Paper Group NANR 105
Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning. Distributed Representation, LDA Topic Modelling and Deep Learning for Emerging Named Entity Recognition from Social Media. Beyond Binary Labels: Political Ideology Prediction of Twitter Users. Analysing Market Sentiments: Utilising Deep Learning to Exploit Relationshi …
Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning
| Title | Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning |
| Authors | Jing Ma, Wei Gao, Kam-Fai Wong |
| Abstract | How fake news goes viral via social media? How does its propagation pattern differ from real stories? In this paper, we attempt to address the problem of identifying rumors, i.e., fake information, out of microblog posts based on their propagation structure. We firstly model microblog posts diffusion with propagation trees, which provide valuable clues on how an original message is transmitted and developed over time. We then propose a kernel-based method called Propagation Tree Kernel, which captures high-order patterns differentiating different types of rumors by evaluating the similarities between their propagation tree structures. Experimental results on two real-world datasets demonstrate that the proposed kernel-based approach can detect rumors more quickly and accurately than state-of-the-art rumor detection models. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1066/ |
| https://www.aclweb.org/anthology/P17-1066 | |
| PWC | https://paperswithcode.com/paper/detect-rumors-in-microblog-posts-using |
| Repo | |
| Framework | |
Distributed Representation, LDA Topic Modelling and Deep Learning for Emerging Named Entity Recognition from Social Media
| Title | Distributed Representation, LDA Topic Modelling and Deep Learning for Emerging Named Entity Recognition from Social Media |
| Authors | Patrick Jansson, Shuhua Liu |
| Abstract | This paper reports our participation in the W-NUT 2017 shared task on emerging and rare entity recognition from user generated noisy text such as tweets, online reviews and forum discussions. To accomplish this challenging task, we explore an approach that combines LDA topic modelling with deep learning on word level and character level embeddings. The LDA topic modelling generates topic representation for each tweet which is used as a feature for each word in the tweet. The deep learning component consists of two-layer bidirectional LSTM and a CRF output layer. Our submitted result performed at 39.98 (F1) on entity and 37.77 on surface forms. Our new experiments after submission reached a best performance of 41.81 on entity and 40.57 on surface forms. |
| Tasks | Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4420/ |
| https://www.aclweb.org/anthology/W17-4420 | |
| PWC | https://paperswithcode.com/paper/distributed-representation-lda-topic |
| Repo | |
| Framework | |
Beyond Binary Labels: Political Ideology Prediction of Twitter Users
| Title | Beyond Binary Labels: Political Ideology Prediction of Twitter Users |
| Authors | Daniel Preo{\c{t}}iuc-Pietro, Ye Liu, Daniel Hopkins, Lyle Ungar |
| Abstract | Automatic political orientation prediction from social media posts has to date proven successful only in distinguishing between publicly declared liberals and conservatives in the US. This study examines users{'} political ideology using a seven-point scale which enables us to identify politically moderate and neutral users {–} groups which are of particular interest to political scientists and pollsters. Using a novel data set with political ideology labels self-reported through surveys, our goal is two-fold: a) to characterize the groups of politically engaged users through language use on Twitter; b) to build a fine-grained model that predicts political ideology of unseen users. Our results identify differences in both political leaning and engagement and the extent to which each group tweets using political keywords. Finally, we demonstrate how to improve ideology prediction accuracy by exploiting the relationships between the user groups. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1068/ |
| https://www.aclweb.org/anthology/P17-1068 | |
| PWC | https://paperswithcode.com/paper/beyond-binary-labels-political-ideology |
| Repo | |
| Framework | |
Analysing Market Sentiments: Utilising Deep Learning to Exploit Relationships within the Economy
| Title | Analysing Market Sentiments: Utilising Deep Learning to Exploit Relationships within the Economy |
| Authors | Tobias Daudert |
| Abstract | In today{'}s world, globalisation is not only affecting inter-culturalism but also linking markets across the globe. Given that all markets are affecting each other and are not only driven by fundamental data but also by sentiments, sentiment analysis regarding the markets becomes a tool to predict, anticipate, and milden future economic crises such as the one we faced in 2008. In this paper, an approach to improve sentiment analysis by exploiting relationships among different kinds of sentiment, together with supplementary information, from and across various data sources is proposed. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-2002/ |
| https://doi.org/10.26615/issn.1314-9156.2017_002 | |
| PWC | https://paperswithcode.com/paper/analysing-market-sentiments-utilising-deep |
| Repo | |
| Framework | |
Toward Pan-Slavic NLP: Some Experiments with Language Adaptation
| Title | Toward Pan-Slavic NLP: Some Experiments with Language Adaptation |
| Authors | Serge Sharoff |
| Abstract | There is great variation in the amount of NLP resources available for Slavonic languages. For example, the Universal Dependency treebank (Nivre et al., 2016) has about 2 MW of training resources for Czech, more than 1 MW for Russian, while only 950 words for Ukrainian and nothing for Belorussian, Bosnian or Macedonian. Similarly, the Autodesk Machine Translation dataset only covers three Slavonic languages (Czech, Polish and Russian). In this talk I will discuss a general approach, which can be called Language Adaptation, similarly to Domain Adaptation. In this approach, a model for a particular language processing task is built by lexical transfer of cognate words and by learning a new feature representation for a lesser-resourced (recipient) language starting from a better-resourced (donor) language. More specifically, I will demonstrate how language adaptation works in such training scenarios as Translation Quality Estimation, Part-of-Speech tagging and Named Entity Recognition. |
| Tasks | Domain Adaptation, Language Modelling, Machine Translation, Named Entity Recognition, Opinion Mining, Part-Of-Speech Tagging |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1401/ |
| https://www.aclweb.org/anthology/W17-1401 | |
| PWC | https://paperswithcode.com/paper/toward-pan-slavic-nlp-some-experiments-with |
| Repo | |
| Framework | |
The Ultimate Presentation Makeup Tutorial: How to Polish your Posters, Slides and Presentations Skills
| Title | The Ultimate Presentation Makeup Tutorial: How to Polish your Posters, Slides and Presentations Skills |
| Authors | Gustavo Paetzold, Lucia Specia |
| Abstract | There is no question that our research community have, and still has been producing an insurmountable amount of interesting strategies, models and tools to a wide array of problems and challenges in diverse areas of knowledge. But for as long as interesting work has existed, we{'}ve been plagued by a great unsolved mystery: how come there is so much interesting work being published in conferences, but not as many interesting and engaging posters and presentations being featured in them? In this tutorial, we present practical step-by-step makeup solutions for poster, slides and oral presentations in order to help researchers who feel like they are not able to convey the importance of their research to the community in conferences. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-5005/ |
| https://www.aclweb.org/anthology/I17-5005 | |
| PWC | https://paperswithcode.com/paper/the-ultimate-presentation-makeup-tutorial-how |
| Repo | |
| Framework | |
Proceedings of the Computing Natural Language Inference Workshop
| Title | Proceedings of the Computing Natural Language Inference Workshop |
| Authors | |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W17/W17-7200/ |
| https://www.aclweb.org/anthology/W17-7200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-computing-natural-language |
| Repo | |
| Framework | |
Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing
| Title | Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing |
| Authors | Tim Vieira, Jason Eisner |
| Abstract | Pruning hypotheses during dynamic programming is commonly used to speed up inference in settings such as parsing. Unlike prior work, we train a pruning policy under an objective that measures end-to-end performance: we search for a fast and accurate policy. This poses a difficult machine learning problem, which we tackle with the lols algorithm. lols training must continually compute the effects of changing pruning decisions: we show how to make this efficient in the constituency parsing setting, via dynamic programming and change propagation algorithms. We find that optimizing end-to-end performance in this way leads to a better Pareto frontier{—}i.e., parsers which are more accurate for a given runtime. |
| Tasks | Constituency Parsing, Decision Making, Machine Translation, Structured Prediction |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/Q17-1019/ |
| https://www.aclweb.org/anthology/Q17-1019 | |
| PWC | https://paperswithcode.com/paper/learning-to-prune-exploring-the-frontier-of |
| Repo | |
| Framework | |
Self-Crowdsourcing Training for Relation Extraction
| Title | Self-Crowdsourcing Training for Relation Extraction |
| Authors | Azad Abad, Moin Nabi, Aless Moschitti, ro |
| Abstract | In this paper we introduce a self-training strategy for crowdsourcing. The training examples are automatically selected to train the crowd workers. Our experimental results show an impact of 5{%} Improvement in terms of F1 for relation extraction task, compared to the method based on distant supervision. |
| Tasks | Question Answering, Relation Extraction, Text Summarization |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2082/ |
| https://www.aclweb.org/anthology/P17-2082 | |
| PWC | https://paperswithcode.com/paper/self-crowdsourcing-training-for-relation |
| Repo | |
| Framework | |
A Generative Attentional Neural Network Model for Dialogue Act Classification
| Title | A Generative Attentional Neural Network Model for Dialogue Act Classification |
| Authors | Quan Hung Tran, Gholamreza Haffari, Ingrid Zukerman |
| Abstract | We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a novel attentional technique and a label to label connection for sequence learning, akin to Hidden Markov Models. The experiments show that both of these innovations lead our model to outperform strong baselines for dialogue act classification on MapTask and Switchboard corpora. We further empirically analyse the effectiveness of each of the new innovations. |
| Tasks | Dialogue Act Classification, Machine Translation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2083/ |
| https://www.aclweb.org/anthology/P17-2083 | |
| PWC | https://paperswithcode.com/paper/a-generative-attentional-neural-network-model |
| Repo | |
| Framework | |
Implicit Syntactic Features for Target-dependent Sentiment Analysis
| Title | Implicit Syntactic Features for Target-dependent Sentiment Analysis |
| Authors | Yuze Gao, Yue Zhang, Tong Xiao |
| Abstract | Targeted sentiment analysis investigates the sentiment polarities on given target mentions from input texts. Different from sentence level sentiment, it offers more fine-grained knowledge on each entity mention. While early work leveraged syntactic information, recent research has used neural representation learning to induce features automatically, thereby avoiding error propagation of syntactic parsers, which are particularly severe on social media texts. We study a method to leverage syntactic information without explicitly building the parser outputs, by training an encoder-decoder structure parser model on standard syntactic treebanks, and then leveraging its hidden encoder layers when analysing tweets. Such hidden vectors do not contain explicit syntactic outputs, yet encode rich syntactic features. We use them to augment the inputs to a baseline state-of-the-art targeted sentiment classifier, observing significant improvements on various benchmark datasets. We obtain the best accuracies on all test sets. |
| Tasks | Representation Learning, Sentiment Analysis |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1052/ |
| https://www.aclweb.org/anthology/I17-1052 | |
| PWC | https://paperswithcode.com/paper/implicit-syntactic-features-for-target |
| Repo | |
| Framework | |
EuroSense: Automatic Harvesting of Multilingual Sense Annotations from Parallel Text
| Title | EuroSense: Automatic Harvesting of Multilingual Sense Annotations from Parallel Text |
| Authors | Claudio Delli Bovi, Jose Camacho-Collados, Aless Raganato, ro, Roberto Navigli |
| Abstract | Parallel corpora are widely used in a variety of Natural Language Processing tasks, from Machine Translation to cross-lingual Word Sense Disambiguation, where parallel sentences can be exploited to automatically generate high-quality sense annotations on a large scale. In this paper we present EuroSense, a multilingual sense-annotated resource based on the joint disambiguation of the Europarl parallel corpus, with almost 123 million sense annotations for over 155 thousand distinct concepts and entities from a language-independent unified sense inventory. We evaluate the quality of our sense annotations intrinsically and extrinsically, showing their effectiveness as training data for Word Sense Disambiguation. |
| Tasks | Entity Linking, Machine Translation, Word Sense Disambiguation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2094/ |
| https://www.aclweb.org/anthology/P17-2094 | |
| PWC | https://paperswithcode.com/paper/eurosense-automatic-harvesting-of |
| Repo | |
| Framework | |
Determining Whether and When People Participate in the Events They Tweet About
| Title | Determining Whether and When People Participate in the Events They Tweet About |
| Authors | Krishna Chaitanya Sanagavarapu, Alakan Vempala, a, Eduardo Blanco |
| Abstract | This paper describes an approach to determine whether people participate in the events they tweet about. Specifically, we determine whether people are participants in events with respect to the tweet timestamp. We target all events expressed by verbs in tweets, including past, present and events that may occur in the future. We present new annotations using 1,096 event mentions, and experimental results showing that the task is challenging. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2101/ |
| https://www.aclweb.org/anthology/P17-2101 | |
| PWC | https://paperswithcode.com/paper/determining-whether-and-when-people |
| Repo | |
| Framework | |
On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit
| Title | On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit |
| Authors | Jie Shen, Ping Li |
| Abstract | Recovering the support of a sparse signal from its compressed samples has been one of the most important problems in high dimensional statistics. In this paper, we present a novel analysis for the hard thresholding pursuit (HTP) algorithm, showing that it exactly recovers the support of an arbitrary s-sparse signal within O(sklogk) iterations via a properly chosen proxy function, where k is the condition number of the problem. In stark contrast to the theoretical results in the literature, the iteration complexity we obtained holds without assuming the restricted isometry property, or relaxing the sparsity, or utilizing the optimality of the underlying signal. We further extend our result to a more challenging scenario, where the subproblem involved in HTP cannot be solved exactly. We prove that even in this setting, support recovery is possible and the computational complexity of HTP is established. Numerical study substantiates our theoretical results. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=663 |
| http://proceedings.mlr.press/v70/shen17a/shen17a.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-iteration-complexity-of-support |
| Repo | |
| Framework | |
Character-Aware Neural Morphological Disambiguation
| Title | Character-Aware Neural Morphological Disambiguation |
| Authors | Alymzhan Toleu, Gulmira Tolegen, Aibek Makazhanov |
| Abstract | We develop a language-independent, deep learning-based approach to the task of morphological disambiguation. Guided by the intuition that the correct analysis should be {``}most similar{''} to the context, we propose dense representations for morphological analyses and surface context and a simple yet effective way of combining the two to perform disambiguation. Our approach improves on the language-dependent state of the art for two agglutinative languages (Turkish and Kazakh) and can be potentially applied to other morphologically complex languages. | |
| Tasks | Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2105/ |
| https://www.aclweb.org/anthology/P17-2105 | |
| PWC | https://paperswithcode.com/paper/character-aware-neural-morphological |
| Repo | |
| Framework | |
