Paper Group NAWR 3
TweeTime : A Minimally Supervised Method for Recognizing and Normalizing Time Expressions in Twitter. Learning local feature descriptors with triplets and shallow convolutional neural networks. Optimizing Statistical Machine Translation for Text Simplification. Deep Neural Networks with Inexact Matching for Person Re-Identification. MeTA: A Unified …
TweeTime : A Minimally Supervised Method for Recognizing and Normalizing Time Expressions in Twitter
| Title | TweeTime : A Minimally Supervised Method for Recognizing and Normalizing Time Expressions in Twitter |
| Authors | Jeniya Tabassum, Alan Ritter, Wei Xu |
| Abstract | |
| Tasks | Information Retrieval, Knowledge Base Population |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1030/ |
| https://www.aclweb.org/anthology/D16-1030 | |
| PWC | https://paperswithcode.com/paper/tweetime-a-minimally-supervised-method-for-1 |
| Repo | https://github.com/jeniyat/TweeTime |
| Framework | none |
Learning local feature descriptors with triplets and shallow convolutional neural networks
| Title | Learning local feature descriptors with triplets and shallow convolutional neural networks |
| Authors | V. Balntas, E. Riba, D. Ponsa, and K. Mikolajczyk. |
| Abstract | It has recently been demonstrated that local feature descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance. Previous work on learning such descriptors has focused on exploiting pairs of positive and negative patches to learn discriminative CNN representations. In this work, we propose to utilize triplets of training samples, together with in-triplet mining of hard negatives. We show that our method achieves state of the art results, without the computational overhead typically associated with mining of negatives and with lower complexity of the network architecture. We compare our approach to recently introduced convolutional local feature descriptors, and demonstrate the advantages of the proposed methods in terms of performance and speed. We also examine different loss functions associated with triplets. |
| Tasks | |
| Published | 2016-09-01 |
| URL | http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf |
| http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf | |
| PWC | https://paperswithcode.com/paper/learning-local-feature-descriptors-with |
| Repo | https://github.com/vbalnt/tfeat |
| Framework | pytorch |
Optimizing Statistical Machine Translation for Text Simplification
| Title | Optimizing Statistical Machine Translation for Text Simplification |
| Authors | Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, Chris Callison-Burch |
| Abstract | Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods are limited by the quality and quantity of manually simplified corpora, which are expensive to build. In this paper, we conduct an in-depth adaptation of statistical machine translation to perform text simplification, taking advantage of large-scale paraphrases learned from bilingual texts and a small amount of manual simplifications with multiple references. Our work is the first to design automatic metrics that are effective for tuning and evaluating simplification systems, which will facilitate iterative development for this task. |
| Tasks | Machine Translation, Text Simplification |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1029/ |
| https://www.aclweb.org/anthology/Q16-1029 | |
| PWC | https://paperswithcode.com/paper/optimizing-statistical-machine-translation |
| Repo | https://github.com/cocoxu/simplification |
| Framework | none |
Deep Neural Networks with Inexact Matching for Person Re-Identification
| Title | Deep Neural Networks with Inexact Matching for Person Re-Identification |
| Authors | Arulkumar Subramaniam, Moitreya Chatterjee, Anurag Mittal |
| Abstract | Person Re-Identification is the task of matching images of a person across multiple camera views. Almost all prior approaches address this challenge by attempting to learn the possible transformations that relate the different views of a person from a training corpora. Then, they utilize these transformation patterns for matching a query image to those in a gallery image bank at test time. This necessitates learning good feature representations of the images and having a robust feature matching technique. Deep learning approaches, such as Convolutional Neural Networks (CNN), simultaneously do both and have shown great promise recently. In this work, we propose two CNN-based architectures for Person Re-Identification. In the first, given a pair of images, we extract feature maps from these images via multiple stages of convolution and pooling. A novel inexact matching technique then matches pixels in the first representation with those of the second. Furthermore, we search across a wider region in the second representation for matching. Our novel matching technique allows us to tackle the challenges posed by large viewpoint variations, illumination changes or partial occlusions. Our approach shows a promising performance and requires only about half the parameters as a current state-of-the-art technique. Nonetheless, it also suffers from false matches at times. In order to mitigate this issue, we propose a fused architecture that combines our inexact matching pipeline with a state-of-the-art exact matching technique. We observe substantial gains with the fused model over the current state-of-the-art on multiple challenging datasets of varying sizes, with gains of up to about 21%. |
| Tasks | Person Re-Identification |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6367-deep-neural-networks-with-inexact-matching-for-person-re-identification |
| http://papers.nips.cc/paper/6367-deep-neural-networks-with-inexact-matching-for-person-re-identification.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-networks-with-inexact-matching |
| Repo | https://github.com/InnovArul/personreid_normxcorr |
| Framework | torch |
MeTA: A Unified Toolkit for Text Retrieval and Analysis
| Title | MeTA: A Unified Toolkit for Text Retrieval and Analysis |
| Authors | Sean Massung, Chase Geigle, ChengXiang Zhai |
| Abstract | |
| Tasks | Document Classification, Information Retrieval, Tokenization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4016/ |
| https://www.aclweb.org/anthology/P16-4016 | |
| PWC | https://paperswithcode.com/paper/meta-a-unified-toolkit-for-text-retrieval-and |
| Repo | https://github.com/meta-toolkit/meta |
| Framework | none |
Neural Sentiment Classification with User and Product Attention
| Title | Neural Sentiment Classification with User and Product Attention |
| Authors | Huimin Chen, Maosong Sun, Cunchao Tu, Yankai Lin, Zhiyuan Liu |
| Abstract | |
| Tasks | Feature Engineering, Sentiment Analysis, Speech Recognition, Text Classification |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1171/ |
| https://www.aclweb.org/anthology/D16-1171 | |
| PWC | https://paperswithcode.com/paper/neural-sentiment-classification-with-user-and |
| Repo | https://github.com/thunlp/NSC |
| Framework | none |
FlexTag: A Highly Flexible PoS Tagging Framework
| Title | FlexTag: A Highly Flexible PoS Tagging Framework |
| Authors | Torsten Zesch, Tobias Horsmann |
| Abstract | We present FlexTag, a highly flexible PoS tagging framework. In contrast to monolithic implementations that can only be retrained but not adapted otherwise, FlexTag enables users to modify the feature space and the classification algorithm. Thus, FlexTag makes it easy to quickly develop custom-made taggers exactly fitting the research problem. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1675/ |
| https://www.aclweb.org/anthology/L16-1675 | |
| PWC | https://paperswithcode.com/paper/flextag-a-highly-flexible-pos-tagging |
| Repo | https://github.com/Horsmann/FlexTag |
| Framework | none |
Supervised Machine Learning for Hybrid Meter
| Title | Supervised Machine Learning for Hybrid Meter |
| Authors | Alex Estes, Christopher Hench |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0201/ |
| https://www.aclweb.org/anthology/W16-0201 | |
| PWC | https://paperswithcode.com/paper/supervised-machine-learning-for-hybrid-meter |
| Repo | https://github.com/henchc/CLFL |
| Framework | none |
A domain-agnostic approach for opinion prediction on speech
| Title | A domain-agnostic approach for opinion prediction on speech |
| Authors | Pedro Bispo Santos, Lisa Beinborn, Iryna Gurevych |
| Abstract | We explore a domain-agnostic approach for analyzing speech with the goal of opinion prediction. We represent the speech signal by mel-frequency cepstral coefficients and apply long short-term memory neural networks to automatically learn temporal regularities in speech. In contrast to previous work, our approach does not require complex feature engineering and works without textual transcripts. As a consequence, it can easily be applied on various speech analysis tasks for different languages and the results show that it can nevertheless be competitive to the state-of-the-art in opinion prediction. In a detailed error analysis for opinion mining we find that our approach performs well in identifying speaker-specific characteristics, but should be combined with additional information if subtle differences in the linguistic content need to be identified. |
| Tasks | Emotion Recognition, Feature Engineering, Opinion Mining, Speaker Identification |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4318/ |
| https://www.aclweb.org/anthology/W16-4318 | |
| PWC | https://paperswithcode.com/paper/a-domain-agnostic-approach-for-opinion |
| Repo | https://github.com/UKPLab/coling-peoples2016-opinion-prediction |
| Framework | none |
Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information
| Title | Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information |
| Authors | Alexander Shishkin, Anastasia Bezzubtseva, Alexey Drutsa, Ilia Shishkov, Ekaterina Gladkikh, Gleb Gusev, Pavel Serdyukov |
| Abstract | This study introduces a novel feature selection approach CMICOT, which is a further evolution of filter methods with sequential forward selection (SFS) whose scoring functions are based on conditional mutual information (MI). We state and study a novel saddle point (max-min) optimization problem to build a scoring function that is able to identify joint interactions between several features. This method fills the gap of MI-based SFS techniques with high-order dependencies. In this high-dimensional case, the estimation of MI has prohibitively high sample complexity. We mitigate this cost using a greedy approximation and binary representatives what makes our technique able to be effectively used. The superiority of our approach is demonstrated by comparison with recently proposed interaction-aware filters and several interaction-agnostic state-of-the-art ones on ten publicly available benchmark datasets. |
| Tasks | Feature Selection |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6584-efficient-high-order-interaction-aware-feature-selection-based-on-conditional-mutual-information |
| http://papers.nips.cc/paper/6584-efficient-high-order-interaction-aware-feature-selection-based-on-conditional-mutual-information.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-high-order-interaction-aware |
| Repo | https://github.com/yandex/CMICOT |
| Framework | none |
Universal Decompositional Semantics on Universal Dependencies
| Title | Universal Decompositional Semantics on Universal Dependencies |
| Authors | Aaron Steven White, Drew Reisinger, Keisuke Sakaguchi, Tim Vieira, Sheng Zhang, Rachel Rudinger, Kyle Rawlins, Benjamin Van Durme |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1177/ |
| https://www.aclweb.org/anthology/D16-1177 | |
| PWC | https://paperswithcode.com/paper/universal-decompositional-semantics-on |
| Repo | https://github.com/hltcoe/PredPatt |
| Framework | none |
Incorporating Label Dependency for Answer Quality Tagging in Community Question Answering via CNN-LSTM-CRF
| Title | Incorporating Label Dependency for Answer Quality Tagging in Community Question Answering via CNN-LSTM-CRF |
| Authors | Yang Xiang, Xiaoqiang Zhou, Qingcai Chen, Zhihui Zheng, Buzhou Tang, Xiaolong Wang, Yang Qin |
| Abstract | In community question answering (cQA), the quality of answers are determined by the matching degree between question-answer pairs and the correlation among the answers. In this paper, we show that the dependency between the answer quality labels also plays a pivotal role. To validate the effectiveness of label dependency, we propose two neural network-based models, with different combination modes of Convolutional Neural Net-works, Long Short Term Memory and Conditional Random Fields. Extensive experi-ments are taken on the dataset released by the SemEval-2015 cQA shared task. The first model is a stacked ensemble of the networks. It achieves 58.96{%} on macro averaged F1, which improves the state-of-the-art neural network-based method by 2.82{%} and outper-forms the Top-1 system in the shared task by 1.77{%}. The second is a simple attention-based model whose input is the connection of the question and its corresponding answers. It produces promising results with 58.29{%} on overall F1 and gains the best performance on the Good and Bad categories. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1117/ |
| https://www.aclweb.org/anthology/C16-1117 | |
| PWC | https://paperswithcode.com/paper/incorporating-label-dependency-for-answer |
| Repo | https://github.com/o0laika0o/CNN-LSTM-CRF-for-cQA-answer-tagging |
| Framework | none |
Context-Sensitive Lexicon Features for Neural Sentiment Analysis
| Title | Context-Sensitive Lexicon Features for Neural Sentiment Analysis |
| Authors | Zhiyang Teng, Duy-Tin Vo, Yue Zhang |
| Abstract | |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1169/ |
| https://www.aclweb.org/anthology/D16-1169 | |
| PWC | https://paperswithcode.com/paper/context-sensitive-lexicon-features-for-neural |
| Repo | https://github.com/zeeeyang/lexicon_rnn |
| Framework | none |
BioMedLAT Corpus: Annotation of the Lexical Answer Type for Biomedical Questions
| Title | BioMedLAT Corpus: Annotation of the Lexical Answer Type for Biomedical Questions |
| Authors | Mariana Neves, Milena Kraus |
| Abstract | Question answering (QA) systems need to provide exact answers for the questions that are posed to the system. However, this can only be achieved through a precise processing of the question. During this procedure, one important step is the detection of the expected type of answer that the system should provide by extracting the headword of the questions and identifying its semantic type. We have annotated the headword and assigned UMLS semantic types to 643 factoid/list questions from the BioASQ training data. We present statistics on the corpus and a preliminary evaluation in baseline experiments. We also discuss the challenges on both the manual annotation and the automatic detection of the headwords and the semantic types. We believe that this is a valuable resource for both training and evaluation of biomedical QA systems. The corpus is available at: \url{https://github.com/mariananeves/BioMedLAT}. |
| Tasks | Part-Of-Speech Tagging, Question Answering, Semantic Role Labeling, Tokenization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4407/ |
| https://www.aclweb.org/anthology/W16-4407 | |
| PWC | https://paperswithcode.com/paper/biomedlat-corpus-annotation-of-the-lexical |
| Repo | https://github.com/mariananeves/BioMedLAT |
| Framework | none |
Leveraging RDF Graphs for Crossing Multiple Bilingual Dictionaries
| Title | Leveraging RDF Graphs for Crossing Multiple Bilingual Dictionaries |
| Authors | Marta Villegas, Maite Melero, N{'u}ria Bel, Jorge Gracia |
| Abstract | The experiments presented here exploit the properties of the Apertium RDF Graph, principally cycle density and nodes{'} degree, to automatically generate new translation relations between words, and therefore to enrich existing bilingual dictionaries with new entries. Currently, the Apertium RDF Graph includes data from 22 Apertium bilingual dictionaries and constitutes a large unified array of linked lexical entries and translations that are available and accessible on the Web (http://linguistic.linkeddata.es/apertium/). In particular, its graph structure allows for interesting exploitation opportunities, some of which are addressed in this paper. Two {`}massive{'} experiments are reported: in the first one, the original EN-ES translation set was removed from the Apertium RDF Graph and a new EN-ES version was generated. The results were compared against the previously removed EN-ES data and against the Concise Oxford Spanish Dictionary. In the second experiment, a new non-existent EN-FR translation set was generated. In this case the results were compared against a converted wiktionary English-French file. The results we got are really good and perform well for the extreme case of correlated polysemy. This lead us to address the possibility to use cycles and nodes degree to identify potential oddities in the source data. If cycle density proves efficient when considering potential targets, we can assume that in dense graphs nodes with low degree may indicate potential errors. | |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1140/ |
| https://www.aclweb.org/anthology/L16-1140 | |
| PWC | https://paperswithcode.com/paper/leveraging-rdf-graphs-for-crossing-multiple |
| Repo | https://github.com/martavillegas/ApertiumRDF |
| Framework | none |
