Paper Group NANR 136
Transparent text quality assessment with convolutional neural networks. Repeat before Forgetting: Spaced Repetition for Efficient and Effective Training of Neural Networks. Language Based Mapping of Science Assessment Items to Skills. Regularized Modal Regression with Applications in Cognitive Impairment Prediction. Visualiza\cc~ao de gloss'ario …
Transparent text quality assessment with convolutional neural networks
| Title | Transparent text quality assessment with convolutional neural networks |
| Authors | Robert {"O}stling, Gintare Grigonyte |
| Abstract | We present a very simple model for text quality assessment based on a deep convolutional neural network, where the only supervision required is one corpus of user-generated text of varying quality, and one contrasting text corpus of consistently high quality. Our model is able to provide local quality assessments in different parts of a text, which allows visual feedback about where potentially problematic parts of the text are located, as well as a way to evaluate which textual features are captured by our model. We evaluate our method on two corpora: a large corpus of manually graded student essays and a longitudinal corpus of language learner written production, and find that the text quality metric learned by our model is a fairly strong predictor of both essay grade and learner proficiency level. |
| Tasks | Feature Engineering, Multi-Task Learning, Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5031/ |
| https://www.aclweb.org/anthology/W17-5031 | |
| PWC | https://paperswithcode.com/paper/transparent-text-quality-assessment-with |
| Repo | |
| Framework | |
Repeat before Forgetting: Spaced Repetition for Efficient and Effective Training of Neural Networks
| Title | Repeat before Forgetting: Spaced Repetition for Efficient and Effective Training of Neural Networks |
| Authors | Hadi Amiri, Timothy Miller, Guergana Savova |
| Abstract | We present a novel approach for training artificial neural networks. Our approach is inspired by broad evidence in psychology that shows human learners can learn efficiently and effectively by increasing intervals of time between subsequent reviews of previously learned materials (spaced repetition). We investigate the analogy between training neural models and findings in psychology about human memory model and develop an efficient and effective algorithm to train neural models. The core part of our algorithm is a cognitively-motivated scheduler according to which training instances and their {``}reviews{''} are spaced over time. Our algorithm uses only 34-50{%} of data per epoch, is 2.9-4.8 times faster than standard training, and outperforms competing state-of-the-art baselines. Our code is available at \url{scholar.harvard.edu/hadi/RbF/}. | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1255/ |
| https://www.aclweb.org/anthology/D17-1255 | |
| PWC | https://paperswithcode.com/paper/repeat-before-forgetting-spaced-repetition |
| Repo | |
| Framework | |
Language Based Mapping of Science Assessment Items to Skills
| Title | Language Based Mapping of Science Assessment Items to Skills |
| Authors | Farah Nadeem, Mari Ostendorf |
| Abstract | Knowledge of the association between assessment questions and the skills required to solve them is necessary for analysis of student learning. This association, often represented as a Q-matrix, is either hand-labeled by domain experts or learned as latent variables given a large student response data set. As a means of automating the match to formal standards, this paper uses neural text classification methods, leveraging the language in the standards documents to identify online text for a proxy training task. Experiments involve identifying the topic and crosscutting concepts of middle school science questions leveraging multi-task training. Results show that it is possible to automatically build a Q-matrix without student response data and using a modest number of hand-labeled questions. |
| Tasks | Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5036/ |
| https://www.aclweb.org/anthology/W17-5036 | |
| PWC | https://paperswithcode.com/paper/language-based-mapping-of-science-assessment |
| Repo | |
| Framework | |
Regularized Modal Regression with Applications in Cognitive Impairment Prediction
| Title | Regularized Modal Regression with Applications in Cognitive Impairment Prediction |
| Authors | Xiaoqian Wang, Hong Chen, Weidong Cai, Dinggang Shen, Heng Huang |
| Abstract | Linear regression models have been successfully used to function estimation and model selection in high-dimensional data analysis. However, most existing methods are built on least squares with the mean square error (MSE) criterion, which are sensitive to outliers and their performance may be degraded for heavy-tailed noise. In this paper, we go beyond this criterion by investigating the regularized modal regression from a statistical learning viewpoint. A new regularized modal regression model is proposed for estimation and variable selection, which is robust to outliers, heavy-tailed noise, and skewed noise. On the theoretical side, we establish the approximation estimate for learning the conditional mode function, the sparsity analysis for variable selection, and the robustness characterization. On the application side, we applied our model to successfully improve the cognitive impairment prediction using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort data. |
| Tasks | Model Selection |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6743-regularized-modal-regression-with-applications-in-cognitive-impairment-prediction |
| http://papers.nips.cc/paper/6743-regularized-modal-regression-with-applications-in-cognitive-impairment-prediction.pdf | |
| PWC | https://paperswithcode.com/paper/regularized-modal-regression-with |
| Repo | |
| Framework | |
Visualiza\cc~ao de gloss'ario em sistemas de recupera\cc~ao de informa\cc~ao (Glossary visualization in information retrieval systems)[In Portuguese]
| Title | Visualiza\cc~ao de gloss'ario em sistemas de recupera\cc~ao de informa\cc~ao (Glossary visualization in information retrieval systems)[In Portuguese] |
| Authors | Glauber Vaz, Le Oliveira, ro Mendon{\c{c}}a, Jr. Ivo Pierozzi |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6611/ |
| https://www.aclweb.org/anthology/W17-6611 | |
| PWC | https://paperswithcode.com/paper/visualizaaao-de-glossario-em-sistemas-de |
| Repo | |
| Framework | |
Natural-language Interactive Narratives in Imaginal Exposure Therapy for Obsessive-Compulsive Disorder
| Title | Natural-language Interactive Narratives in Imaginal Exposure Therapy for Obsessive-Compulsive Disorder |
| Authors | Melissa Roemmele, Paola Mardo, Andrew Gordon |
| Abstract | Obsessive-compulsive disorder (OCD) is an anxiety-based disorder that affects around 2.5{%} of the population. A common treatment for OCD is exposure therapy, where the patient repeatedly confronts a feared experience, which has the long-term effect of decreasing their anxiety. Some exposures consist of reading and writing stories about an imagined anxiety-provoking scenario. In this paper, we present a technology that enables patients to interactively contribute to exposure stories by supplying natural language input (typed or spoken) that advances a scenario. This interactivity could potentially increase the patient{'}s sense of immersion in an exposure and contribute to its success. We introduce the NLP task behind processing inputs to predict new events in the scenario, and describe our initial approach. We then illustrate the future possibility of this work with an example of an exposure scenario authored with our application. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3106/ |
| https://www.aclweb.org/anthology/W17-3106 | |
| PWC | https://paperswithcode.com/paper/natural-language-interactive-narratives-in |
| Repo | |
| Framework | |
A Survey on Hate Speech Detection using Natural Language Processing
| Title | A Survey on Hate Speech Detection using Natural Language Processing |
| Authors | Anna Schmidt, Michael Wiegand |
| Abstract | |
| Tasks | Hate Speech Detection |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/papers/W17-1101/w17-1101 |
| https://www.aclweb.org/anthology/W17-1101 | |
| PWC | https://paperswithcode.com/paper/a-survey-on-hate-speech-detection-using |
| Repo | |
| Framework | |
Wordnet extension via word embeddings: Experiments on the Norwegian Wordnet
| Title | Wordnet extension via word embeddings: Experiments on the Norwegian Wordnet |
| Authors | Heidi Sand, Erik Velldal, Lilja Ãvrelid |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/papers/W17-0242/w17-0242 |
| https://www.aclweb.org/anthology/W17-0242 | |
| PWC | https://paperswithcode.com/paper/wordnet-extension-via-word-embeddings |
| Repo | |
| Framework | |
Annotation of argument structure in Japanese legal documents
| Title | Annotation of argument structure in Japanese legal documents |
| Authors | Hiroaki Yamada, Simone Teufel, Takenobu Tokunaga |
| Abstract | We propose a method for the annotation of Japanese civil judgment documents, with the purpose of creating flexible summaries of these. The first step, described in the current paper, concerns content selection, i.e., the question of which material should be extracted initially for the summary. In particular, we utilize the hierarchical argument structure of the judgment documents. Our main contributions are a) the design of an annotation scheme that stresses the connection between legal points (called issue topics) and argument structure, b) an adaptation of rhetorical status to suit the Japanese legal system and c) the definition of a linked argument structure based on legal sub-arguments. In this paper, we report agreement between two annotators on several aspects of the overall task. |
| Tasks | Argument Mining |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5103/ |
| https://www.aclweb.org/anthology/W17-5103 | |
| PWC | https://paperswithcode.com/paper/annotation-of-argument-structure-in-japanese |
| Repo | |
| Framework | |
Learning Bilingual Projections of Embeddings for Vocabulary Expansion in Machine Translation
| Title | Learning Bilingual Projections of Embeddings for Vocabulary Expansion in Machine Translation |
| Authors | Pranava Swaroop Madhyastha, Cristina Espa{~n}a-Bonet |
| Abstract | We propose a simple log-bilinear softmax-based model to deal with vocabulary expansion in machine translation. Our model uses word embeddings trained on significantly large unlabelled monolingual corpora and learns over a fairly small, word-to-word bilingual dictionary. Given an out-of-vocabulary source word, the model generates a probabilistic list of possible translations in the target language using the trained bilingual embeddings. We integrate these translation options into a standard phrase-based statistical machine translation system and obtain consistent improvements in translation quality on the English{–}Spanish language pair. When tested over an out-of-domain testset, we get a significant improvement of 3.9 BLEU points. |
| Tasks | Machine Translation, Representation Learning, Transliteration, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2617/ |
| https://www.aclweb.org/anthology/W17-2617 | |
| PWC | https://paperswithcode.com/paper/learning-bilingual-projections-of-embeddings |
| Repo | |
| Framework | |
Evaluating Hierarchies of Verb Argument Structure with Hierarchical Clustering
| Title | Evaluating Hierarchies of Verb Argument Structure with Hierarchical Clustering |
| Authors | Jesse Mu, Joshua K. Hartshorne, Timothy O{'}Donnell |
| Abstract | Verbs can only be used with a few specific arrangements of their arguments (syntactic frames). Most theorists note that verbs can be organized into a hierarchy of verb classes based on the frames they admit. Here we show that such a hierarchy is objectively well-supported by the patterns of verbs and frames in English, since a systematic hierarchical clustering algorithm converges on the same structure as the handcrafted taxonomy of VerbNet, a broad-coverage verb lexicon. We also show that the hierarchies capture meaningful psychological dimensions of generalization by predicting novel verb coercions by human participants. We discuss limitations of a simple hierarchical representation and suggest similar approaches for identifying the representations underpinning verb argument structure. |
| Tasks | Language Acquisition, Natural Language Inference, Semantic Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1104/ |
| https://www.aclweb.org/anthology/D17-1104 | |
| PWC | https://paperswithcode.com/paper/evaluating-hierarchies-of-verb-argument |
| Repo | |
| Framework | |
Avaliando a similaridade sem^antica entre frases curtas atrav'es de uma abordagem h'\ibrida (A hybrid approach to measure Semantic Textual Similarity between short sentences in Brazilian Portuguese)[In Portuguese]
| Title | Avaliando a similaridade sem^antica entre frases curtas atrav'es de uma abordagem h'\ibrida (A hybrid approach to measure Semantic Textual Similarity between short sentences in Brazilian Portuguese)[In Portuguese] |
| Authors | Allan Silva, S Rigo, ro, Isa Mara Alves, Jorge Barbosa |
| Abstract | |
| Tasks | Semantic Textual Similarity |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6612/ |
| https://www.aclweb.org/anthology/W17-6612 | |
| PWC | https://paperswithcode.com/paper/avaliando-a-similaridade-semantica-entre |
| Repo | |
| Framework | |
Influ^encia de T'ecnicas N~ao-supervisionadas de Redu\cc~ao de Dimensionalidade para Organiza\cc~ao Flex'\ivel de Documentos (The Unsupervised Dimensionality Reduction Weight on Flexible Document Organization)[In Portuguese]
| Title | Influ^encia de T'ecnicas N~ao-supervisionadas de Redu\cc~ao de Dimensionalidade para Organiza\cc~ao Flex'\ivel de Documentos (The Unsupervised Dimensionality Reduction Weight on Flexible Document Organization)[In Portuguese] |
| Authors | Beatriz Lima, Fern Eust{'a}quio, a, Tatiane Nogueira |
| Abstract | |
| Tasks | Dimensionality Reduction |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6614/ |
| https://www.aclweb.org/anthology/W17-6614 | |
| PWC | https://paperswithcode.com/paper/influaancia-de-tacnicas-nao-supervisionadas |
| Repo | |
| Framework | |
Using Question-Answering Techniques to Implement a Knowledge-Driven Argument Mining Approach
| Title | Using Question-Answering Techniques to Implement a Knowledge-Driven Argument Mining Approach |
| Authors | Patrick Saint-Dizier |
| Abstract | This short paper presents a first implementation of a knowledge-driven argument mining approach. The major processing steps and language resources of the system are surveyed. An indicative evaluation outlines challenges and improvement directions. |
| Tasks | Argument Mining, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5111/ |
| https://www.aclweb.org/anthology/W17-5111 | |
| PWC | https://paperswithcode.com/paper/using-question-answering-techniques-to |
| Repo | |
| Framework | |
What works and what does not: Classifier and feature analysis for argument mining
| Title | What works and what does not: Classifier and feature analysis for argument mining |
| Authors | Ahmet Aker, Alfred Sliwa, Yuan Ma, Ruishen Lui, Niravkumar Borad, Seyedeh Ziyaei, Mina Ghobadi |
| Abstract | This paper offers a comparative analysis of the performance of different supervised machine learning methods and feature sets on argument mining tasks. Specifically, we address the tasks of extracting argumentative segments from texts and predicting the structure between those segments. Eight classifiers and different combinations of six feature types reported in previous work are evaluated. The results indicate that overall best performing features are the structural ones. Although the performance of classifiers varies depending on the feature combinations and corpora used for training and testing, Random Forest seems to be among the best performing classifiers. These results build a basis for further development of argument mining techniques and can guide an implementation of argument mining into different applications such as argument based search. |
| Tasks | Argument Mining |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5112/ |
| https://www.aclweb.org/anthology/W17-5112 | |
| PWC | https://paperswithcode.com/paper/what-works-and-what-does-not-classifier-and |
| Repo | |
| Framework | |
