Paper Group NANR 203
![Paper Group NANR 203](/2016/images/pwc/paper-all_hu5eb227011acad6b922a57ded5f50b7dc_25576_900x500_fit_q75_box.jpg)
Exploring the Realization of Irony in Twitter Data. Text-attentional convolutional neural network for scene text detection. DT-Neg: Tutorial Dialogues Annotated for Negation Scope and Focus in Context. Appraising UMLS Coverage for Summarizing Medical Evidence. Toward incremental dialogue act segmentation in fast-paced interactive dialogue systems. …
Exploring the Realization of Irony in Twitter Data
Title | Exploring the Realization of Irony in Twitter Data |
Authors | Cynthia Van Hee, Els Lefever, V{'e}ronique Hoste |
Abstract | Handling figurative language like irony is currently a challenging task in natural language processing. Since irony is commonly used in user-generated content, its presence can significantly undermine accurate analysis of opinions and sentiment in such texts. Understanding irony is therefore important if we want to push the state-of-the-art in tasks such as sentiment analysis. In this research, we present the construction of a Twitter dataset for two languages, being English and Dutch, and the development of new guidelines for the annotation of verbal irony in social media texts. Furthermore, we present some statistics on the annotated corpora, from which we can conclude that the detection of contrasting evaluations might be a good indicator for recognizing irony. |
Tasks | Sentiment Analysis |
Published | 2016-05-01 |
URL | https://www.aclweb.org/anthology/L16-1283/ |
https://www.aclweb.org/anthology/L16-1283 | |
PWC | https://paperswithcode.com/paper/exploring-the-realization-of-irony-in-twitter |
Repo | |
Framework | |
Text-attentional convolutional neural network for scene text detection
Title | Text-attentional convolutional neural network for scene text detection |
Authors | Tong He, Weilin Huang, Yu Qiao, Jian Yao |
Abstract | Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature computed globally from a whole image component (patch), where the cluttered background information may dominate true text features in the deep representation. This leads to less discriminative power and poorer robustness. In this work, we present a new system for scene text detection by proposing a novel Text-Attentional Convolutional Neural Network (Text-CNN) that particularly focuses on extracting text-related regions and features from the image components. We develop a new learning mechanism to train the Text-CNN with multi-level and rich supervised information, including text region mask, character label, and binary text/nontext information. The rich supervision information enables the Text CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components. The training process is formulated as a multi-task learning problem, where low-level supervised information greatly facilitates main task of text/non-text classification. In addition, a powerful low-level detector called ContrastEnhancement Maximally Stable Extremal Regions (CE-MSERs) is developed, which extends the widely-used MSERs by enhancing intensity contrast between text patterns and background. This allows it to detect highly challenging text patterns, resulting in a higher recall. Our approach achieved promising results on the ICDAR 2013 dataset, with a F-measure of 0.82, improving the state-of-the-art results substantially. |
Tasks | Multi-Task Learning, Scene Text Detection, Text Classification |
Published | 2016-03-24 |
URL | https://arxiv.org/abs/1510.03283 |
https://arxiv.org/pdf/1510.03283.pdf | |
PWC | https://paperswithcode.com/paper/text-attentional-convolutional-neural-network |
Repo | |
Framework | |
DT-Neg: Tutorial Dialogues Annotated for Negation Scope and Focus in Context
Title | DT-Neg: Tutorial Dialogues Annotated for Negation Scope and Focus in Context |
Authors | Rajendra Banjade, Vasile Rus |
Abstract | Negation is often found more frequent in dialogue than commonly written texts, such as literary texts. Furthermore, the scope and focus of negation depends on context in dialogues than other forms of texts. Existing negation datasets have focused on non-dialogue texts such as literary texts where the scope and focus of negation is normally present within the same sentence where the negation is located and therefore are not the most appropriate to inform the development of negation handling algorithms for dialogue-based systems. In this paper, we present DT -Neg corpus (DeepTutor Negation corpus) which contains texts extracted from tutorial dialogues where students interacted with an Intelligent Tutoring System (ITS) to solve conceptual physics problems. The DT -Neg corpus contains annotated negations in student responses with scope and focus marked based on the context of the dialogue. Our dataset contains 1,088 instances and is available for research purposes at http://language.memphis.edu/dt-neg. |
Tasks | |
Published | 2016-05-01 |
URL | https://www.aclweb.org/anthology/L16-1597/ |
https://www.aclweb.org/anthology/L16-1597 | |
PWC | https://paperswithcode.com/paper/dt-neg-tutorial-dialogues-annotated-for |
Repo | |
Framework | |
Appraising UMLS Coverage for Summarizing Medical Evidence
Title | Appraising UMLS Coverage for Summarizing Medical Evidence |
Authors | Elaheh ShafieiBavani, Mohammad Ebrahimi, Raymond Wong, Fang Chen |
Abstract | When making clinical decisions, practitioners need to rely on the most relevant evidence available. However, accessing a vast body of medical evidence and confronting with the issue of information overload can be challenging and time consuming. This paper proposes an effective summarizer for medical evidence by utilizing both UMLS and WordNet. Given a clinical query and a set of relevant abstracts, our aim is to generate a fluent, well-organized, and compact summary that answers the query. Analysis via ROUGE metrics shows that using WordNet as a general-purpose lexicon helps to capture the concepts not covered by the UMLS Metathesaurus, and hence significantly increases the performance. The effectiveness of our proposed approach is demonstrated by conducting a set of experiments over a specialized evidence-based medicine (EBM) corpus - which has been gathered and annotated for the purpose of biomedical text summarization. |
Tasks | Text Summarization |
Published | 2016-12-01 |
URL | https://www.aclweb.org/anthology/C16-1050/ |
https://www.aclweb.org/anthology/C16-1050 | |
PWC | https://paperswithcode.com/paper/appraising-umls-coverage-for-summarizing |
Repo | |
Framework | |
Toward incremental dialogue act segmentation in fast-paced interactive dialogue systems
Title | Toward incremental dialogue act segmentation in fast-paced interactive dialogue systems |
Authors | Ramesh Manuvinakurike, Maike Paetzel, Cheng Qu, David Schlangen, David DeVault |
Abstract | |
Tasks | Spoken Dialogue Systems |
Published | 2016-09-01 |
URL | https://www.aclweb.org/anthology/W16-3632/ |
https://www.aclweb.org/anthology/W16-3632 | |
PWC | https://paperswithcode.com/paper/toward-incremental-dialogue-act-segmentation |
Repo | |
Framework | |
Supporting Spoken Assistant Systems with a Graphical User Interface that Signals Incremental Understanding and Prediction State
Title | Supporting Spoken Assistant Systems with a Graphical User Interface that Signals Incremental Understanding and Prediction State |
Authors | Casey Kennington, David Schlangen |
Abstract | |
Tasks | Slot Filling, Spoken Dialogue Systems |
Published | 2016-09-01 |
URL | https://www.aclweb.org/anthology/W16-3631/ |
https://www.aclweb.org/anthology/W16-3631 | |
PWC | https://paperswithcode.com/paper/supporting-spoken-assistant-systems-with-a |
Repo | |
Framework | |
Proceedings of ACL-2016 System Demonstrations
Title | Proceedings of ACL-2016 System Demonstrations |
Authors | |
Abstract | |
Tasks | |
Published | 2016-08-01 |
URL | https://www.aclweb.org/anthology/P16-4000/ |
https://www.aclweb.org/anthology/P16-4000 | |
PWC | https://paperswithcode.com/paper/proceedings-of-acl-2016-system-demonstrations |
Repo | |
Framework | |
Language Related Issues for Machine Translation between Closely Related South Slavic Languages
Title | Language Related Issues for Machine Translation between Closely Related South Slavic Languages |
Authors | Maja Popovi{'c}, Mihael Ar{\v{c}}an, Filip Klubi{\v{c}}ka |
Abstract | Machine translation between closely related languages is less challenging and exibits a smaller number of translation errors than translation between distant languages, but there are still obstacles which should be addressed in order to improve such systems. This work explores the obstacles for machine translation systems between closely related South Slavic languages, namely Croatian, Serbian and Slovenian. Statistical systems for all language pairs and translation directions are trained using parallel texts from different domains, however mainly on spoken language i.e. subtitles. For translation between Serbian and Croatian, a rule-based system is also explored. It is shown that for all language pairs and translation systems, the main obstacles are differences between structural properties. |
Tasks | Machine Translation |
Published | 2016-12-01 |
URL | https://www.aclweb.org/anthology/W16-4806/ |
https://www.aclweb.org/anthology/W16-4806 | |
PWC | https://paperswithcode.com/paper/language-related-issues-for-machine |
Repo | |
Framework | |
Keynote - Modeling Human Communication Dynamics
Title | Keynote - Modeling Human Communication Dynamics |
Authors | Louis-Philippe Morency |
Abstract | |
Tasks | Opinion Mining |
Published | 2016-09-01 |
URL | https://www.aclweb.org/anthology/W16-3633/ |
https://www.aclweb.org/anthology/W16-3633 | |
PWC | https://paperswithcode.com/paper/keynote-modeling-human-communication-dynamics |
Repo | |
Framework | |
Reference Resolution in Situated Dialogue with Learned Semantics
Title | Reference Resolution in Situated Dialogue with Learned Semantics |
Authors | Xiaolong Li, Kristy Boyer |
Abstract | |
Tasks | |
Published | 2016-09-01 |
URL | https://www.aclweb.org/anthology/W16-3642/ |
https://www.aclweb.org/anthology/W16-3642 | |
PWC | https://paperswithcode.com/paper/reference-resolution-in-situated-dialogue |
Repo | |
Framework | |
QU-IR at SemEval 2016 Task 3: Learning to Rank on Arabic Community Question Answering Forums with Word Embedding
Title | QU-IR at SemEval 2016 Task 3: Learning to Rank on Arabic Community Question Answering Forums with Word Embedding |
Authors | Rana Malhas, Marwan Torki, Tamer Elsayed |
Abstract | |
Tasks | Community Question Answering, Learning-To-Rank, Question Answering |
Published | 2016-06-01 |
URL | https://www.aclweb.org/anthology/S16-1134/ |
https://www.aclweb.org/anthology/S16-1134 | |
PWC | https://paperswithcode.com/paper/qu-ir-at-semeval-2016-task-3-learning-to-rank |
Repo | |
Framework | |
Weighting Finite-State Transductions With Neural Context
Title | Weighting Finite-State Transductions With Neural Context |
Authors | Pushpendre Rastogi, Ryan Cotterell, Jason Eisner |
Abstract | |
Tasks | Lemmatization, Structured Prediction, Transliteration |
Published | 2016-06-01 |
URL | https://www.aclweb.org/anthology/N16-1076/ |
https://www.aclweb.org/anthology/N16-1076 | |
PWC | https://paperswithcode.com/paper/weighting-finite-state-transductions-with |
Repo | |
Framework | |
Direct vs. indirect evaluation of distributional thesauri
Title | Direct vs. indirect evaluation of distributional thesauri |
Authors | Vincent Claveau, Ewa Kijak |
Abstract | With the success of word embedding methods in various Natural Language Processing tasks, all the field of distributional semantics has experienced a renewed interest. Beside the famous word2vec, recent studies have presented efficient techniques to build distributional thesaurus; in particular, Claveau et al. (2014) have already shown that Information Retrieval (IR) tools and concepts can be successfully used to build a thesaurus. In this paper, we address the problem of the evaluation of such thesauri or embedding models and compare their results. Through several experiments and by evaluating directly the results with reference lexicons, we show that the recent IR-based distributional models outperform state-of-the-art systems such as word2vec. Following the work of Claveau and Kijak (2016), we use IR as an applicative framework to indirectly evaluate the generated thesaurus. Here again, this task-based evaluation validates the IR approach used to build the thesaurus. Moreover, it allows us to compare these results with those from the direct evaluation framework used in the literature. The observed differences bring these evaluation habits into question. |
Tasks | Information Retrieval |
Published | 2016-12-01 |
URL | https://www.aclweb.org/anthology/C16-1173/ |
https://www.aclweb.org/anthology/C16-1173 | |
PWC | https://paperswithcode.com/paper/direct-vs-indirect-evaluation-of |
Repo | |
Framework | |
Inner Attention based Recurrent Neural Networks for Answer Selection
Title | Inner Attention based Recurrent Neural Networks for Answer Selection |
Authors | Bingning Wang, Kang Liu, Jun Zhao |
Abstract | |
Tasks | Answer Selection, Machine Translation, Open-Domain Question Answering, Question Answering |
Published | 2016-08-01 |
URL | https://www.aclweb.org/anthology/P16-1122/ |
https://www.aclweb.org/anthology/P16-1122 | |
PWC | https://paperswithcode.com/paper/inner-attention-based-recurrent-neural |
Repo | |
Framework | |
SLS at SemEval-2016 Task 3: Neural-based Approaches for Ranking in Community Question Answering
Title | SLS at SemEval-2016 Task 3: Neural-based Approaches for Ranking in Community Question Answering |
Authors | Mitra Mohtarami, Yonatan Belinkov, Wei-Ning Hsu, Yu Zhang, Tao Lei, Kfir Bar, Scott Cyphers, Jim Glass |
Abstract | |
Tasks | Answer Selection, Community Question Answering, Question Answering, Question Similarity, Semantic Textual Similarity |
Published | 2016-06-01 |
URL | https://www.aclweb.org/anthology/S16-1128/ |
https://www.aclweb.org/anthology/S16-1128 | |
PWC | https://paperswithcode.com/paper/sls-at-semeval-2016-task-3-neural-based |
Repo | |
Framework | |