Paper Group NANR 187
Normalization of Indonesian-English Code-Mixed Twitter Data. DATNet: Dual Adversarial Transfer for Low-resource Named Entity Recognition. The Titans at SemEval-2019 Task 5: Detection of hate speech against immigrants and women in Twitter. Integration of Knowledge Graph Embedding Into Topic Modeling with Hierarchical Dirichlet Process. Team Fernando …
Normalization of Indonesian-English Code-Mixed Twitter Data
| Title | Normalization of Indonesian-English Code-Mixed Twitter Data |
| Authors | Anab Maulana Barik, Rahmad Mahendra, Mirna Adriani |
| Abstract | Twitter is an excellent source of data for NLP researches as it offers tremendous amount of textual data. However, processing tweet to extract meaningful information is very challenging, at least for two reasons: (i) using nonstandard words as well as informal writing manner, and (ii) code-mixing issues, which is combining multiple languages in single tweet conversation. Most of the previous works have addressed both issues in isolated different task. In this study, we work on normalization task in code-mixed Twitter data, more specifically in Indonesian-English language. We propose a pipeline that consists of four modules, i.e tokenization, language identification, lexical normalization, and translation. Another contribution is to provide a gold standard of Indonesian-English code-mixed data for each module. |
| Tasks | Language Identification, Lexical Normalization, Tokenization |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5554/ |
| https://www.aclweb.org/anthology/D19-5554 | |
| PWC | https://paperswithcode.com/paper/normalization-of-indonesian-english-code |
| Repo | |
| Framework | |
DATNet: Dual Adversarial Transfer for Low-resource Named Entity Recognition
| Title | DATNet: Dual Adversarial Transfer for Low-resource Named Entity Recognition |
| Authors | Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Rick Siow Mong Goh, Kenneth Kwok |
| Abstract | We propose a new architecture termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER). Specifically, two variants of DATNet, i.e., DATNet-F and DATNet-P, are proposed to explore effective feature fusion between high and low resource. To address the noisy and imbalanced training data, we propose a novel Generalized Resource-Adversarial Discriminator (GRAD). Additionally, adversarial training is adopted to boost model generalization. We examine the effects of different components in DATNet across domains and languages and show that significant improvement can be obtained especially for low-resource data. Without augmenting any additional hand-crafted features, we achieve new state-of-the-art performances on CoNLL and Twitter NER—88.16% F1 for Spanish, 53.43% F1 for WNUT-2016, and 42.83% F1 for WNUT-2017. |
| Tasks | Named Entity Recognition |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkGzUjR5tQ |
| https://openreview.net/pdf?id=HkGzUjR5tQ | |
| PWC | https://paperswithcode.com/paper/datnet-dual-adversarial-transfer-for-low |
| Repo | |
| Framework | |
The Titans at SemEval-2019 Task 5: Detection of hate speech against immigrants and women in Twitter
| Title | The Titans at SemEval-2019 Task 5: Detection of hate speech against immigrants and women in Twitter |
| Authors | Avishek Garain, Arpan Basu |
| Abstract | This system paper is a description of the system submitted to {''}SemEval-2019 Task 5{''} Task B for the English language, where we had to primarily detect hate speech and then detect aggressive behaviour and its target audience in Twitter. There were two specific target audiences, immigrants and women. The language of the tweets was English. We were required to first detect whether a tweet is containing hate speech. Thereafter we were required to find whether the tweet was showing aggressive behaviour, and then we had to find whether the targeted audience was an individual or a group of people. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2088/ |
| https://www.aclweb.org/anthology/S19-2088 | |
| PWC | https://paperswithcode.com/paper/the-titans-at-semeval-2019-task-5-detection |
| Repo | |
| Framework | |
Integration of Knowledge Graph Embedding Into Topic Modeling with Hierarchical Dirichlet Process
| Title | Integration of Knowledge Graph Embedding Into Topic Modeling with Hierarchical Dirichlet Process |
| Authors | Dingcheng Li, Siamak Zamani, Jingyuan Zhang, Ping Li |
| Abstract | Leveraging domain knowledge is an effective strategy for enhancing the quality of inferred low-dimensional representations of documents by topic models. In this paper, we develop \textit{topic modeling with knowledge graph embedding} (TMKGE), a Bayesian nonparametric model to employ knowledge graph (KG) embedding in the context of topic modeling, for extracting more coherent topics. Specifically, we build a hierarchical Dirichlet process (HDP) based model to flexibly borrow information from KG to improve the interpretability of topics. An efficient online variational inference method based on a stick-breaking construction of HDP is developed for TMKGE, making TMKGE suitable for large document corpora and KGs. Experiments on three public datasets illustrate the superior performance of TMKGE in terms of topic coherence and document classification accuracy, compared to state-of-the-art topic modeling methods. |
| Tasks | Document Classification, Graph Embedding, Knowledge Graph Embedding, Topic Models |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1099/ |
| https://www.aclweb.org/anthology/N19-1099 | |
| PWC | https://paperswithcode.com/paper/integration-of-knowledge-graph-embedding-into |
| Repo | |
| Framework | |
Team Fernando-Pessa at SemEval-2019 Task 4: Back to Basics in Hyperpartisan News Detection
| Title | Team Fernando-Pessa at SemEval-2019 Task 4: Back to Basics in Hyperpartisan News Detection |
| Authors | Andr{'e} Cruz, Gil Rocha, Rui Sousa-Silva, Henrique Lopes Cardoso |
| Abstract | This paper describes our submission to the SemEval 2019 Hyperpartisan News Detection task. Our system aims for a linguistics-based document classification from a minimal set of interpretable features, while maintaining good performance. To this goal, we follow a feature-based approach and perform several experiments with different machine learning classifiers. Additionally, we explore feature importances and distributions among the two classes. On the main task, our model achieved an accuracy of 71.7{%}, which was improved after the task{'}s end to 72.9{%}. We also participate on the meta-learning sub-task, for classifying documents with the binary classifications of all submitted systems as input, achieving an accuracy of 89.9{%}. |
| Tasks | Document Classification, Meta-Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2173/ |
| https://www.aclweb.org/anthology/S19-2173 | |
| PWC | https://paperswithcode.com/paper/team-fernando-pessa-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
Analysis of Memory Organization for Dynamic Neural Networks
| Title | Analysis of Memory Organization for Dynamic Neural Networks |
| Authors | Ying Ma, Jose Principe |
| Abstract | An increasing number of neural memory networks have been developed, leading to the need for a systematic approach to analyze and compare their underlying memory capabilities. Thus, in this paper, we propose a taxonomy for four popular dynamic models: vanilla recurrent neural network, long short-term memory, neural stack and neural RAM and their variants. Based on this taxonomy, we create a framework to analyze memory organization and then compare these network architectures. This analysis elucidates how different mapping functions capture the information in the past of the input, and helps to open the dynamic neural network black box from the perspective of memory usage. Four representative tasks that would fit optimally the characteristics of each memory network are carefully selected to show each network’s expressive power. We also discuss how to use this taxonomy to help users select the most parsimonious type of memory network for a specific task. Two natural language processing applications are used to evaluate the methodology in a realistic setting. |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://openreview.net/forum?id=H1gRM2A5YX |
| https://openreview.net/pdf?id=H1gRM2A5YX | |
| PWC | https://paperswithcode.com/paper/analysis-of-memory-organization-for-dynamic |
| Repo | |
| Framework | |
NICT’s Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task
| Title | NICT’s Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task |
| Authors | Benjamin Marie, Haipeng Sun, Rui Wang, Kehai Chen, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita |
| Abstract | This paper presents the NICT{'}s participation in the WMT19 unsupervised news translation task. We participated in the unsupervised translation direction: German-Czech. Our primary submission to the task is the result of a simple combination of our unsupervised neural and statistical machine translation systems. Our system is ranked first for the German-to-Czech translation task, using only the data provided by the organizers ({``}constraint{'}{''}), according to both BLEU-cased and human evaluation. We also performed contrastive experiments with other language pairs, namely, English-Gujarati and English-Kazakh, to better assess the effectiveness of unsupervised machine translation in for distant language pairs and in truly low-resource conditions. | |
| Tasks | Machine Translation, Unsupervised Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5330/ |
| https://www.aclweb.org/anthology/W19-5330 | |
| PWC | https://paperswithcode.com/paper/nicts-unsupervised-neural-and-statistical |
| Repo | |
| Framework | |
Characterizing the Accuracy/Complexity Landscape of Explanations of Deep Networks through Knowledge Extraction
| Title | Characterizing the Accuracy/Complexity Landscape of Explanations of Deep Networks through Knowledge Extraction |
| Authors | Simon Odense, Artur d’Avila Garcez |
| Abstract | Knowledge extraction techniques are used to convert neural networks into symbolic descriptions with the objective of producing more comprehensible learning models. The central challenge is to find an explanation which is more comprehensible than the original model while still representing that model faithfully. The distributed nature of deep networks has led many to believe that the hidden features of a neural network cannot be explained by logical descriptions simple enough to be understood by humans, and that decompositional knowledge extraction should be abandoned in favour of other methods. In this paper we examine this question systematically by proposing a knowledge extraction method using \textit{M-of-N} rules which allows us to map the complexity/accuracy landscape of rules describing hidden features in a Convolutional Neural Network (CNN). Experiments reported in this paper show that the shape of this landscape reveals an optimal trade off between comprehensibility and accuracy, showing that each latent variable has an optimal \textit{M-of-N} rule to describe its behaviour. We find that the rules with optimal tradeoff in the first and final layer have a high degree of explainability whereas the rules with the optimal tradeoff in the second and third layer are less explainable. The results shed light on the feasibility of rule extraction from deep networks, and point to the value of decompositional knowledge extraction as a method of explainability. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ByEtPiAcY7 |
| https://openreview.net/pdf?id=ByEtPiAcY7 | |
| PWC | https://paperswithcode.com/paper/characterizing-the-accuracycomplexity |
| Repo | |
| Framework | |
STAC: Science Toolkit Based on Chinese Idiom Knowledge Graph
| Title | STAC: Science Toolkit Based on Chinese Idiom Knowledge Graph |
| Authors | Meiling Wang, Min Xiao, Changliang Li, Yu Guo, Zhixin Zhao, Xiaonan Liu |
| Abstract | Chinese idioms (Cheng Yu) have seen five thousand years{'} history and culture of China, meanwhile they contain large number of scientific achievement of ancient China. However, existing Chinese online idiom dictionaries have limited function for scientific exploration. In this paper, we first construct a Chinese idiom knowledge graph by extracting domains and dynasties and associating them with idioms, and based on the idiom knowledge graph, we propose a Science Toolkit for Ancient China (STAC) aiming to support scientific exploration. In the STAC toolkit, idiom navigator helps users explore overall scientific progress from idiom perspective with visualization tools, and idiom card and idiom QA shorten action path and avoid thinking being interrupted while users are reading and writing. The current STAC toolkit is deployed at http://120.92.208.22:7476/demo/{#}/stac. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2608/ |
| https://www.aclweb.org/anthology/W19-2608 | |
| PWC | https://paperswithcode.com/paper/stac-science-toolkit-based-on-chinese-idiom |
| Repo | |
| Framework | |
Unsupervised Adversarial Image Reconstruction
| Title | Unsupervised Adversarial Image Reconstruction |
| Authors | Arthur Pajot, Emmanuel de Bezenac, Patrick Gallinari |
| Abstract | We address the problem of recovering an underlying signal from lossy, inaccurate observations in an unsupervised setting. Typically, we consider situations where there is little to no background knowledge on the structure of the underlying signal, no access to signal-measurement pairs, nor even unpaired signal-measurement data. The only available information is provided by the observations and the measurement process statistics. We cast the problem as finding the \textit{maximum a posteriori} estimate of the signal given each measurement, and propose a general framework for the reconstruction problem. We use a formulation of generative adversarial networks, where the generator takes as input a corrupted observation in order to produce realistic reconstructions, and add a penalty term tying the reconstruction to the associated observation. We evaluate our reconstructions on several image datasets with different types of corruptions. The proposed approach yields better results than alternative baselines, and comparable performance with model variants trained with additional supervision. |
| Tasks | Image Reconstruction |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJg4Z3RqF7 |
| https://openreview.net/pdf?id=BJg4Z3RqF7 | |
| PWC | https://paperswithcode.com/paper/unsupervised-adversarial-image-reconstruction |
| Repo | |
| Framework | |
Evaluation of vector embedding models in clustering of text documents
| Title | Evaluation of vector embedding models in clustering of text documents |
| Authors | Tomasz Walkowiak, Mateusz Gniewkowski |
| Abstract | The paper presents an evaluation of word embedding models in clustering of texts in the Polish language. Authors verified six different embedding models, starting from widely used word2vec, across fastText with character n-grams embedding, to deep learning-based ELMo and BERT. Moreover, four standardisation methods, three distance measures and four clustering methods were evaluated. The analysis was performed on two corpora of texts in Polish classified into subjects. The Adjusted Mutual Information (AMI) metric was used to verify the quality of clustering results. The performed experiments show that Skipgram models with n-grams character embedding, built on KGR10 corpus and provided by Clarin-PL, outperforms other publicly available models for Polish. Moreover, presented results suggest that Yeo{–}Johnson transformation for document vectors standardisation and Agglomerative Clustering with a cosine distance should be used for grouping of text documents. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1149/ |
| https://www.aclweb.org/anthology/R19-1149 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-vector-embedding-models-in |
| Repo | |
| Framework | |
Dialect-Specific Models for Automatic Speech Recognition of African American Vernacular English
| Title | Dialect-Specific Models for Automatic Speech Recognition of African American Vernacular English |
| Authors | Rachel Dorn |
| Abstract | African American Vernacular English (AAVE) is a widely-spoken dialect of English, yet it is under-represented in major speech corpora. As a result, speakers of this dialect are often misunderstood by NLP applications. This study explores the effect on transcription accuracy of an automatic voice recognition system when AAVE data is used. Models trained on AAVE data and on Standard American English data were compared to a baseline model trained on a combination of the two dialects. The accuracy for both dialect-specific models was significantly higher than the baseline model, with the AAVE model showing over 18{%} improvement. By isolating the effect of having AAVE speakers in the training data, this study highlights the importance of increasing diversity in the field of natural language processing. |
| Tasks | Speech Recognition |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2003/ |
| https://www.aclweb.org/anthology/R19-2003 | |
| PWC | https://paperswithcode.com/paper/dialect-specific-models-for-automatic-speech |
| Repo | |
| Framework | |
Multi-View Domain Adapted Sentence Embeddings for Low-Resource Unsupervised Duplicate Question Detection
| Title | Multi-View Domain Adapted Sentence Embeddings for Low-Resource Unsupervised Duplicate Question Detection |
| Authors | Nina Poerner, Hinrich Sch{"u}tze |
| Abstract | We address the problem of Duplicate Question Detection (DQD) in low-resource domain-specific Community Question Answering forums. Our multi-view framework MV-DASE combines an ensemble of sentence encoders via Generalized Canonical Correlation Analysis, using unlabeled data only. In our experiments, the ensemble includes generic and domain-specific averaged word embeddings, domain-finetuned BERT and the Universal Sentence Encoder. We evaluate MV-DASE on the CQADupStack corpus and on additional low-resource Stack Exchange forums. Combining the strengths of different encoders, we significantly outperform BM25, all single-view systems as well as a recent supervised domain-adversarial DQD method. |
| Tasks | Community Question Answering, Question Answering, Sentence Embeddings, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1173/ |
| https://www.aclweb.org/anthology/D19-1173 | |
| PWC | https://paperswithcode.com/paper/multi-view-domain-adapted-sentence-embeddings |
| Repo | |
| Framework | |
Privacy Preserving Image Queries for Camera Localization
| Title | Privacy Preserving Image Queries for Camera Localization |
| Authors | Pablo Speciale, Johannes L. Schonberger, Sudipta N. Sinha, Marc Pollefeys |
| Abstract | Augmented/mixed reality and robotic applications are increasingly relying on cloud-based localization services, which require users to upload query images to perform camera pose estimation on a server. This raises significant privacy concerns when consumers use such services in their homes or in confidential industrial settings. Even if only image features are uploaded, the privacy concerns remain as the images can be reconstructed fairly well from feature locations and descriptors. We propose to conceal the content of the query images from an adversary on the server or a man-in-the-middle intruder. The key insight is to replace the 2D image feature points in the query image with randomly oriented 2D lines passing through their original 2D positions. It will be shown that this feature representation hides the image contents, and thereby protects user privacy, yet still provides sufficient geometric constraints to enable robust and accurate 6-DOF camera pose estimation from feature correspondences. Our proposed method can handle single- and multi-image queries as well as exploit additional information about known structure, gravity, and scale. Numerous experiments demonstrate the high practical relevance of our approach. |
| Tasks | Camera Localization, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Speciale_Privacy_Preserving_Image_Queries_for_Camera_Localization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Speciale_Privacy_Preserving_Image_Queries_for_Camera_Localization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-image-queries-for-camera |
| Repo | |
| Framework | |
SRM: A Style-Based Recalibration Module for Convolutional Neural Networks
| Title | SRM: A Style-Based Recalibration Module for Convolutional Neural Networks |
| Authors | HyunJae Lee, Hyo-Eun Kim, Hyeonseob Nam |
| Abstract | Following the advance of style transfer with Convolutional Neural Networks (CNNs), the role of styles in CNNs has drawn growing attention from a broader perspective. In this paper, we aim to fully leverage the potential of styles to improve the performance of CNNs in general vision tasks. We propose a Style-based Recalibration Module (SRM), a simple yet effective architectural unit, which adaptively recalibrates intermediate feature maps by exploiting their styles. SRM first extracts the style information from each channel of the feature maps by style pooling, then estimates per-channel recalibration weight via channel-independent style integration. By incorporating the relative importance of individual styles into feature maps, SRM effectively enhances the representational ability of a CNN. The proposed module is directly fed into existing CNN architectures with negligible overhead. We conduct comprehensive experiments on general image recognition as well as tasks related to styles, which verify the benefit of SRM over recent approaches such as Squeeze-and-Excitation (SE). To explain the inherent difference between SRM and SE, we provide an in-depth comparison of their representational properties. |
| Tasks | Style Transfer |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Lee_SRM_A_Style-Based_Recalibration_Module_for_Convolutional_Neural_Networks_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Lee_SRM_A_Style-Based_Recalibration_Module_for_Convolutional_Neural_Networks_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/srm-a-style-based-recalibration-module-for-1 |
| Repo | |
| Framework | |
