Paper Group NANR 193
BREAKING! Presenting Fake News Corpus for Automated Fact Checking. Fake News Detection using Deep Markov Random Fields. Distant Supervision for Sentiment Attitude Extraction. Samvaadhana: A Telugu Dialogue System in Hospital Domain. Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template. A Constituency Parsing …
BREAKING! Presenting Fake News Corpus for Automated Fact Checking
| Title | BREAKING! Presenting Fake News Corpus for Automated Fact Checking |
| Authors | Archita Pathak, Rohini Srihari |
| Abstract | Popular fake news articles spread faster than mainstream articles on the same topic which renders manual fact checking inefficient. At the same time, creating tools for automatic detection is as challenging due to lack of dataset containing articles which present fake or manipulated stories as compelling facts. In this paper, we introduce manually verified corpus of compelling fake and questionable news articles on the USA politics, containing around 700 articles from Aug-Nov, 2016. We present various analyses on this corpus and finally implement classification model based on linguistic features. This work is still in progress as we plan to extend the dataset in the future and use it for our approach towards automated fake news detection. |
| Tasks | Fake News Detection |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2050/ |
| https://www.aclweb.org/anthology/P19-2050 | |
| PWC | https://paperswithcode.com/paper/breaking-presenting-fake-news-corpus-for |
| Repo | |
| Framework | |
Fake News Detection using Deep Markov Random Fields
| Title | Fake News Detection using Deep Markov Random Fields |
| Authors | Duc Minh Nguyen, Tien Huu Do, Robert Calderbank, Nikos Deligiannis |
| Abstract | Deep-learning-based models have been successfully applied to the problem of detecting fake news on social media. While the correlations among news articles have been shown to be effective cues for online news analysis, existing deep-learning-based methods often ignore this information and only consider each news article individually. To overcome this limitation, we develop a graph-theoretic method that inherits the power of deep learning while at the same time utilizing the correlations among the articles. We formulate fake news detection as an inference problem in a Markov random field (MRF) which can be solved by the iterative mean-field algorithm. We then unfold the mean-field algorithm into hidden layers that are composed of common neural network operations. By integrating these hidden layers on top of a deep network, which produces the MRF potentials, we obtain our deep MRF model for fake news detection. Experimental results on well-known datasets show that the proposed model improves upon various state-of-the-art models. |
| Tasks | Fake News Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1141/ |
| https://www.aclweb.org/anthology/N19-1141 | |
| PWC | https://paperswithcode.com/paper/fake-news-detection-using-deep-markov-random |
| Repo | |
| Framework | |
Distant Supervision for Sentiment Attitude Extraction
| Title | Distant Supervision for Sentiment Attitude Extraction |
| Authors | Nicolay Rusnachenko, Natalia Loukachevitch, Elena Tutubalina |
| Abstract | News articles often convey attitudes between the mentioned subjects, which is essential for understanding the described situation. In this paper, we describe a new approach to distant supervision for extracting sentiment attitudes between named entities mentioned in texts. Two factors (pair-based and frame-based) were used to automatically label an extensive news collection, dubbed as RuAttitudes. The latter became a basis for adaptation and training convolutional architectures, including piecewise max pooling and full use of information across different sentences. The results show that models, trained with RuAttitudes, outperform ones that were trained with only supervised learning approach and achieve 13.4{%} increase in F1-score on RuSentRel collection. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1118/ |
| https://www.aclweb.org/anthology/R19-1118 | |
| PWC | https://paperswithcode.com/paper/distant-supervision-for-sentiment-attitude |
| Repo | |
| Framework | |
Samvaadhana: A Telugu Dialogue System in Hospital Domain
| Title | Samvaadhana: A Telugu Dialogue System in Hospital Domain |
| Authors | Suma Reddy Duggenpudi, Kusampudi Siva Subrahamanyam Varma, Radhika Mamidi |
| Abstract | In this paper, a dialogue system for Hospital domain in Telugu, which is a resource-poor Dravidian language, has been built. It handles various hospital and doctor related queries. The main aim of this paper is to present an approach for modelling a dialogue system in a resource-poor language by combining linguistic and domain knowledge. Focusing on the question answering aspect of the dialogue system, we identified Question Classification and Query Processing as the two most important parts of the dialogue system. Our method combines deep learning techniques for question classification and computational rule-based analysis for query processing. Human evaluation of the system has been performed as there is no automated evaluation tool for dialogue systems in Telugu. Our system achieves a high overall rating along with a significantly accurate context-capturing method as shown in the results. |
| Tasks | Question Answering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6126/ |
| https://www.aclweb.org/anthology/D19-6126 | |
| PWC | https://paperswithcode.com/paper/samvaadhana-a-telugu-dialogue-system-in |
| Repo | |
| Framework | |
Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template
| Title | Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template |
| Authors | Yunfan Gu, Yang Yuqiao, Zhongyu Wei |
| Abstract | Question paraphrasing aims to restate a given question with different expressions but keep the original meaning. Recent approaches are mostly based on neural networks following a sequence-to-sequence fashion, however, these models tend to generate unpredictable results. To overcome this drawback, we propose a pipeline model based on templates. It follows three steps, a) identifies template from the input question, b) retrieves candidate templates, c) fills candidate templates with original topic words. Experiment results on two self-constructed datasets show that our model outperforms the sequence-to-sequence model in a large margin and the advantage is more promising when the size of training sample is small. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5514/ |
| https://www.aclweb.org/anthology/D19-5514 | |
| PWC | https://paperswithcode.com/paper/extract-transform-and-filling-a-pipeline |
| Repo | |
| Framework | |
A Constituency Parsing Tree based Method for Relation Extraction from Abstracts of Scholarly Publications
| Title | A Constituency Parsing Tree based Method for Relation Extraction from Abstracts of Scholarly Publications |
| Authors | Ming Jiang, Jana Diesner |
| Abstract | We present a simple, rule-based method for extracting entity networks from the abstracts of scientific literature. By taking advantage of selected syntactic features of constituent parsing trees, our method automatically extracts and constructs graphs in which nodes represent text-based entities (in this case, noun phrases) and their relationships (in this case, verb phrases or preposition phrases). We use two benchmark datasets for evaluation and compare with previously presented results for these data. Our evaluation results show that the proposed method leads to accuracy rates that are comparable to or exceed the results achieved with state-of-the-art, learning-based methods in several cases. |
| Tasks | Constituency Parsing, Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5323/ |
| https://www.aclweb.org/anthology/D19-5323 | |
| PWC | https://paperswithcode.com/paper/a-constituency-parsing-tree-based-method-for |
| Repo | |
| Framework | |
LORIA / Lorraine University at Multilingual Surface Realisation 2019
| Title | LORIA / Lorraine University at Multilingual Surface Realisation 2019 |
| Authors | Anastasia Shimorina, Claire Gardent |
| Abstract | This paper presents the LORIA / Lorraine University submission at the Multilingual Surface Realisation shared task 2019 for the shallow track. We outline our approach and evaluate it on 11 languages covered by the shared task. We provide a separate evaluation of each component of our pipeline, concluding on some difficulties and suggesting directions for future work. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6312/ |
| https://www.aclweb.org/anthology/D19-6312 | |
| PWC | https://paperswithcode.com/paper/loria-lorraine-university-at-multilingual |
| Repo | |
| Framework | |
Learning From the Experience of Others: Approximate Empirical Bayes in Neural Networks
| Title | Learning From the Experience of Others: Approximate Empirical Bayes in Neural Networks |
| Authors | Han Zhao, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Geoff Gordon |
| Abstract | Learning deep neural networks could be understood as the combination of representation learning and learning halfspaces. While most previous work aims to diversify representation learning by data augmentations and regularizations, we explore the opposite direction through the lens of empirical Bayes method. Specifically, we propose a matrix-variate normal prior whose covariance matrix has a Kronecker product structure to capture the correlations in learning different neurons through backpropagation. The prior encourages neurons to learn from the experience of others, hence it provides an effective regularization when training large networks on small datasets. To optimize the model, we design an efficient block coordinate descent algorithm with analytic solutions. Empirically, we show that the proposed method helps the network converge to better local optima that also generalize better, and we verify the effectiveness of the approach on both multiclass classification and multitask regression problems with various network structures. |
| Tasks | Representation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1E0OsA9tX |
| https://openreview.net/pdf?id=r1E0OsA9tX | |
| PWC | https://paperswithcode.com/paper/learning-from-the-experience-of-others |
| Repo | |
| Framework | |
Proceedings of the 18th BioNLP Workshop and Shared Task
| Title | Proceedings of the 18th BioNLP Workshop and Shared Task |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5000/ |
| https://www.aclweb.org/anthology/W19-5000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-18th-bionlp-workshop-and |
| Repo | |
| Framework | |
SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage
| Title | SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage |
| Authors | Elizabeth Boschee, Joel Barry, Jayadev Billa, Marjorie Freedman, Thamme Gowda, Constantine Lignos, Chester Palen-Michel, Michael Pust, Banriskhem Kayang Khonglah, Srikanth Madikeri, Jonathan May, Scott Miller |
| Abstract | With the increasing democratization of electronic media, vast information resources are available in less-frequently-taught languages such as Swahili or Somali. That information, which may be crucially important and not available elsewhere, can be difficult for monolingual English speakers to effectively access. In this paper we present an end-to-end cross-lingual information retrieval (CLIR) and summarization system for low-resource languages that 1) enables English speakers to search foreign language repositories of text and audio using English queries, 2) summarizes the retrieved documents in English with respect to a particular information need, and 3) provides complete transcriptions and translations as needed. The SARAL system achieved the top end-to-end performance in the most recent IARPA MATERIAL CLIR+summarization evaluations. Our demonstration system provides end-to-end open query retrieval and summarization capability, and presents the original source text or audio, speech transcription, and machine translation, for two low resource languages. |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-3004/ |
| https://www.aclweb.org/anthology/P19-3004 | |
| PWC | https://paperswithcode.com/paper/saral-a-low-resource-cross-lingual-domain |
| Repo | |
| Framework | |
Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks
| Title | Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks |
| Authors | Attila Reiss, Ina Indlekofer, Philip Schmidt, Kristof Van Laerhoven |
| Abstract | Photoplethysmography (PPG)-based continuous heart rate monitoring is essential in a number of domains, e.g., for healthcare or fitness applications. Recently, methods based on time-frequency spectra emerged to address the challenges of motion artefact compensation. However, existing approaches are highly parametrised and optimised for specific scenarios of small, public datasets. We address this fragmentation by contributing research into the robustness and generalisation capabilities of PPG-based heart rate estimation approaches. First, we introduce a novel large-scale dataset (called PPG-DaLiA), including a wide range of activities performed under close to real-life conditions. Second, we extend a state-of-the-art algorithm, significantly improving its performance on several datasets. Third, we introduce deep learning to this domain, and investigate various convolutional neural network architectures. Our end-to-end learning approach takes the time-frequency spectra of synchronised PPG- and accelerometer-signals as input, and provides the estimated heart rate as output. Finally, we compare the novel deep learning approach to classical methods, performing evaluation on four public datasets. We show that on large datasets the deep learning model significantly outperforms other methods: The mean absolute error could be reduced by 31% on the new dataset PPG-DaLiA, and by 21% on the dataset WESAD. |
| Tasks | Heart rate estimation, Photoplethysmography (PPG) |
| Published | 2019-07-12 |
| URL | https://doi.org/10.3390/s19143079 |
| https://www.mdpi.com/1424-8220/19/14/3079/pdf | |
| PWC | https://paperswithcode.com/paper/deep-ppg-large-scale-heart-rate-estimation |
| Repo | |
| Framework | |
Measuring English Readability for Vietnamese Speakers
| Title | Measuring English Readability for Vietnamese Speakers |
| Authors | Phuoc Nguyen, Alex Uitdenbogerd, ra |
| Abstract | Reading is important for any language learner, but the difficulty level of the text needs to match a reader{'}s level to enable efficient learning of new vocabulary. Many widely used traditional readability measures are not effective for those who speak English as a second or additional language. This study examines English readability for Vietnamese native speakers (VL1). A collection of text difficulty judgements of nearly 100 English text passages was obtained from 12 VL1 participants, using a 5-point Likert scale. Using the same basic features found in traditional English readability measures we found that SVMs and Dale-Chall features were slightly better than linear models using either Flesch or Dale-Chall. VL1 participants{'} text judgements were strongly correlated with their past IELTS test scores. This study introduces a first approximation to readability of English text for VL1, with suggestions for further improvements. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1018/ |
| https://www.aclweb.org/anthology/U19-1018 | |
| PWC | https://paperswithcode.com/paper/measuring-english-readability-for-vietnamese |
| Repo | |
| Framework | |
Extracting Possessions from Social Media: Images Complement Language
| Title | Extracting Possessions from Social Media: Images Complement Language |
| Authors | Dhivya Chinnappa, Srikala Murugan, Eduardo Blanco |
| Abstract | This paper describes a new dataset and experiments to determine whether authors of tweets possess the objects they tweet about. We work with 5,000 tweets and show that both humans and neural networks benefit from images in addition to text. We also introduce a simple yet effective strategy to incorporate visual information into any neural network beyond weights from pretrained networks. Specifically, we consider the tags identified in an image as an additional textual input, and leverage pretrained word embeddings as usually done with regular text. Experimental results show this novel strategy is beneficial. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1061/ |
| https://www.aclweb.org/anthology/D19-1061 | |
| PWC | https://paperswithcode.com/paper/extracting-possessions-from-social-media |
| Repo | |
| Framework | |
The Feasibility of Embedding Based Automatic Evaluation for Single Document Summarization
| Title | The Feasibility of Embedding Based Automatic Evaluation for Single Document Summarization |
| Authors | Simeng Sun, Ani Nenkova |
| Abstract | ROUGE is widely used to automatically evaluate summarization systems. However, ROUGE measures semantic overlap between a system summary and a human reference on word-string level, much at odds with the contemporary treatment of semantic meaning. Here we present a suite of experiments on using distributed representations for evaluating summarizers, both in reference-based and in reference-free setting. Our experimental results show that the max value over each dimension of the summary ELMo word embeddings is a good representation that results in high correlation with human ratings. Averaging the cosine similarity of all encoders we tested yields high correlation with manual scores in reference-free setting. The distributed representations outperform ROUGE in recent corpora for abstractive news summarization but are less good on test data used in past evaluations. |
| Tasks | Document Summarization, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1116/ |
| https://www.aclweb.org/anthology/D19-1116 | |
| PWC | https://paperswithcode.com/paper/the-feasibility-of-embedding-based-automatic |
| Repo | |
| Framework | |
Better and Faster: Exponential Loss for Image Patch Matching
| Title | Better and Faster: Exponential Loss for Image Patch Matching |
| Authors | Shuang Wang, Yanfeng Li, Xuefeng Liang, Dou Quan, Bowu Yang, Shaowei Wei, Licheng Jiao |
| Abstract | Recent studies on image patch matching are paying more attention on hard sample learning, because easy samples do not contribute much to the network optimization. They have proposed various hard negative sample mining strategies, but very few addressed this problem from the perspective of loss functions. Our research shows that the conventional Siamese and triplet losses treat all samples linearly, thus make the training time consuming. Instead, we propose the exponential Siamese and triplet losses, which can naturally focus more on hard samples and put less emphasis on easy ones, meanwhile, speed up the optimization. To assist the exponential losses, we introduce the hard positive sample mining to further enhance the effectiveness. The extensive experiments demonstrate our proposal improves both metric and descriptor learning on several well accepted benchmarks, and outperforms the state-of-the-arts on the UBC dataset. Moreover, it also shows a better generalizability on cross-spectral image matching and image retrieval tasks. |
| Tasks | Image Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Better_and_Faster_Exponential_Loss_for_Image_Patch_Matching_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Better_and_Faster_Exponential_Loss_for_Image_Patch_Matching_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/better-and-faster-exponential-loss-for-image |
| Repo | |
| Framework | |
