Paper Group NAWR 19
GenSense: A Generalized Sense Retrofitting Model. Deep Affix Features Improve Neural Named Entity Recognizers. The Rise of Guardians: Fact-checking URL Recommendation to Combat Fake News. ChAnot: An Intelligent Annotation Tool for Indigenous and Highly Agglutinative Languages in Peru. A Sound and Complete Left-Corner Parsing for Minimalist Grammars …
GenSense: A Generalized Sense Retrofitting Model
| Title | GenSense: A Generalized Sense Retrofitting Model |
| Authors | Yang-Yin Lee, Ting-Yu Yen, Hen-Hsen Huang, Yow-Ting Shiue, Hsin-Hsi Chen |
| Abstract | With the aid of recently proposed word embedding algorithms, the study of semantic similarity has progressed and advanced rapidly. However, many natural language processing tasks need sense level representation. To address this issue, some researches propose sense embedding learning algorithms. In this paper, we present a generalized model from existing sense retrofitting model. The generalization takes three major components: semantic relations between the senses, the relation strength and the semantic strength. In the experiment, we show that the generalized model can outperform previous approaches in three types of experiment: semantic relatedness, contextual word similarity and semantic difference. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1141/ |
| https://www.aclweb.org/anthology/C18-1141 | |
| PWC | https://paperswithcode.com/paper/gensense-a-generalized-sense-retrofitting |
| Repo | https://github.com/y95847frank/GenSense |
| Framework | none |
Deep Affix Features Improve Neural Named Entity Recognizers
| Title | Deep Affix Features Improve Neural Named Entity Recognizers |
| Authors | Vikas Yadav, Rebecca Sharp, Steven Bethard |
| Abstract | We propose a practical model for named entity recognition (NER) that combines word and character-level information with a specific learned representation of the prefixes and suffixes of the word. We apply this approach to multilingual and multi-domain NER and show that it achieves state of the art results on the CoNLL 2002 Spanish and Dutch and CoNLL 2003 German NER datasets, consistently achieving 1.5-2.3 percent over the state of the art without relying on any dictionary features. Additionally, we show improvement on SemEval 2013 task 9.1 DrugNER, achieving state of the art results on the MedLine dataset and the second best results overall (-1.3{%} from state of the art). We also establish a new benchmark on the I2B2 2010 Clinical NER dataset with 84.70 F-score. |
| Tasks | Feature Engineering, Morphological Analysis, Named Entity Recognition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2021/ |
| https://www.aclweb.org/anthology/S18-2021 | |
| PWC | https://paperswithcode.com/paper/deep-affix-features-improve-neural-named |
| Repo | https://github.com/vikas95/Pref_Suff_Span_NN |
| Framework | none |
The Rise of Guardians: Fact-checking URL Recommendation to Combat Fake News
| Title | The Rise of Guardians: Fact-checking URL Recommendation to Combat Fake News |
| Authors | Vo, Nguyen; Lee, Kyumin |
| Abstract | A large body of research work and efforts have been focused on detecting fake news and building online fact-check systems in order to debunk fake news as soon as possible. Despite the existence of these systems, fake news is still wildly shared by online users. It indicates that these systems may not be fully utilized. After detecting fake news, what is the next step to stop people from sharing it? How can we improve the utilization of these fact-check systems? To fill this gap, in this paper, we (i) collect and analyze online users called guardians, who correct misinformation and fake news in online discussions by referring fact-checking URLs; and (ii) propose a novel fact-checking URL recommendation model to encourage the guardians to engage more in fact-checking activities. We found that the guardians usually took less than one day to reply to claims in online conversations and took another day to spread verified information to hundreds of millions of followers. Our proposed recommendation model outperformed four state-of-the-art models by 11%~33%. |
| Tasks | Fake News Detection, Recommendation Systems |
| Published | 2018-07-11 |
| URL | https://arxiv.org/abs/1806.07516 |
| https://arxiv.org/abs/1806.07516 | |
| PWC | https://paperswithcode.com/paper/the-rise-of-guardians-fact-checking-url-1 |
| Repo | https://github.com/nguyenvo09/CombatingFakeNews |
| Framework | pytorch |
ChAnot: An Intelligent Annotation Tool for Indigenous and Highly Agglutinative Languages in Peru
| Title | ChAnot: An Intelligent Annotation Tool for Indigenous and Highly Agglutinative Languages in Peru |
| Authors | Rodolfo Mercado-Gonzales, Jos{'e} Pereira-Noriega, Marco Sobrevilla, Arturo Oncevay |
| Abstract | |
| Tasks | Morphological Analysis, Part-Of-Speech Tagging |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1655/ |
| https://www.aclweb.org/anthology/L18-1655 | |
| PWC | https://paperswithcode.com/paper/chanot-an-intelligent-annotation-tool-for |
| Repo | https://github.com/iapucp/chanot-lrec2018 |
| Framework | none |
A Sound and Complete Left-Corner Parsing for Minimalist Grammars
| Title | A Sound and Complete Left-Corner Parsing for Minimalist Grammars |
| Authors | Milo{\v{s}} Stanojevi{'c}, Edward Stabler |
| Abstract | This paper presents a left-corner parser for minimalist grammars. The relation between the parser and the grammar is transparent in the sense that there is a very simple 1-1 correspondence between derivations and parses. Like left-corner context-free parsers, left-corner minimalist parsers can be non-terminating when the grammar has empty left corners, so an easily computed left-corner oracle is defined to restrict the search. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2809/ |
| https://www.aclweb.org/anthology/W18-2809 | |
| PWC | https://paperswithcode.com/paper/a-sound-and-complete-left-corner-parsing-for |
| Repo | https://github.com/stanojevic/Left-Corner-MG-parser |
| Framework | none |
Adaptive Weighting for Neural Machine Translation
| Title | Adaptive Weighting for Neural Machine Translation |
| Authors | Yachao Li, Junhui Li, Min Zhang |
| Abstract | In the popular sequence to sequence (seq2seq) neural machine translation (NMT), there exist many weighted sum models (WSMs), each of which takes a set of input and generates one output. However, the weights in a WSM are independent of each other and fixed for all inputs, suggesting that by ignoring different needs of inputs, the WSM lacks effective control on the influence of each input. In this paper, we propose adaptive weighting for WSMs to control the contribution of each input. Specifically, we apply adaptive weighting for both GRU and the output state in NMT. Experimentation on Chinese-to-English translation and English-to-German translation demonstrates that the proposed adaptive weighting is able to much improve translation accuracy by achieving significant improvement of 1.49 and 0.92 BLEU points for the two translation tasks. Moreover, we discuss in-depth on what type of information is encoded in the encoder and how information influences the generation of target words in the decoder. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1257/ |
| https://www.aclweb.org/anthology/C18-1257 | |
| PWC | https://paperswithcode.com/paper/adaptive-weighting-for-neural-machine |
| Repo | https://github.com/liyc7711/weighted-nmt |
| Framework | none |
Task-oriented Word Embedding for Text Classification
| Title | Task-oriented Word Embedding for Text Classification |
| Authors | Qian Liu, Heyan Huang, Yang Gao, Xiaochi Wei, Yuxin Tian, Luyang Liu |
| Abstract | Distributed word representation plays a pivotal role in various natural language processing tasks. In spite of its success, most existing methods only consider contextual information, which is suboptimal when used in various tasks due to a lack of task-specific features. The rational word embeddings should have the ability to capture both the semantic features and task-specific features of words. In this paper, we propose a task-oriented word embedding method and apply it to the text classification task. With the function-aware component, our method regularizes the distribution of words to enable the embedding space to have a clear classification boundary. We evaluate our method using five text classification datasets. The experiment results show that our method significantly outperforms the state-of-the-art methods. |
| Tasks | Information Retrieval, Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1172/ |
| https://www.aclweb.org/anthology/C18-1172 | |
| PWC | https://paperswithcode.com/paper/task-oriented-word-embedding-for-text |
| Repo | https://github.com/qianliu0708/ToWE |
| Framework | none |
Structured Representation Learning for Online Debate Stance Prediction
| Title | Structured Representation Learning for Online Debate Stance Prediction |
| Authors | Chang Li, Aldo Porco, Dan Goldwasser |
| Abstract | Online debates can help provide valuable information about various perspectives on a wide range of issues. However, understanding the stances expressed in these debates is a highly challenging task, which requires modeling both textual content and users{'} conversational interactions. Current approaches take a collective classification approach, which ignores the relationships between different debate topics. In this work, we suggest to view this task as a representation learning problem, and embed the text and authors jointly based on their interactions. We evaluate our model over the Internet Argumentation Corpus, and compare different approaches for structural information embedding. Experimental results show that our model can achieve significantly better results compared to previous competitive models. |
| Tasks | Representation Learning |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1316/ |
| https://www.aclweb.org/anthology/C18-1316 | |
| PWC | https://paperswithcode.com/paper/structured-representation-learning-for-online |
| Repo | https://github.com/BillMcGrady/StancePrediction |
| Framework | pytorch |
NL-FIIT at IEST-2018: Emotion Recognition utilizing Neural Networks and Multi-level Preprocessing
| Title | NL-FIIT at IEST-2018: Emotion Recognition utilizing Neural Networks and Multi-level Preprocessing |
| Authors | Samuel Pecar, Michal Farkas, Marian Simko, Peter Lacko, Maria Bielikova |
| Abstract | In this paper, we present neural models submitted to Shared Task on Implicit Emotion Recognition, organized as part of WASSA 2018. We propose a Bi-LSTM architecture with regularization through dropout and Gaussian noise. Our models use three different embedding layers: GloVe word embeddings trained on Twitter dataset, ELMo embeddings and also sentence embeddings. We see preprocessing as one of the most important parts of the task. We focused on handling emojis, emoticons, hashtags, and also various shortened word forms. In some cases, we proposed to remove some parts of the text, as they do not affect emotion of the original sentence. We also experimented with other modifications like category weights for learning and stacking multiple layers. Our model achieved a macro average F1 score of 65.55{%}, significantly outperforming the baseline model produced by a simple logistic regression. |
| Tasks | Emotion Recognition, Sentence Embeddings, Sentiment Analysis, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6231/ |
| https://www.aclweb.org/anthology/W18-6231 | |
| PWC | https://paperswithcode.com/paper/nl-fiit-at-iest-2018-emotion-recognition |
| Repo | https://github.com/SamuelPecar/nl-fiit-wassa-emotion |
| Framework | none |
Topic or Style? Exploring the Most Useful Features for Authorship Attribution
| Title | Topic or Style? Exploring the Most Useful Features for Authorship Attribution |
| Authors | Yunita Sari, Mark Stevenson, Andreas Vlachos |
| Abstract | Approaches to authorship attribution, the task of identifying the author of a document, are based on analysis of individuals{'} writing style and/or preferred topics. Although the problem has been widely explored, no previous studies have analysed the relationship between dataset characteristics and effectiveness of different types of features. This study carries out an analysis of four widely used datasets to explore how different types of features affect authorship attribution accuracy under varying conditions. The results of the analysis are applied to authorship attribution models based on both discrete and continuous representations. We apply the conclusions from our analysis to an extension of an existing approach to authorship attribution and outperform the prior state-of-the-art on two out of the four datasets used. |
| Tasks | Text Categorization |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1029/ |
| https://www.aclweb.org/anthology/C18-1029 | |
| PWC | https://paperswithcode.com/paper/topic-or-style-exploring-the-most-useful |
| Repo | https://github.com/yunitata/coling2018 |
| Framework | tf |
Measuring the Evolution of a Scientific Field through Citation Frames
| Title | Measuring the Evolution of a Scientific Field through Citation Frames |
| Authors | David Jurgens, Srijan Kumar, Raine Hoover, Dan McFarland, Dan Jurafsky |
| Abstract | |
| Tasks | Citation Intent Classification, Sentence Classification |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/papers/Q18-1028/q18-1028 |
| https://www.aclweb.org/anthology/Q18-1028 | |
| PWC | https://paperswithcode.com/paper/measuring-the-evolution-of-a-scientific-field |
| Repo | https://github.com/davidjurgens/citation-function |
| Framework | none |
Deep Factorization Machines for Knowledge Tracing
| Title | Deep Factorization Machines for Knowledge Tracing |
| Authors | Jill-J{^e}nn Vie |
| Abstract | This paper introduces our solution to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM). We used deep factorization machines, a wide and deep learning model of pairwise relationships between users, items, skills, and other entities considered. Our solution (AUC 0.815) hopefully managed to beat the logistic regression baseline (AUC 0.774) but not the top performing model (AUC 0.861) and reveals interesting strategies to build upon item response theory models. |
| Tasks | Knowledge Tracing, Language Acquisition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0545/ |
| https://www.aclweb.org/anthology/W18-0545 | |
| PWC | https://paperswithcode.com/paper/deep-factorization-machines-for-knowledge-1 |
| Repo | https://github.com/jilljenn/ktm |
| Framework | tf |
Collaborative and Adversarial Network for Unsupervised Domain Adaptation
| Title | Collaborative and Adversarial Network for Unsupervised Domain Adaptation |
| Authors | Weichen Zhang, Wanli Ouyang, Wen Li, Dong Xu |
| Abstract | In this paper, we propose a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN) through domain-collaborative and domain-adversarial training of neural networks. We use several domain classifiers on multiple CNN feature extraction layers/blocks, in which each domain classifier is connected to the hidden representations from one block and one loss function is defined based on the hidden presentation and the domain labels (e.g., source and target). We design a new loss function by integrating the losses from all blocks in order to learn informative representations from lower layers through collaborative learning and learn uninformative representations from higher layers through adversarial learning. We further extend our CAN method as Incremental CAN (iCAN), in which we iteratively select a set of pseudo-labelled target samples based on the image classifier and the last domain classifier from the previous training epoch and re-train our CAN model using the enlarged training set. Comprehensive experiments on two benchmark datasets Office and ImageCLEF-DA clearly demonstrate the effectiveness of our newly proposed approaches CAN and iCAN for unsupervised domain adaptation. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Collaborative_and_Adversarial_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Collaborative_and_Adversarial_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-and-adversarial-network-for |
| Repo | https://github.com/zhangweichen2006/iCAN |
| Framework | pytorch |
Inducing Temporal Relations from Time Anchor Annotation
| Title | Inducing Temporal Relations from Time Anchor Annotation |
| Authors | Fei Cheng, Yusuke Miyao |
| Abstract | Recognizing temporal relations among events and time expressions has been an essential but challenging task in natural language processing. Conventional annotation of judging temporal relations puts a heavy load on annotators. In reality, the existing annotated corpora include annotations on only {``}salient{''} event pairs, or on pairs in a fixed window of sentences. In this paper, we propose a new approach to obtain temporal relations from absolute time value (a.k.a. time anchors), which is suitable for texts containing rich temporal information such as news articles. We start from time anchors for events and time expressions, and temporal relation annotations are induced automatically by computing relative order of two time anchors. This proposal shows several advantages over the current methods for temporal relation annotation: it requires less annotation effort, can induce inter-sentence relations easily, and increases informativeness of temporal relations. We compare the empirical statistics and automatic recognition results with our data against a previous temporal relation corpus. We also reveal that our data contributes to a significant improvement of the downstream time anchor prediction task, demonstrating 14.1 point increase in overall accuracy. | |
| Tasks | Question Answering, Temporal Information Extraction |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1166/ |
| https://www.aclweb.org/anthology/N18-1166 | |
| PWC | https://paperswithcode.com/paper/inducing-temporal-relations-from-time-anchor |
| Repo | https://github.com/racerandom/temporalorder |
| Framework | none |
Tilde’s Machine Translation Systems for WMT 2018
| Title | Tilde’s Machine Translation Systems for WMT 2018 |
| Authors | M{=a}rcis Pinnis, Mat{=\i}ss Rikters, Rihards Kri{\v{s}}lauks |
| Abstract | The paper describes the development process of the Tilde{'}s NMT systems that were submitted for the WMT 2018 shared task on news translation. We describe the data filtering and pre-processing workflows, the NMT system training architectures, and automatic evaluation results. For the WMT 2018 shared task, we submitted seven systems (both constrained and unconstrained) for English-Estonian and Estonian-English translation directions. The submitted systems were trained using Transformer models. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6423/ |
| https://www.aclweb.org/anthology/W18-6423 | |
| PWC | https://paperswithcode.com/paper/tildes-machine-translation-systems-for-wmt |
| Repo | https://github.com/M4t1ss/parallel-corpora-tools |
| Framework | none |
