Paper Group NANR 87
Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning. Arabizi sentiment analysis based on transliteration and automatic corpus annotation. The LMU Munich Unsupervised Machine Translation Systems. Correcting Chinese Word Usage Errors for Learning Chinese as a Second Language. A Pronoun Test Suite Evaluation of the …
Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning
| Title | Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning |
| Authors | Ramit Sawhney, Manch, Prachi a, Puneet Mathur, Rajiv Shah, Raj Singh |
| Abstract | The increasing suicide rates amongst youth and its high correlation with suicidal ideation expression on social media warrants a deeper investigation into models for the detection of suicidal intent in text such as tweets to enable prevention. However, the complexity of the natural language constructs makes this task very challenging. Deep Learning architectures such as LSTMs, CNNs, and RNNs show promise in sentence level classification problems. This work investigates the ability of deep learning architectures to build an accurate and robust model for suicidal ideation detection and compares their performance with standard baselines in text classification problems. The experimental results reveal the merit in C-LSTM based models as compared to other deep learning and machine learning based classification models for suicidal ideation detection. |
| Tasks | Sentence Classification, Text Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6223/ |
| https://www.aclweb.org/anthology/W18-6223 | |
| PWC | https://paperswithcode.com/paper/exploring-and-learning-suicidal-ideation |
| Repo | |
| Framework | |
Arabizi sentiment analysis based on transliteration and automatic corpus annotation
| Title | Arabizi sentiment analysis based on transliteration and automatic corpus annotation |
| Authors | Imane Guellil, Ahsan Adeel, Faical Azouaou, Fodil Benali, Ala-eddine Hachani, Amir Hussain |
| Abstract | Arabizi is a form of writing Arabic text which relies on Latin letters, numerals and punctuation rather than Arabic letters. In the literature, the difficulties associated with Arabizi sentiment analysis have been underestimated, principally due to the complexity of Arabizi. In this paper, we present an approach to automatically classify sentiments of Arabizi messages into positives or negatives. In the proposed approach, Arabizi messages are first transliterated into Arabic. Afterwards, we automatically classify the sentiment of the transliterated corpus using an automatically annotated corpus. For corpus validation, shallow machine learning algorithms such as Support Vectors Machine (SVM) and Naive Bays (NB) are used. Simulations results demonstrate the outperformance of NB algorithm over all others. The highest achieved F1-score is up to 78{%} and 76{%} for manually and automatically transliterated dataset respectively. Ongoing work is aimed at improving the transliterator module and annotated sentiment dataset. |
| Tasks | Opinion Mining, Sentiment Analysis, Transliteration |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6249/ |
| https://www.aclweb.org/anthology/W18-6249 | |
| PWC | https://paperswithcode.com/paper/arabizi-sentiment-analysis-based-on |
| Repo | |
| Framework | |
The LMU Munich Unsupervised Machine Translation Systems
| Title | The LMU Munich Unsupervised Machine Translation Systems |
| Authors | Dario Stojanovski, Viktor Hangya, Matthias Huck, Alex Fraser, er |
| Abstract | We describe LMU Munich{'}s unsupervised machine translation systems for English↔German translation. These systems were used to participate in the WMT18 news translation shared task and more specifically, for the unsupervised learning sub-track. The systems are trained on English and German monolingual data only and exploit and combine previously proposed techniques such as using word-by-word translated data based on bilingual word embeddings, denoising and on-the-fly backtranslation. |
| Tasks | Denoising, Language Modelling, Machine Translation, Unsupervised Machine Translation, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6428/ |
| https://www.aclweb.org/anthology/W18-6428 | |
| PWC | https://paperswithcode.com/paper/the-lmu-munich-unsupervised-machine |
| Repo | |
| Framework | |
Correcting Chinese Word Usage Errors for Learning Chinese as a Second Language
| Title | Correcting Chinese Word Usage Errors for Learning Chinese as a Second Language |
| Authors | Yow-Ting Shiue, Hen-Hsen Huang, Hsin-Hsi Chen |
| Abstract | With more and more people around the world learning Chinese as a second language, the need of Chinese error correction tools is increasing. In the HSK dynamic composition corpus, word usage error (WUE) is the most common error type. In this paper, we build a neural network model that considers both target erroneous token and context to generate a correction vector and compare it against a candidate vocabulary to propose suitable corrections. To deal with potential alternative corrections, the top five proposed candidates are judged by native Chinese speakers. For more than 91{%} of the cases, our system can propose at least one acceptable correction within a list of five candidates. To the best of our knowledge, this is the first research addressing general-type Chinese WUE correction. Our system can help non-native Chinese learners revise their sentences by themselves. |
| Tasks | Grammatical Error Correction |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1204/ |
| https://www.aclweb.org/anthology/C18-1204 | |
| PWC | https://paperswithcode.com/paper/correcting-chinese-word-usage-errors-for |
| Repo | |
| Framework | |
A Pronoun Test Suite Evaluation of the English–German MT Systems at WMT 2018
| Title | A Pronoun Test Suite Evaluation of the English–German MT Systems at WMT 2018 |
| Authors | Liane Guillou, Christian Hardmeier, Ekaterina Lapshinova-Koltunski, Sharid Lo{'a}iciga |
| Abstract | We evaluate the output of 16 English-to-German MT systems with respect to the translation of pronouns in the context of the WMT 2018 competition. We work with a test suite specifically designed to assess system quality in various fine-grained categories known to be problematic. The main evaluation scores come from a semi-automatic process, combining automatic reference matching with extensive manual annotation of uncertain cases. We find that current NMT systems are good at translating pronouns with intra-sentential reference, but the inter-sentential cases remain difficult. NMT systems are also good at the translation of event pronouns, unlike systems from the phrase-based SMT paradigm. No single system performs best at translating all types of anaphoric pronouns, suggesting unexplained random effects influencing the translation of pronouns with NMT. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6435/ |
| https://www.aclweb.org/anthology/W18-6435 | |
| PWC | https://paperswithcode.com/paper/a-pronoun-test-suite-evaluation-of-the |
| Repo | |
| Framework | |
Hand PointNet: 3D Hand Pose Estimation Using Point Sets
| Title | Hand PointNet: 3D Hand Pose Estimation Using Point Sets |
| Authors | Liuhao Ge, Yujun Cai, Junwu Weng, Junsong Yuan |
| Abstract | Convolutional Neural Network (CNN) has shown promising results for 3D hand pose estimation in depth images. Different from existing CNN-based hand pose estimation methods that take either 2D images or 3D volumes as the input, our proposed Hand PointNet directly processes the 3D point cloud that models the visible surface of the hand for pose regression. Taking the normalized point cloud as the input, our proposed hand pose regression network is able to capture complex hand structures and accurately regress a low dimensional representation of the 3D hand pose. In order to further improve the accuracy of fingertips, we design a fingertip refinement network that directly takes the neighboring points of the estimated fingertip location as input to refine the fingertip location. Experiments on three challenging hand pose datasets show that our proposed method outperforms state-of-the-art methods. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Ge_Hand_PointNet_3D_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Ge_Hand_PointNet_3D_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hand-pointnet-3d-hand-pose-estimation-using |
| Repo | |
| Framework | |
Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)
| Title | Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4900/ |
| https://www.aclweb.org/anthology/W18-4900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-joint-workshop-on-2 |
| Repo | |
| Framework | |
Word-word Relations in Dementia and Typical Aging
| Title | Word-word Relations in Dementia and Typical Aging |
| Authors | Natalia Arias-Trejo, Aline Minto-Garc{'\i}a, Diana I. Luna-Umanzor, Alma E. R{'\i}os-Ponce, Balderas-Pliego Mariana, Gemma Bel-Enguix |
| Abstract | Older adults tend to suffer a decline in some of their cognitive capabilities, being language one of least affected processes. Word association norms (WAN) also known as free word associations reflect word-word relations, the participant reads or hears a word and is asked to write or say the first word that comes to mind. Free word associations show how the organization of semantic memory remains almost unchanged with age. We have performed a WAN task with very small samples of older adults with Alzheimer{'}s disease (AD), vascular dementia (VaD) and mixed dementia (MxD), and also with a control group of typical aging adults, matched by age, sex and education. All of them are native speakers of Mexican Spanish. The results show, as expected, that Alzheimer disease has a very important impact in lexical retrieval, unlike vascular and mixed dementia. This suggests that linguistic tests elaborated from WAN can be also used for detecting AD at early stages. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4109/ |
| https://www.aclweb.org/anthology/W18-4109 | |
| PWC | https://paperswithcode.com/paper/word-word-relations-in-dementia-and-typical |
| Repo | |
| Framework | |
RTM results for Predicting Translation Performance
| Title | RTM results for Predicting Translation Performance |
| Authors | Ergun Bi{\c{c}}ici |
| Abstract | With improved prediction combination using weights based on their training performance and stacking and multilayer perceptrons to build deeper prediction models, RTMs become the 3rd system in general at the sentence-level prediction of translation scores and achieve the lowest RMSE in English to German NMT QET results. For the document-level task, we compare document-level RTM models with sentence-level RTM models obtained with the concatenation of document sentences and obtain similar results. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6458/ |
| https://www.aclweb.org/anthology/W18-6458 | |
| PWC | https://paperswithcode.com/paper/rtm-results-for-predicting-translation |
| Repo | |
| Framework | |
Classifying Referential and Non-referential It Using Gaze
| Title | Classifying Referential and Non-referential It Using Gaze |
| Authors | Victoria Yaneva, Le An Ha, Richard Evans, Ruslan Mitkov |
| Abstract | When processing a text, humans and machines must disambiguate between different uses of the pronoun it, including non-referential, nominal anaphoric or clause anaphoric ones. In this paper we use eye-tracking data to learn how humans perform this disambiguation and use this knowledge to improve the automatic classification of it. We show that by using gaze data and a POS-tagger we are able to significantly outperform a common baseline and classify between three categories of it with an accuracy comparable to that of linguistic-based approaches. In addition, the discriminatory power of specific gaze features informs the way humans process the pronoun, which, to the best of our knowledge, has not been explored using data from a natural reading task. |
| Tasks | Eye Tracking, Question Answering |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1528/ |
| https://www.aclweb.org/anthology/D18-1528 | |
| PWC | https://paperswithcode.com/paper/classifying-referential-and-non-referential |
| Repo | |
| Framework | |
A Lexical Tool for Academic Writing in Spanish based on Expert and Novice Corpora
| Title | A Lexical Tool for Academic Writing in Spanish based on Expert and Novice Corpora |
| Authors | Marcos Garc{'\i}a Salido, Marcos Garc{'\i}a, Villay, Milka re-Llamazares, Margarita Alonso-Ramos |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1039/ |
| https://www.aclweb.org/anthology/L18-1039 | |
| PWC | https://paperswithcode.com/paper/a-lexical-tool-for-academic-writing-in |
| Repo | |
| Framework | |
Alibaba Submission for WMT18 Quality Estimation Task
| Title | Alibaba Submission for WMT18 Quality Estimation Task |
| Authors | Jiayi Wang, Kai Fan, Bo Li, Fengming Zhou, Boxing Chen, Yangbin Shi, Luo Si |
| Abstract | The goal of WMT 2018 Shared Task on Translation Quality Estimation is to investigate automatic methods for estimating the quality of machine translation results without reference translations. This paper presents the QE Brain system, which proposes the neural Bilingual Expert model as a feature extractor based on conditional target language model with a bidirectional transformer and then processes the semantic representations of source and the translation output with a Bi-LSTM predictive model for automatic quality estimation. The system has been applied to the sentence-level scoring and ranking tasks as well as the word-level tasks for finding errors for each word in translations. An extensive set of experimental results have shown that our system outperformed the best results in WMT 2017 Quality Estimation tasks and obtained top results in WMT 2018. |
| Tasks | Automatic Post-Editing, Language Modelling, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6465/ |
| https://www.aclweb.org/anthology/W18-6465 | |
| PWC | https://paperswithcode.com/paper/alibaba-submission-for-wmt18-quality |
| Repo | |
| Framework | |
Towards a Computational Lexicon for Moroccan Darija: Words, Idioms, and Constructions
| Title | Towards a Computational Lexicon for Moroccan Darija: Words, Idioms, and Constructions |
| Authors | Jamal Laoudi, Claire Bonial, Lucia Donatelli, Stephen Tratz, Clare Voss |
| Abstract | In this paper, we explore the challenges of building a computational lexicon for Moroccan Darija (MD), an Arabic dialect spoken by over 32 million people worldwide but which only recently has begun appearing frequently in written form in social media. We raise the question of what belongs in such a lexicon and start by describing our work building traditional word-level lexicon entries with their English translations. We then discuss challenges in translating idiomatic MD text that led to creating multi-word expression lexicon entries whose meanings could not be fully derived from the individual words. Finally, we provide a preliminary exploration of constructions to be considered for inclusion in an MD constructicon by translating examples of English constructions and examining their MD counterparts. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4910/ |
| https://www.aclweb.org/anthology/W18-4910 | |
| PWC | https://paperswithcode.com/paper/towards-a-computational-lexicon-for-moroccan |
| Repo | |
| Framework | |
Extracting Entities and Relations with Joint Minimum Risk Training
| Title | Extracting Entities and Relations with Joint Minimum Risk Training |
| Authors | Changzhi Sun, Yuanbin Wu, Man Lan, Shiliang Sun, Wenting Wang, Kuang-Chih Lee, Kewen Wu |
| Abstract | We investigate the task of joint entity relation extraction. Unlike prior efforts, we propose a new lightweight joint learning paradigm based on minimum risk training (MRT). Specifically, our algorithm optimizes a global loss function which is flexible and effective to explore interactions between the entity model and the relation model. We implement a strong and simple neural network where the MRT is executed. Experiment results on the benchmark ACE05 and NYT datasets show that our model is able to achieve state-of-the-art joint extraction performances. |
| Tasks | Relation Extraction |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1249/ |
| https://www.aclweb.org/anthology/D18-1249 | |
| PWC | https://paperswithcode.com/paper/extracting-entities-and-relations-with-joint |
| Repo | |
| Framework | |
A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation
| Title | A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation |
| Authors | Kang Wang, Rui Zhao, Qiang Ji |
| Abstract | In this work, we introduce a Hierarchical Generative Model (HGM) to enable realistic forward eye image synthe- sis, as well as effective backward eye gaze estimation. The proposed HGM consists of a hierarchical generative shape model (HGSM), and a conditional bidirectional generative adversarial network (c-BiGAN). The HGSM encodes eye ge- ometry knowledge and relates eye gaze with eye shape, while c-BiGAN leverages on big data and captures the dependency between eye shape and eye appearance. As an intermedi- ate component, eye shape connects knowledge-based model (HGSM) with data-driven model (c-BiGAN) and enables bidirectional inference. Through a top-down inference, the HGM can synthesize eye images consistent with the given eye gaze. Through a bottom-up inference, HGM can infer eye gaze effectively from a given eye image. Qualitative and quantitative evaluations on benchmark datasets demonstrate our modelâs effectiveness on both eye image synthesis and eye gaze estimation. In addition, the proposed model is not restricted to eye images only. It can be adapted to face images and any shape-appearance related fields. |
| Tasks | Gaze Estimation, Image Generation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_A_Hierarchical_Generative_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_A_Hierarchical_Generative_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-generative-model-for-eye-image |
| Repo | |
| Framework | |
