/paper/semantic-linking-in-convolutional-neural
Repo
Framework

WikiArt Emotions: An Annotated Dataset of Emotions Evoked by Art

Title WikiArt Emotions: An Annotated Dataset of Emotions Evoked by Art
Authors Saif Mohammad, Svetlana Kiritchenko
Abstract
Tasks Emotion Recognition, Image Generation, Image Retrieval
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1197/
PDF https://www.aclweb.org/anthology/L18-1197
PWC https://paperswithcode.com/paper/wikiart-emotions-an-annotated-dataset-of
Repo
Framework

Cross-Modal Hamming Hashing

Title Cross-Modal Hamming Hashing
Authors Yue Cao , Bin Liu, Mingsheng Long, Jianmin Wang
Abstract Cross-modal hashing enables similarity retrieval across different content modalities, such as searching relevant images in response to text queries. It provides with the advantages of computation efficiency and retrieval quality for multimedia retrieval. Hamming space retrieval enables efficient constant-time search that returns data items within a given Hamming radius to each query, by hash lookups instead of linear scan. However, Hamming space retrieval is ineffective in existing cross-modal hashing methods, subject to their weak capability of concentrating the relevant items to be within a small Hamming ball, while worse still, the Hamming distances between hash codes from different modalities are inevitably large due to the large heterogeneity across different modalities. This work presents Cross-Modal Hamming Hashing (CMHH), a novel deep cross-modal hashing approach that generates compact and highly concentrated hash codes to enable efficient and effective Hamming space retrieval. The main idea is to penalize significantly on similar cross-modal pairs with Hamming distance larger than the Hamming radius threshold, by designing a pairwise focal loss based on the exponential distribution. Extensive experiments demonstrate that CMHH can generate highly concentrated hash codes and achieve state-of-the-art cross-modal retrieval performance for both hash lookups and linear scan scenarios on three benchmark datasets, NUS-WIDE, MIRFlickr-25K, and IAPR TC-12.
Tasks Cross-Modal Retrieval
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Yue_Cao_Cross-Modal_Hamming_Hashing_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Yue_Cao_Cross-Modal_Hamming_Hashing_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/cross-modal-hamming-hashing
Repo
Framework

What’s This Movie About? A Joint Neural Network Architecture for Movie Content Analysis

Title What’s This Movie About? A Joint Neural Network Architecture for Movie Content Analysis
Authors Philip John Gorinski, Mirella Lapata
Abstract This work takes a first step toward movie content analysis by tackling the novel task of movie overview generation. Overviews are natural language texts that give a first impression of a movie, describing aspects such as its genre, plot, mood, or artistic style. We create a dataset that consists of movie scripts, attribute-value pairs for the movies{'} aspects, as well as overviews, which we extract from an online database. We present a novel end-to-end model for overview generation, consisting of a multi-label encoder for identifying screenplay attributes, and an LSTM decoder to generate natural language sentences conditioned on the identified attributes. Automatic and human evaluation show that the encoder is able to reliably assign good labels for the movie{'}s attributes, and the overviews provide descriptions of the movie{'}s content which are informative and faithful.
Tasks Decision Making
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1160/
PDF https://www.aclweb.org/anthology/N18-1160
PWC https://paperswithcode.com/paper/whatas-this-movie-about-a-joint-neural
Repo
Framework
comments powered by Disqus