Below is the list of the abstracts accepted to the 2018 WiNLP workshop. Congratulations to all authors!
WiNLP is non-archival. Abstracts will be made available through a short period under certain restrictions. Please contact the authors directly if you are interested in the abstract. Full text will be uploaded shortly.
- Luganda Text-to-Speech Machine. Irene Nandutu and Ernest Mwebaze
- Context-Sensitive Normalization of Social Media Text in Bahasa Indonesia Based on Neural Word Embeddings. Renny Pradina Kusumawardani and Stezar Priansya
- Churn Prediction Using Structured Logical Knowledge and Convolutional Neural Networks. Mourad Gridach and Hatem Haddad
- A Novel Post-editing Algorithm to Optimize Amharic Speech Recognition for Speech Translation. Michael Melese, Laurent Besacier and Million Meshesha
- Building on Word Animacy to Determine Coreference Chain Animacy in Cultural Narratives. Labiba Jahan, Geeticka Chauhan and Mark A. Finlayson
- Neural Morphological Segmentation for Polysynthetic Minimal-Resource Languages. Katharina Kann, Manuel Mager, Ivan Vladimir Meza Ruiz and Hinrich Schütze
- Empirical Evaluation of Preprocessing for Tunisian Dialect (Darija) Sentiment Analysis. Hatem Haddad and Hala Mulki
- Human vs Automatic Metrics: on the Importance of Correlation Design. Anastasia Shimorina
- Sentence Level Amharic Text Sentiment Analysis Model: A Combined Approach. Bitseat Aragaw, Tensae Ayalew and Tibebe Beshah
- Development of Pronunciation Lexicons for Amharic Automatic Speech Recognition (ASR). Martha Yifiru Tachbelie and Solomon Teferra Abate
- Neural Network-based Model for Named Entity Recognition in Low-Resource Settings. Ngoc Tan Le, Hong Buu Long Nguyen and Fatiha Sadat
- Data Adaptation for Named Entity Recognition in Twitter with Features-Rich CRF. Ngoc Tan Le, Fatiha Sadat and Damien Nouvel
- Linguistic Accommodation and Codeswitching in Conversation. Rouzbeh Shirvani, Mario Piergallini, Amirsina Torfi, Mugizi Rwebangira and Mohamed Chouikha
- Improving Zero-Shot Translation of Low-Resource Languages. Surafel Melaku Lakew, Quintino Francesco Lotito, Matteo Negri, Marco Turchi and Marcello Federico
- Emotionality in Patients and Therapists speaking German. Margot Mieskes and Svetlana Shutyi
- Concept Linking in Medical Domain for Social Media Posts Using RNNs. Elena Tutubalina, Zulfat Miftahutdinov and Valentin Malykh
- Predicting Glosses in Interlinear Glossed Text. Angelina McMillan-Major
- The Entrainment of Creaky Voice in Spoken Dialogue. Courtney Mansfield
- NeuroSign: a Seq2Seq Model Proposal for Sign Language Translation. Héctor Ricardo Murrieta Bello and Ivan Vladimir Meza Ruiz
- Multimodal Multilingual Representation Learning. Spandana Gella
- #MeToo Alexa: Sexual Harassment and Conversational AI. Amanda Cercas Curry and Verena Rieser
- #MeToo: Neural Detection and Explanation of Language in Personal Abuse Stories. Sweta Karlekar and Mohit Bansal
- Text Mining of Student Generated Content for Culturally Relevant Pedagogies in Data Science. Jaye Nias
- A Corpus for the Analysis of Online News Comments. Varada Kolhatkar and Maite Taboada
- Modeling of Policy Frames for Morality Detection on Twitter. Kristen Johnson and Dan Goldwasser
- Longer Acoustic Units for Amharic Speech Recognition. Adey Edessa and Martha Yifiru
- A Framework for Suggestion Mining from Vietnamese Conversational Texts. Thi Lan Ngo and Pham Khac Linh
- Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT. Marianna Martindale and Marine Carpuat
- Multi-label Element Extraction for Evidence-Based Medicine. Amandalynne Paullada, Ebrahim al-Safadi, Malhar Jhaveri, and Xiang Li
- Creating and Annotating a Corpus of Health Coaching Dialogue. Itika Gupta, Barbara Di Eugenio, Brian Ziebart, Bing Liu, Ben Gerber, Lisa Sharp, Rafe Davis and Aiswarya Baiju
- Using Machine Learning to Detect Potential Child Suicide Bombers. Francisca Oladipo and Haruna Abdu
- Learning Diacritic Embeddings. Ignatius Ezeani, Ikechukwu Onyenwe, Mark Hepple and Enemouh Chioma
- Transfer between Disparate Labels with Weak Supervision. Rasha Obeidat, Xiaoli Fern and Prasad Tadepalli
- Unsupervised Sentence Embeddings for Answer Summarization in Non-factoid CQA. Thi-Thanh Ha, Nguyen Thanh-Chinh, Nguyen Kiem-Hieu and Vu Van-Chung
- New Entity Identification Approaches in Entity Linking Systems. Priya Radhakrishnan, Manish Gupta and Vasudeva Varma
- A finite-state morphological analyzer for Wolaytta. Tewodros Gebreselassie
- Exploring Morphology Learning of Igbo with Different Degrees of Supervision. Enemouh Chioma, Ignatius Ezeani, Mark Hepple and Ikechukwu Onyenwe
- Comparing the Performance of Crowdworkers and NLP Tools on Named-Entity Recognition and Entity-Level Sentiment Analysis of Political Tweets. Mona Jalal, Kate K. Mays, Lei Guo and Margrit Betke
- Implicit and Explicit Information for Categorization. Felipe Paula, Rodrigo Wilkens, Marco Idiart and Aline Villavicencio
- Computational Analysis of Polarity in Poetry. Navjyoti Singh and Amitha Gopidi
- Differences in the Acquisition of Polysemy vs. Ambiguity. Sammy Floyd, Libby Barak and Adele Goldberg
- Language Models for Brain Computer Interface as Augmentative and Alternative Communication. Shiran Dudy, Steven Bedrick, David Smith and Shaobin Xu
- Lightweight Word-Level Confidence Estimation for Neural Interactive Translation Prediction. Rebecca Knowles and Philipp Koehn
- Hierarchical Neural Model for Tagging Address Queries in Map Search. Shekoofeh Mokhtari, Ning Xie and Dragomir Yankov
- Sentiment Based Word Substitutions to Generate Humorous Phrases in Hindi. Srishti Aggarwal, Kritik Mathur and Radhika Mamidi
- Faster Pace in Human-Robot Dialogue Leads to Fewer Dialogue Overlaps. Cassidy Henry, Carla Gordon, David Traum, Stephanie Lukin, Kimberly A. Pollard, Ron Artstein, Claire Bonial, Clare Voss, Ashley Foots and Matthew Marge
- A Formal Ontology-Based Classification of Lexemes and its Applications. Sreekavitha Parupalli and Navjyoti Singh
- Cross-Situational Word Learning under Uncertainty: an Algorithmic-Level Analysis. Aida Nematzadeh, Zahra Shekarchi and Suzanne Stevenson
- Generating Creative Restaurant Descriptions from User Reviews. Shereen Oraby and Marilyn Walker
- Learning Lexico-Functional Patterns for First-Person Affect. Lena Reed and Marilyn Walker
- Building a NLI Corpus for Portuguese. Livy Real, Valeria dePaiva, Bruno Guide, Bruna Thalenberg, Cindy Silva, Guilherme Oliveira Lima, Ana Rodrigues, Beatriz Albiero, Rodrigo Souza and Igor de Camargo e Souza Câmara
- Incorporating Subword Information into Matrix Factorization Word Embeddings. Alexandre Salle and Aline Villavicencio
- WitWise: A funny proverb generator. Geetanjali Rakshit