October 16, 2019

1481 words 7 mins read

Paper Group NANR 27

Paper Group NANR 27

Visualizing the ``Dictionary of Regionalisms of France’’ (DRF). BrainT at IEST 2018: Fine-tuning Multiclass Perceptron For Implicit Emotion Classification. Evaluation of Dictionary Creating Methods for Finno-Ugric Minority Languages. Sentence and Clause Level Emotion Annotation, Detection, and Classification in a Multi-Genre Corpus. An Annotation L …

Visualizing the ``Dictionary of Regionalisms of France’’ (DRF)

Title Visualizing the ``Dictionary of Regionalisms of France’’ (DRF) |
Authors Ada Wan
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1578/
PDF https://www.aclweb.org/anthology/L18-1578
PWC https://paperswithcode.com/paper/visualizing-the-dictionary-of-regionalisms-of
Repo
Framework

BrainT at IEST 2018: Fine-tuning Multiclass Perceptron For Implicit Emotion Classification

Title BrainT at IEST 2018: Fine-tuning Multiclass Perceptron For Implicit Emotion Classification
Authors Vachagan Gratian, Marina Haid
Abstract We present \textit{BrainT}, a multi-class, averaged perceptron tested on implicit emotion prediction of tweets. We show that the dataset is linearly separable and explore ways in fine-tuning the baseline classifier. Our results indicate that the bag-of-words features benefit the model moderately and prediction can be improved with bigrams, trigrams, \textit{skip-one}-tetragrams and POS-tags. Furthermore, we find preprocessing of the n-grams, including stemming, lowercasing, stopword filtering, emoji and emoticon conversion generally not useful. The model is trained on an annotated corpus of 153,383 tweets and predictions on the test data were submitted to the WASSA-2018 Implicit Emotion Shared Task. BrainT attained a Macro F-score of 0.63.
Tasks Emotion Classification, Emotion Recognition, Sentiment Analysis
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6235/
PDF https://www.aclweb.org/anthology/W18-6235
PWC https://paperswithcode.com/paper/braint-at-iest-2018-fine-tuning-multiclass
Repo
Framework

Evaluation of Dictionary Creating Methods for Finno-Ugric Minority Languages

Title Evaluation of Dictionary Creating Methods for Finno-Ugric Minority Languages
Authors Zsanett Ferenczi, Iv{'a}n Mittelholcz, Eszter Simon, Tam{'a}s V{'a}radi
Abstract
Tasks Word Embeddings
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1313/
PDF https://www.aclweb.org/anthology/L18-1313
PWC https://paperswithcode.com/paper/evaluation-of-dictionary-creating-methods-for
Repo
Framework

Sentence and Clause Level Emotion Annotation, Detection, and Classification in a Multi-Genre Corpus

Title Sentence and Clause Level Emotion Annotation, Detection, and Classification in a Multi-Genre Corpus
Authors Shabnam Tafreshi, Mona Diab
Abstract
Tasks Emotion Classification, Emotion Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1199/
PDF https://www.aclweb.org/anthology/L18-1199
PWC https://paperswithcode.com/paper/sentence-and-clause-level-emotion-annotation
Repo
Framework
Title An Annotation Language for Semantic Search of Legal Sources
Authors Adeline Nazarenko, Fran{\c{c}}ois Levy, Adam Wyner
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1177/
PDF https://www.aclweb.org/anthology/L18-1177
PWC https://paperswithcode.com/paper/an-annotation-language-for-semantic-search-of
Repo
Framework

GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition

Title GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition
Authors Yifan Feng, Zizhao Zhang, Xibin Zhao, Rongrong Ji, Yue Gao
Abstract 3D shape recognition has attracted much attention recently. Its recent advances advocate the usage of deep features and achieve the state-of-the-art performance. However, existing deep features for 3D shape recognition are restricted to a view-to-shape setting, which learns the shape descriptor from the view-level feature directly. Despite the exciting progress on view-based 3D shape description, the intrinsic hierarchical correlation and discriminability among views have not been well exploited, which is important for 3D shape representation. To tackle this issue, in this paper, we propose a group-view convolutional neural network (GVCNN) framework for hierarchical correlation modeling towards discriminative 3D shape description. The proposed GVCNN framework is composed of a hierarchical view-group-shape architecture, i.e., from the view level, the group level and the shape level, which are organized using a grouping strategy. Concretely, we first use an expanded CNN to extract a view level descriptor. Then, a grouping module is introduced to estimate the content discrimination of each view, based on which all views can be splitted into different groups according to their discriminative level. A group level description can be further generated by pooling from view descriptors. Finally, all group level descriptors are combined into the shape level descriptor according to their discriminative weights. Experimental results and comparison with state-of-the-art methods show that our proposed GVCNN method can achieve a significant performance gain on both the 3D shape classification and retrieval tasks.
Tasks 3D Shape Recognition, 3D Shape Representation
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Feng_GVCNN_Group-View_Convolutional_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Feng_GVCNN_Group-View_Convolutional_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/gvcnn-group-view-convolutional-neural
Repo
Framework

New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity

Title New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity
Authors Pan Zhou, Xiaotong Yuan, Jiashi Feng
Abstract As an incremental-gradient algorithm, the hybrid stochastic gradient descent (HSGD) enjoys merits of both stochastic and full gradient methods for finite-sum minimization problem. However, the existing rate-of-convergence analysis for HSGD is made under with-replacement sampling (WRS) and is restricted to convex problems. It is not clear whether HSGD still carries these advantages under the common practice of without-replacement sampling (WoRS) for non-convex problems. In this paper, we affirmatively answer this open question by showing that under WoRS and for both convex and non-convex problems, it is still possible for HSGD (with constant step-size) to match full gradient descent in rate of convergence, while maintaining comparable sample-size-independent incremental first-order oracle complexity to stochastic gradient descent. For a special class of finite-sum problems with linear prediction models, our convergence results can be further improved in some cases. Extensive numerical results confirm our theoretical affirmation and demonstrate the favorable efficiency of WoRS-based HSGD.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7399-new-insight-into-hybrid-stochastic-gradient-descent-beyond-with-replacement-sampling-and-convexity
PDF http://papers.nips.cc/paper/7399-new-insight-into-hybrid-stochastic-gradient-descent-beyond-with-replacement-sampling-and-convexity.pdf
PWC https://paperswithcode.com/paper/new-insight-into-hybrid-stochastic-gradient
Repo
Framework

Aye' or No’? Speech-level Sentiment Analysis of Hansard UK Parliamentary Debate Transcripts

Title Aye' or No’? Speech-level Sentiment Analysis of Hansard UK Parliamentary Debate Transcripts
Authors Gavin Abercrombie, Riza Batista-Navarro
Abstract
Tasks Opinion Mining, Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1659/
PDF https://www.aclweb.org/anthology/L18-1659
PWC https://paperswithcode.com/paper/aye-or-no-speech-level-sentiment-analysis-of
Repo
Framework

Statistical NLG for Generating the Content and Form of Referring Expressions

Title Statistical NLG for Generating the Content and Form of Referring Expressions
Authors Xiao Li, Kees van Deemter, Chenghua Lin
Abstract This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.
Tasks Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6561/
PDF https://www.aclweb.org/anthology/W18-6561
PWC https://paperswithcode.com/paper/statistical-nlg-for-generating-the-content
Repo
Framework

Parallel Corpora in Mboshi (Bantu C25, Congo-Brazzaville)

Title Parallel Corpora in Mboshi (Bantu C25, Congo-Brazzaville)
Authors Annie Rialland, Martine Adda-Decker, Guy-Noël Kouarata, Gilles Adda, Laurent Besacier, Lori Lamel, Elodie Gauthier, Pierre Godard, Jamison Cooper-Leavitt
Abstract
Tasks Machine Translation, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/papers/L18-1674/l18-1674
PDF https://www.aclweb.org/anthology/L18-1674
PWC https://paperswithcode.com/paper/parallel-corpora-in-mboshi-bantu-c25-congo
Repo
Framework

KU-CST at CoNLL–SIGMORPHON 2018 Shared Task: a Tridirectional Model

Title KU-CST at CoNLL–SIGMORPHON 2018 Shared Task: a Tridirectional Model
Authors Manex Agirrezabal
Abstract
Tasks Morphological Analysis, Morphological Inflection, Named Entity Recognition, Sentiment Analysis
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-3002/
PDF https://www.aclweb.org/anthology/K18-3002
PWC https://paperswithcode.com/paper/ku-cst-at-conllasigmorphon-2018-shared-task-a
Repo
Framework

DeModify: A Dataset for Analyzing Contextual Constraints on Modifier Deletion

Title DeModify: A Dataset for Analyzing Contextual Constraints on Modifier Deletion
Authors Vivi Nastase, Devon Fritz, Anette Frank
Abstract
Tasks Language Modelling, Natural Language Inference, Text Simplification
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1217/
PDF https://www.aclweb.org/anthology/L18-1217
PWC https://paperswithcode.com/paper/demodify-a-dataset-for-analyzing-contextual
Repo
Framework

Modelling Pro-drop with the Rational Speech Acts Model

Title Modelling Pro-drop with the Rational Speech Acts Model
Authors Guanyi Chen, Kees van Deemter, Chenghua Lin
Abstract We extend the classic Referring Expressions Generation task by considering zero pronouns in {``}pro-drop{''} languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model (Frank and Goodman, 2012). By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically. |
Tasks Coreference Resolution, Machine Translation, Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6519/
PDF https://www.aclweb.org/anthology/W18-6519
PWC https://paperswithcode.com/paper/modelling-pro-drop-with-the-rational-speech
Repo
Framework

Multimodal Differential Network for Visual Question Generation

Title Multimodal Differential Network for Visual Question Generation
Authors Badri Narayana Patro, S Kumar, eep, Vinod Kumar Kurmi, Vinay Namboodiri
Abstract Generating natural questions from an image is a semantic task that requires using visual and language modality to learn multimodal representations. Images can have multiple visual and language contexts that are relevant for generating questions namely places, captions, and tags. In this paper, we propose the use of exemplars for obtaining the relevant context. We obtain this by using a Multimodal Differential Network to produce natural and engaging questions. The generated questions show a remarkable similarity to the natural questions as validated by a human study. Further, we observe that the proposed approach substantially improves over state-of-the-art benchmarks on the quantitative metrics (BLEU, METEOR, ROUGE, and CIDEr).
Tasks Image Captioning, Object Classification, Question Answering, Question Generation, Visual Question Answering
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1434/
PDF https://www.aclweb.org/anthology/D18-1434
PWC https://paperswithcode.com/paper/multimodal-differential-network-for-visual-1
Repo
Framework
Title FrNewsLink : a corpus linking TV Broadcast News Segments and Press Articles
Authors Nathalie Camelin, G{'e}raldine Damnati, Abdessalam Bouchekif, L, Anais eau, Delphine Charlet, Yannick Est{`e}ve
Abstract
Tasks Question Similarity, Semantic Textual Similarity
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1329/
PDF https://www.aclweb.org/anthology/L18-1329
PWC https://paperswithcode.com/paper/frnewslink-a-corpus-linking-tv-broadcast-news
Repo
Framework
comments powered by Disqus