Paper Group NANR 62
Distribution of Emotional Reactions to News Articles in Twitter. Neural Multitask Learning for Simile Recognition. Clinical Skin Lesion Diagnosis Using Representations Inspired by Dermatologist Criteria. Integrating Generative Lexicon Event Structures into VerbNet. Tailored Sequence to Sequence Models to Different Conversation Scenarios. NegPar: A …
Distribution of Emotional Reactions to News Articles in Twitter
Title | Distribution of Emotional Reactions to News Articles in Twitter |
Authors | Omar Ju{'a}rez Gambino, Hiram Calvo, Consuelo-Varinia Garc{'\i}a-Mendoza |
Abstract | |
Tasks | Sentiment Analysis, Twitter Sentiment Analysis |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1225/ |
https://www.aclweb.org/anthology/L18-1225 | |
PWC | https://paperswithcode.com/paper/distribution-of-emotional-reactions-to-news |
Repo | |
Framework | |
Neural Multitask Learning for Simile Recognition
Title | Neural Multitask Learning for Simile Recognition |
Authors | Lizhen Liu, Xiao Hu, Wei Song, Ruiji Fu, Ting Liu, Guoping Hu |
Abstract | Simile is a special type of metaphor, where comparators such as like and as are used to compare two objects. Simile recognition is to recognize simile sentences and extract simile components, i.e., the tenor and the vehicle. This paper presents a study of simile recognition in Chinese. We construct an annotated corpus for this research, which consists of 11.3k sentences that contain a comparator. We propose a neural network framework for jointly optimizing three tasks: simile sentence classification, simile component extraction and language modeling. The experimental results show that the neural network based approaches can outperform all rule-based and feature-based baselines. Both simile sentence classification and simile component extraction can benefit from multitask learning. The former can be solved very well, while the latter is more difficult. |
Tasks | Language Modelling, Sentence Classification |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1183/ |
https://www.aclweb.org/anthology/D18-1183 | |
PWC | https://paperswithcode.com/paper/neural-multitask-learning-for-simile |
Repo | |
Framework | |
Clinical Skin Lesion Diagnosis Using Representations Inspired by Dermatologist Criteria
Title | Clinical Skin Lesion Diagnosis Using Representations Inspired by Dermatologist Criteria |
Authors | Jufeng Yang, Xiaoxiao Sun, Jie Liang, Paul L. Rosin |
Abstract | The skin is the largest organ in human body. Around 30%-70% of individuals worldwide have skin related health problems, for whom effective and efficient diagnosis is necessary. Recently, computer aided diagnosis (CAD) systems have been successfully applied to the recognition of skin cancers in dermatoscopic images. However, little work has concentrated on the commonly encountered skin diseases in clinical images captured by easily-accessed cameras or mobile phones. Meanwhile, for a CAD system, the representations of skin lesions are required to be understandable for dermatologists so that the predictions are convincing. To address this problem, we present effective representations inspired by the accepted dermatological criteria for diagnosing clinical skin lesions. We demonstrate that the dermatological criteria are highly correlated with measurable visual components. Accordingly, we design six medical representations considering different criteria for the recognition of skin lesions, and construct a diagnosis system for clinical skin disease images. Experimental results show that the proposed medical representations can not only capture the manifestations of skin lesions effectively, and consistently with the dermatological criteria, but also improve the prediction performance with respect to the state-of-the-art methods based on uninterpretable features. |
Tasks | |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Yang_Clinical_Skin_Lesion_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Clinical_Skin_Lesion_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/clinical-skin-lesion-diagnosis-using |
Repo | |
Framework | |
Integrating Generative Lexicon Event Structures into VerbNet
Title | Integrating Generative Lexicon Event Structures into VerbNet |
Authors | Susan Windisch Brown, James Pustejovsky, Annie Zaenen, Martha Palmer |
Abstract | |
Tasks | Semantic Parsing, Semantic Role Labeling |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1009/ |
https://www.aclweb.org/anthology/L18-1009 | |
PWC | https://paperswithcode.com/paper/integrating-generative-lexicon-event |
Repo | |
Framework | |
Tailored Sequence to Sequence Models to Different Conversation Scenarios
Title | Tailored Sequence to Sequence Models to Different Conversation Scenarios |
Authors | Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xueqi Cheng |
Abstract | Sequence to sequence (Seq2Seq) models have been widely used for response generation in the area of conversation. However, the requirements for different conversation scenarios are distinct. For example, customer service requires the generated responses to be specific and accurate, while chatbot prefers diverse responses so as to attract different users. The current Seq2Seq model fails to meet these diverse requirements, by using a general average likelihood as the optimization criteria. As a result, it usually generates safe and commonplace responses, such as {`}I don{'}t know{'}. In this paper, we propose two tailored optimization criteria for Seq2Seq to different conversation scenarios, i.e., the maximum generated likelihood for specific-requirement scenario, and the conditional value-at-risk for diverse-requirement scenario. Experimental results on the Ubuntu dialogue corpus (Ubuntu service scenario) and Chinese Weibo dataset (social chatbot scenario) show that our proposed models not only satisfies diverse requirements for different scenarios, but also yields better performances against traditional Seq2Seq models in terms of both metric-based and human evaluations. | |
Tasks | Chatbot, Dialogue Generation |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-1137/ |
https://www.aclweb.org/anthology/P18-1137 | |
PWC | https://paperswithcode.com/paper/tailored-sequence-to-sequence-models-to |
Repo | |
Framework | |
NegPar: A parallel corpus annotated for negation
Title | NegPar: A parallel corpus annotated for negation |
Authors | Qianchu Liu, Federico Fancellu, Bonnie Webber |
Abstract | |
Tasks | Machine Translation, Negation Detection, Sentiment Analysis, Word Alignment |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1547/ |
https://www.aclweb.org/anthology/L18-1547 | |
PWC | https://paperswithcode.com/paper/negpar-a-parallel-corpus-annotated-for |
Repo | |
Framework | |
An Empirical Study on Fine-Grained Named Entity Recognition
Title | An Empirical Study on Fine-Grained Named Entity Recognition |
Authors | Khai Mai, Thai-Hoang Pham, Minh Trung Nguyen, Tuan Duc Nguyen, Danushka Bollegala, Ryohei Sasano, Satoshi Sekine |
Abstract | Named entity recognition (NER) has attracted a substantial amount of research. Recently, several neural network-based models have been proposed and achieved high performance. However, there is little research on fine-grained NER (FG-NER), in which hundreds of named entity categories must be recognized, especially for non-English languages. It is still an open question whether there is a model that is robust across various settings or the proper model varies depending on the language, the number of named entity categories, and the size of training datasets. This paper first presents an empirical comparison of FG-NER models for English and Japanese and demonstrates that LSTM+CNN+CRF (Ma and Hovy, 2016), one of the state-of-the-art methods for English NER, also works well for English FG-NER but does not work well for Japanese, a language that has a large number of character types. To tackle this problem, we propose a method to improve the neural network-based Japanese FG-NER performance by removing the CNN layer and utilizing dictionary and category embeddings. Experiment results show that the proposed method improves Japanese FG-NER F-score from 66.76{%} to 75.18{%}. |
Tasks | Chatbot, Named Entity Recognition |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1060/ |
https://www.aclweb.org/anthology/C18-1060 | |
PWC | https://paperswithcode.com/paper/an-empirical-study-on-fine-grained-named |
Repo | |
Framework | |
The Importance of Calibration for Estimating Proportions from Annotations
Title | The Importance of Calibration for Estimating Proportions from Annotations |
Authors | Dallas Card, Noah A. Smith |
Abstract | Estimating label proportions in a target corpus is a type of measurement that is useful for answering certain types of social-scientific questions. While past work has described a number of relevant approaches, nearly all are based on an assumption which we argue is invalid for many problems, particularly when dealing with human annotations. In this paper, we identify and differentiate between two relevant data generating scenarios (intrinsic vs. extrinsic labels), introduce a simple but novel method which emphasizes the importance of calibration, and then analyze and experimentally validate the appropriateness of various methods for each of the two scenarios. |
Tasks | Calibration, Sentiment Analysis, Text Categorization |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-1148/ |
https://www.aclweb.org/anthology/N18-1148 | |
PWC | https://paperswithcode.com/paper/the-importance-of-calibration-for-estimating |
Repo | |
Framework | |
INGEOTEC at SemEval-2018 Task 1: EvoMSA and μTC for Sentiment Analysis
Title | INGEOTEC at SemEval-2018 Task 1: EvoMSA and μTC for Sentiment Analysis |
Authors | Mario Graff, Mir, Sabino a-Jim{'e}nez, Eric S. Tellez, Daniela Moctezuma |
Abstract | This paper describes our participation in Affective Tweets task for emotional intensity and sentiment intensity subtasks for English, Spanish, and Arabic languages. We used two approaches, μTC and EvoMSA. The first one is a generic text categorization and regression system; and the second one, a two-stage architecture for Sentiment Analysis. Both approaches are multilingual and domain independent. |
Tasks | Combinatorial Optimization, Sentiment Analysis, Text Categorization |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1020/ |
https://www.aclweb.org/anthology/S18-1020 | |
PWC | https://paperswithcode.com/paper/ingeotec-at-semeval-2018-task-1-evomsa-and |
Repo | |
Framework | |
Preliminary Analysis of Embodied Interactions between Science Communicators and Visitors Based on a Multimodal Corpus of Japanese Conversations in a Science Museum
Title | Preliminary Analysis of Embodied Interactions between Science Communicators and Visitors Based on a Multimodal Corpus of Japanese Conversations in a Science Museum |
Authors | Rui Sakaida, Ryosaku Makino, Mayumi Bono |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1636/ |
https://www.aclweb.org/anthology/L18-1636 | |
PWC | https://paperswithcode.com/paper/preliminary-analysis-of-embodied-interactions |
Repo | |
Framework | |
Stance Detection in Fake News A Combined Feature Representation
Title | Stance Detection in Fake News A Combined Feature Representation |
Authors | Bilal Ghanem, Paolo Rosso, Francisco Rangel |
Abstract | With the uncontrolled increasing of fake news and rumors over the Web, different approaches have been proposed to address the problem. In this paper, we present an approach that combines lexical, word embeddings and n-gram features to detect the stance in fake news. Our approach has been tested on the Fake News Challenge (FNC-1) dataset. Given a news title-article pair, the FNC-1 task aims at determining the relevance of the article and the title. Our proposed approach has achieved an accurate result (59.6 {%} Macro F1) that is close to the state-of-the-art result with 0.013 difference using a simple feature representation. Furthermore, we have investigated the importance of different lexicons in the detection of the classification labels. |
Tasks | Stance Detection, Word Embeddings |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-5510/ |
https://www.aclweb.org/anthology/W18-5510 | |
PWC | https://paperswithcode.com/paper/stance-detection-in-fake-news-a-combined |
Repo | |
Framework | |
Pointing Out SQL Queries From Text
Title | Pointing Out SQL Queries From Text |
Authors | Chenglong Wang, Marc Brockschmidt, Rishabh Singh |
Abstract | The digitization of data has resulted in making datasets available to millions of users in the form of relational databases and spreadsheet tables. However, a majority of these users come from diverse backgrounds and lack the programming expertise to query and analyze such tables. We present a system that allows for querying data tables using natural language questions, where the system translates the question into an executable SQL query. We use a deep sequence to sequence model in wich the decoder uses a simple type system of SQL expressions to structure the output prediction. Based on the type, the decoder either copies an output token from the input question using an attention-based copying mechanism or generates it from a fixed vocabulary. We also introduce a value-based loss function that transforms a distribution over locations to copy from into a distribution over the set of input tokens to improve training of our model. We evaluate our model on the recently released WikiSQL dataset and show that our model trained using only supervised learning significantly outperforms the current state-of-the-art Seq2SQL model that uses reinforcement learning. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=BkUDW_lCb |
https://openreview.net/pdf?id=BkUDW_lCb | |
PWC | https://paperswithcode.com/paper/pointing-out-sql-queries-from-text |
Repo | |
Framework | |
Current and Future Psychological Health Prediction using Language and Socio-Demographics of Children for the CLPysch 2018 Shared Task
Title | Current and Future Psychological Health Prediction using Language and Socio-Demographics of Children for the CLPysch 2018 Shared Task |
Authors | Sharath Ch Guntuku, ra, Salvatore Giorgi, Lyle Ungar |
Abstract | This article is a system description and report on the submission of a team from the University of Pennsylvania in the {'}CLPsych 2018{'} shared task. The goal of the shared task was to use childhood language as a marker for both current and future psychological health over individual lifetimes. Our system employs multiple textual features derived from the essays written and individuals{'} socio-demographic variables at the age of 11. We considered several word clustering approaches, and explore the use of linear regression based on different feature sets. Our approach showed best results for predicting distress at the age of 42 and for predicting current anxiety on Disattenuated Pearson Correlation, and ranked fourth in the future health prediction task. In addition to the subtasks presented, we attempted to provide insight into mental health aspects at different ages. Our findings indicate that misspellings, words with illegible letters and increased use of personal pronouns are correlated with poor mental health at age 11, while descriptions about future physical activity, family and friends are correlated with good mental health. |
Tasks | |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0610/ |
https://www.aclweb.org/anthology/W18-0610 | |
PWC | https://paperswithcode.com/paper/current-and-future-psychological-health |
Repo | |
Framework | |
DeepCx: A transition-based approach for shallow semantic parsing with complex constructional triggers
Title | DeepCx: A transition-based approach for shallow semantic parsing with complex constructional triggers |
Authors | Jesse Dunietz, Jaime Carbonell, Lori Levin |
Abstract | This paper introduces the surface construction labeling (SCL) task, which expands the coverage of Shallow Semantic Parsing (SSP) to include frames triggered by complex constructions. We present DeepCx, a neural, transition-based system for SCL. As a test case for the approach, we apply DeepCx to the task of tagging causal language in English, which relies on a wider variety of constructions than are typically addressed in SSP. We report substantial improvements over previous tagging efforts on a causal language dataset. We also propose ways DeepCx could be extended to still more difficult constructions and to other semantic domains once appropriate datasets become available. |
Tasks | Semantic Parsing |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1196/ |
https://www.aclweb.org/anthology/D18-1196 | |
PWC | https://paperswithcode.com/paper/deepcx-a-transition-based-approach-for |
Repo | |
Framework | |
Better Transition-Based AMR Parsing with a Refined Search Space
Title | Better Transition-Based AMR Parsing with a Refined Search Space |
Authors | Zhijiang Guo, Wei Lu |
Abstract | This paper introduces a simple yet effective transition-based system for Abstract Meaning Representation (AMR) parsing. We argue that a well-defined search space involved in a transition system is crucial for building an effective parser. We propose to conduct the search in a refined search space based on a new compact AMR graph and an improved oracle. Our end-to-end parser achieves the state-of-the-art performance on various datasets with minimal additional information. |
Tasks | Amr Parsing, Named Entity Recognition, Semantic Parsing, Structured Prediction |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1198/ |
https://www.aclweb.org/anthology/D18-1198 | |
PWC | https://paperswithcode.com/paper/better-transition-based-amr-parsing-with-a |
Repo | |
Framework | |