@Book{W18-40:2018, editor = {Luis Espinosa Anke and Dagmar Gromann and Thierry Declerck}, title = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, url = {http://www.aclweb.org/anthology/W18-40} } @InProceedings{gupta-andrassy-schtze:2018:W18-40, author = {Gupta, Pankaj and Andrassy, Bernt and Schütze, Hinrich}, title = {Replicated Siamese LSTM in Ticketing System for Similarity Learning and Retrieval in Asymmetric Texts}, booktitle = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, pages = {1--11}, abstract = {The goal of our industrial ticketing system is to retrieve a relevant solution for an input query, by matching with historical tickets stored in knowledge base. A query is comprised of subject and description, while a historical ticket consists of subject, description and solution. To retrieve a relevant solution, we use textual similarity paradigm to learn similarity in the query and historical tickets. The task is challenging due to significant term mismatch in the query and ticket pairs of asymmetric lengths, where subject is a short text but description and solution are multi-sentence texts. We present a novel Replicated Siamese LSTM model to learn similarity in asymmetric text pairs, that gives 22% and 7% gain (Accuracy$@$10) for retrieval task, respectively over unsupervised and supervised baselines. We also show that the topic and distributed semantic features for short and long texts improved both similarity learning and retrieval.}, url = {http://www.aclweb.org/anthology/W18-4001} } @InProceedings{yoon-EtAl:2018:W18-40, author = {Yoon, Su-Youn and Loukina, Anastassia and Lee, Chong Min and Mulholland, Matthew and Wang, Xinhao and Choi, Ikkyu}, title = {Word-Embedding based Content Features for Automated Oral Proficiency Scoring}, booktitle = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, pages = {12--22}, abstract = {In this study, we develop content features for an automated scoring system of non-native English speakers' spontaneous speech. The features calculate the lexical similarity between the question text and the ASR word hypothesis of the spoken response, based on traditional word vector models or word embeddings. The proposed features do not require any sample training responses for each question, and this is a strong advantage since collecting question-specific data is an expensive task, and sometimes even impossible due to concerns about question exposure. We explore the impact of these new features on the automated scoring of two different question types: (a) providing opinions on familiar topics and (b) answering a question about a stimulus material. The proposed features showed statistically significant correlations with the oral proficiency scores, and the combination of new features with the speech-driven features achieved a small but significant further improvement for the latter question type. Further analyses suggested that the new features were effective in assigning more accurate scores for responses with serious content issues.}, url = {http://www.aclweb.org/anthology/W18-4002} } @InProceedings{nietopia-johansson:2018:W18-40, author = {Nieto Piña, Luis and Johansson, Richard}, title = {Automatically Linking Lexical Resources with Word Sense Embedding Models}, booktitle = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, pages = {23--29}, abstract = {Automatically learnt word sense embeddings are developed as an attempt to refine the capabilities of coarse word embeddings. The word sense representations obtained this way are, however, sensitive to underlying corpora and parameterizations, and they might be difficult to relate to formally defined word senses. We propose to tackle this problem by devising a mechanism to establish links between word sense embeddings and lexical resources created by experts. We evaluate the applicability of these links in a task to retrieve instances of word sense unlisted in the lexicon.}, url = {http://www.aclweb.org/anthology/W18-4003} } @InProceedings{ezeani-onyenwe-hepple:2018:W18-40, author = {Ezeani, Ignatius and Onyenwe, Ikechukwu and Hepple, Mark}, title = {Transferred Embeddings for Igbo Similarity, Analogy, and Diacritic Restoration Tasks}, booktitle = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, pages = {30--38}, abstract = {Existing NLP models are mostly trained with data from well-resourced languages. Most minority languages face the challenge of lack of resources - data and technologies - for NLP research. Building these resources from scratch for each minority language will be very expensive, time-consuming and amount largely to unnecessarily re-inventing the wheel. In this paper, we applied transfer learning techniques to create Igbo word embeddings from a variety of existing English trained embeddings. Transfer learning methods were also used to build standard datasets for Igbo word similarity and analogy tasks for intrinsic evaluation of embeddings. These projected embeddings were also applied to diacritic restoration task. Our results indicate that the projected models not only outperform the trained ones on the semantic-based tasks of analogy, word-similarity, and odd-word identifying, but they also achieve enhanced performance on the diacritic restoration with learned diacritic embeddings.}, url = {http://www.aclweb.org/anthology/W18-4004} } @InProceedings{parupalli-anveshrao-mamidi:2018:W18-40, author = {Parupalli, Sreekavitha and Anvesh Rao, Vijjini and Mamidi, Radhika}, title = {Towards Enhancing Lexical Resource and Using Sense-annotations of OntoSenseNet for Sentiment Analysis}, booktitle = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, pages = {39--44}, abstract = {This paper illustrates the interface of the tool we developed for crowd sourcing and we explain the annotation procedure in detail. Our tool is named as 'పారుపల్లి పదజాలం' (Parupalli Padajaalam) which means web of words by Parupalli. The aim of this tool is to populate the OntoSenseNet, sentiment polarity annotated Telugu resource. Recent works have shown the importance of word-level annotations on sentiment analysis. With this as basis, we aim to analyze the importance of sense-annotations obtained from OntoSenseNet in performing the task of sentiment analysis. We explain the features extracted from OntoSenseNet (Telugu). Furthermore we compute and explain the adverbial class distribution of verbs in OntoSenseNet. This task is known to aid in disambiguating word-senses which helps in enhancing the performance of word-sense disambiguation (WSD) task(s).}, url = {http://www.aclweb.org/anthology/W18-4005} } @InProceedings{schockaert:2018:W18-40, author = {Schockaert, Steven}, title = {Knowledge Representation with Conceptual Spaces}, booktitle = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, pages = {45}, abstract = {}, url = {http://www.aclweb.org/anthology/W18-4006} } @InProceedings{christodoulopoulos:2018:W18-40, author = {Christodoulopoulos, Christos}, title = {Knowledge Representation and Extraction at Scale}, booktitle = {Proceedings of the Third Workshop on Semantic Deep Learning}, month = {August}, year = {2018}, address = {Santa Fe, New Mexico}, publisher = {Association for Computational Linguistics}, pages = {46}, abstract = {}, url = {http://www.aclweb.org/anthology/W18-4007} }