Paper Group NANR 92
COMMIT at SemEval-2017 Task 5: Ontology-based Method for Sentiment Analysis of Financial Headlines. Unifying Text, Metadata, and User Network Representations with a Neural Network for Geolocation Prediction. Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017). Multilingual Vector Representations of W …
COMMIT at SemEval-2017 Task 5: Ontology-based Method for Sentiment Analysis of Financial Headlines
| Title | COMMIT at SemEval-2017 Task 5: Ontology-based Method for Sentiment Analysis of Financial Headlines |
| Authors | Kim Schouten, Flavius Frasincar, Franciska de Jong |
| Abstract | This paper describes our submission to Task 5 of SemEval 2017, Fine-Grained Sentiment Analysis on Financial Microblogs and News, where we limit ourselves to performing sentiment analysis on news headlines only (track 2). The approach presented in this paper uses a Support Vector Machine to do the required regression, and besides unigrams and a sentiment tool, we use various ontology-based features. To this end we created a domain ontology that models various concepts from the financial domain. This allows us to model the sentiment of actions depending on which entity they are affecting (e.g., {}decreasing debt{'} is positive, but {}decreasing profit{'} is negative). The presented approach yielded a cosine distance of 0.6810 on the official test data, resulting in the 12th position. |
| Tasks | Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2151/ |
| https://www.aclweb.org/anthology/S17-2151 | |
| PWC | https://paperswithcode.com/paper/commit-at-semeval-2017-task-5-ontology-based |
| Repo | |
| Framework | |
Unifying Text, Metadata, and User Network Representations with a Neural Network for Geolocation Prediction
| Title | Unifying Text, Metadata, and User Network Representations with a Neural Network for Geolocation Prediction |
| Authors | Yasuhide Miura, Motoki Taniguchi, Tomoki Taniguchi, Tomoko Ohkuma |
| Abstract | We propose a novel geolocation prediction model using a complex neural network. Geolocation prediction in social media has attracted many researchers to use information of various types. Our model unifies text, metadata, and user network representations with an attention mechanism to overcome previous ensemble approaches. In an evaluation using two open datasets, the proposed model exhibited a maximum 3.8{%} increase in accuracy and a maximum of 6.6{%} increase in accuracy@161 against previous models. We further analyzed several intermediate layers of our model, which revealed that their states capture some statistical characteristics of the datasets. |
| Tasks | Sentiment Analysis |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1116/ |
| https://www.aclweb.org/anthology/P17-1116 | |
| PWC | https://paperswithcode.com/paper/unifying-text-metadata-and-user-network |
| Repo | |
| Framework | |
Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017)
| Title | Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1000/ |
| https://www.aclweb.org/anthology/O17-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-29th-conference-on |
| Repo | |
| Framework | |
Multilingual Vector Representations of Words, Sentences, and Documents
| Title | Multilingual Vector Representations of Words, Sentences, and Documents |
| Authors | Gerard de Melo |
| Abstract | Neural vector representations are now ubiquitous in all subfields of natural language processing and text mining. While methods such as word2vec and GloVe are well-known, this tutorial focuses on multilingual and cross-lingual vector representations, of words, but also of sentences and documents as well. |
| Tasks | Knowledge Graphs |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-5002/ |
| https://www.aclweb.org/anthology/I17-5002 | |
| PWC | https://paperswithcode.com/paper/multilingual-vector-representations-of-words |
| Repo | |
| Framework | |
Overview of the 2017 ALTA Shared Task: Correcting OCR Errors
| Title | Overview of the 2017 ALTA Shared Task: Correcting OCR Errors |
| Authors | Diego Moll{'a}-Aliod, Steve Cassidy |
| Abstract | |
| Tasks | Optical Character Recognition |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1014/ |
| https://www.aclweb.org/anthology/U17-1014 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-2017-alta-shared-task |
| Repo | |
| Framework | |
Argument Mining on Twitter: Arguments, Facts and Sources
| Title | Argument Mining on Twitter: Arguments, Facts and Sources |
| Authors | Mihai Dusmanu, Elena Cabrio, Serena Villata |
| Abstract | Social media collect and spread on the Web personal opinions, facts, fake news and all kind of information users may be interested in. Applying argument mining methods to such heterogeneous data sources is a challenging open research issue, in particular considering the peculiarities of the language used to write textual messages on social media. In addition, new issues emerge when dealing with arguments posted on such platforms, such as the need to make a distinction between personal opinions and actual facts, and to detect the source disseminating information about such facts to allow for provenance verification. In this paper, we apply supervised classification to identify arguments on Twitter, and we present two new tasks for argument mining, namely facts recognition and source identification. We study the feasibility of the approaches proposed to address these tasks on a set of tweets related to the Grexit and Brexit news topics. |
| Tasks | Argument Mining |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1245/ |
| https://www.aclweb.org/anthology/D17-1245 | |
| PWC | https://paperswithcode.com/paper/argument-mining-on-twitter-arguments-facts |
| Repo | |
| Framework | |
應用興趣點辨識技術從 Web 中挖掘新商家資訊 (Mining POIs from Web via POI recognition and Relation Verification) [In Chinese]
| Title | 應用興趣點辨識技術從 Web 中挖掘新商家資訊 (Mining POIs from Web via POI recognition and Relation Verification) [In Chinese] |
| Authors | Kuo-Hsin Hsu, Hsiu-Min Chuang, Chien-Lung Chou, Chia-Hui Chang |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1006/ |
| https://www.aclweb.org/anthology/O17-1006 | |
| PWC | https://paperswithcode.com/paper/c-eeee34-eea34-web-a-aae3e-mining-pois-from |
| Repo | |
| Framework | |
手機平台 APP 之四縣客語輸入法的研發 (Research and Implementation of Sixian Hakka Pinyin Input Method for Mobile Cell APP) [In Chinese]
| Title | 手機平台 APP 之四縣客語輸入法的研發 (Research and Implementation of Sixian Hakka Pinyin Input Method for Mobile Cell APP) [In Chinese] |
| Authors | Feng-Long Huang, Kuei-Sen Liu, Sheng-Yi Tseng |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1008/ |
| https://www.aclweb.org/anthology/O17-1008 | |
| PWC | https://paperswithcode.com/paper/a13a-app-a1ac-aeae14-a3cc-c14-research-and |
| Repo | |
| Framework | |
A Screening Rule for l1-Regularized Ising Model Estimation
| Title | A Screening Rule for l1-Regularized Ising Model Estimation |
| Authors | Zhaobin Kuang, Sinong Geng, David Page |
| Abstract | We discover a screening rule for l1-regularized Ising model estimation. The simple closed-form screening rule is a necessary and sufficient condition for exactly recovering the blockwise structure of a solution under any given regularization parameters. With enough sparsity, the screening rule can be combined with various optimization procedures to deliver solutions efficiently in practice. The screening rule is especially suitable for large-scale exploratory data analysis, where the number of variables in the dataset can be thousands while we are only interested in the relationship among a handful of variables within moderate-size clusters for interpretability. Experimental results on various datasets demonstrate the efficiency and insights gained from the introduction of the screening rule. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6674-a-screening-rule-for-l1-regularized-ising-model-estimation |
| http://papers.nips.cc/paper/6674-a-screening-rule-for-l1-regularized-ising-model-estimation.pdf | |
| PWC | https://paperswithcode.com/paper/a-screening-rule-for-l1-regularized-ising |
| Repo | |
| Framework | |
Toward Contextual Valence Shifters in Vietnamese Reviews
| Title | Toward Contextual Valence Shifters in Vietnamese Reviews |
| Authors | Thien Khai Tran, Tuoi Thi Phan |
| Abstract | |
| Tasks | Sentiment Analysis, Subjectivity Analysis |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1016/ |
| https://www.aclweb.org/anthology/O17-1016 | |
| PWC | https://paperswithcode.com/paper/toward-contextual-valence-shifters-in |
| Repo | |
| Framework | |
Amplifying a Sense of Emotion toward Drama-Long Short-Term Memory Recurrent Neural Network for dynamic emotion recognition
| Title | Amplifying a Sense of Emotion toward Drama-Long Short-Term Memory Recurrent Neural Network for dynamic emotion recognition |
| Authors | Huang-Cheng Chou, Chun-Min Chang, Yu-Shuo Liu, Shiuan-Kai Kao, Chi-Chun Lee |
| Abstract | |
| Tasks | Emotion Recognition |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1013/ |
| https://www.aclweb.org/anthology/O17-1013 | |
| PWC | https://paperswithcode.com/paper/amplifying-a-sense-of-emotion-toward-drama |
| Repo | |
| Framework | |
Universal Dependencies are Hard to Parse – or are They?
| Title | Universal Dependencies are Hard to Parse – or are They? |
| Authors | Ines Rehbein, Julius Steen, Bich-Ngoc Do, Anette Frank |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6525/ |
| https://www.aclweb.org/anthology/W17-6525 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-are-hard-to-parse-a-or |
| Repo | |
| Framework | |
PTT 網站餐廳美食類別擷取之研究 (A Study of Restaurant Information and Food Type Extraction from PTT) [In Chinese]
| Title | PTT 網站餐廳美食類別擷取之研究 (A Study of Restaurant Information and Food Type Extraction from PTT) [In Chinese] |
| Authors | Chih-Yu Chung, Chien-Lung Chou, Chia-Hui Chang |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1019/ |
| https://www.aclweb.org/anthology/O17-1019 | |
| PWC | https://paperswithcode.com/paper/ptt-c2cea3c34eeaaa1c-c-a-study-of-restaurant |
| Repo | |
| Framework | |
應用詞向量於語言樣式探勘之研究 (Mining Language Patterns Using Word Embeddings) [In Chinese]
| Title | 應用詞向量於語言樣式探勘之研究 (Mining Language Patterns Using Word Embeddings) [In Chinese] |
| Authors | Xiang Xiao, Shao-Zhen Ye, Liang-Chih Yu, K.Robert Lai |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1022/ |
| https://www.aclweb.org/anthology/O17-1022 | |
| PWC | https://paperswithcode.com/paper/c-eae14eae-a14aa1c-c-mining-language-patterns |
| Repo | |
| Framework | |
Reconstruct & Crush Network
| Title | Reconstruct & Crush Network |
| Authors | Erinc Merdivan, Mohammad Reza Loghmani, Matthieu Geist |
| Abstract | This article introduces an energy-based model that is adversarial regarding data: it minimizes the energy for a given data distribution (the positive samples) while maximizing the energy for another given data distribution (the negative or unlabeled samples). The model is especially instantiated with autoencoders where the energy, represented by the reconstruction error, provides a general distance measure for unknown data. The resulting neural network thus learns to reconstruct data from the first distribution while crushing data from the second distribution. This solution can handle different problems such as Positive and Unlabeled (PU) learning or covariate shift, especially with imbalanced data. Using autoencoders allows handling a large variety of data, such as images, text or even dialogues. Our experiments show the flexibility of the proposed approach in dealing with different types of data in different settings: images with CIFAR-10 and CIFAR-100 (not-in-training setting), text with Amazon reviews (PU learning) and dialogues with Facebook bAbI (next response classification and dialogue completion). |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7041-reconstruct-crush-network |
| http://papers.nips.cc/paper/7041-reconstruct-crush-network.pdf | |
| PWC | https://paperswithcode.com/paper/reconstruct-crush-network |
| Repo | |
| Framework | |
