Paper Group NANR 133
Flexible Non-Terminals for Dependency Tree-to-Tree Reordering. A Comparative Study of Text Preprocessing Approaches for Topic Detection of User Utterances. Semi-supervised Gender Classification with Joint Textual and Social Modeling. An Empirical Exploration of Moral Foundations Theory in Partisan News Sources. Predicting proficiency levels in lear …
Flexible Non-Terminals for Dependency Tree-to-Tree Reordering
| Title | Flexible Non-Terminals for Dependency Tree-to-Tree Reordering |
| Authors | John Richardson, Fabien Cromi{`e}res, Toshiaki Nakazawa, Sadao Kurohashi |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1002/ |
| https://www.aclweb.org/anthology/N16-1002 | |
| PWC | https://paperswithcode.com/paper/flexible-non-terminals-for-dependency-tree-to |
| Repo | |
| Framework | |
A Comparative Study of Text Preprocessing Approaches for Topic Detection of User Utterances
| Title | A Comparative Study of Text Preprocessing Approaches for Topic Detection of User Utterances |
| Authors | Roman Sergienko, Muhammad Shan, Wolfgang Minker |
| Abstract | The paper describes a comparative study of existing and novel text preprocessing and classification techniques for domain detection of user utterances. Two corpora are considered. The first one contains customer calls to a call centre for further call routing; the second one contains answers of call centre employees with different kinds of customer orientation behaviour. Seven different unsupervised and supervised term weighting methods were applied. The collective use of term weighting methods is proposed for classification effectiveness improvement. Four different dimensionality reduction methods were applied: stop-words filtering with stemming, feature selection based on term weights, feature transformation based on term clustering, and a novel feature transformation method based on terms belonging to classes. As classification algorithms we used k-NN and a SVM-based algorithm. The numerical experiments have shown that the simultaneous use of the novel proposed approaches (collectives of term weighting methods and the novel feature transformation method) allows reaching the high classification results with very small number of features. |
| Tasks | Dimensionality Reduction, Feature Selection |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1288/ |
| https://www.aclweb.org/anthology/L16-1288 | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-text-preprocessing |
| Repo | |
| Framework | |
Semi-supervised Gender Classification with Joint Textual and Social Modeling
| Title | Semi-supervised Gender Classification with Joint Textual and Social Modeling |
| Authors | Shoushan Li, Bin Dai, Zhengxian Gong, Guodong Zhou |
| Abstract | In gender classification, labeled data is often limited while unlabeled data is ample. This motivates semi-supervised learning for gender classification to improve the performance by exploring the knowledge in both labeled and unlabeled data. In this paper, we propose a semi-supervised approach to gender classification by leveraging textual features and a specific kind of indirect links among the users which we call {}same-interest{''} links. Specifically, we propose a factor graph, namely Textual and Social Factor Graph (TSFG), to model both the textual and the {}same-interest{''} link information. Empirical studies demonstrate the effectiveness of the proposed approach to semi-supervised gender classification. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1197/ |
| https://www.aclweb.org/anthology/C16-1197 | |
| PWC | https://paperswithcode.com/paper/semi-supervised-gender-classification-with |
| Repo | |
| Framework | |
An Empirical Exploration of Moral Foundations Theory in Partisan News Sources
| Title | An Empirical Exploration of Moral Foundations Theory in Partisan News Sources |
| Authors | Dean Fulgoni, Jordan Carpenter, Lyle Ungar, Daniel Preo{\c{t}}iuc-Pietro |
| Abstract | News sources frame issues in different ways in order to appeal or control the perception of their readers. We present a large scale study of news articles from partisan sources in the US across a variety of different issues. We first highlight that differences between sides exist by predicting the political leaning of articles of unseen political bias. Framing can be driven by different types of morality that each group values. We emphasize differences in framing of different news building on the moral foundations theory quantified using hand crafted lexicons. Our results show that partisan sources frame political issues differently both in terms of words usage and through the moral foundations they relate to. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1591/ |
| https://www.aclweb.org/anthology/L16-1591 | |
| PWC | https://paperswithcode.com/paper/an-empirical-exploration-of-moral-foundations |
| Repo | |
| Framework | |
Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert-written coursebooks
| Title | Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert-written coursebooks |
| Authors | Ildik{'o} Pil{'a}n, Elena Volodina, Torsten Zesch |
| Abstract | The lack of a sufficient amount of data tailored for a task is a well-recognized problem for many statistical NLP methods. In this paper, we explore whether data sparsity can be successfully tackled when classifying language proficiency levels in the domain of learner-written output texts. We aim at overcoming data sparsity by incorporating knowledge in the trained model from another domain consisting of input texts written by teaching professionals for learners. We compare different domain adaptation techniques and find that a weighted combination of the two types of data performs best, which can even rival systems based on considerably larger amounts of in-domain data. Moreover, we show that normalizing errors in learners{'} texts can substantially improve classification when level-annotated in-domain data is not available. |
| Tasks | Domain Adaptation, Language Acquisition, Transfer Learning |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1198/ |
| https://www.aclweb.org/anthology/C16-1198 | |
| PWC | https://paperswithcode.com/paper/predicting-proficiency-levels-in-learner |
| Repo | |
| Framework | |
An Analysis of Prerequisite Skills for Reading Comprehension
| Title | An Analysis of Prerequisite Skills for Reading Comprehension |
| Authors | Saku Sugawara, Akiko Aizawa |
| Abstract | |
| Tasks | Reading Comprehension |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-6001/ |
| https://www.aclweb.org/anthology/W16-6001 | |
| PWC | https://paperswithcode.com/paper/an-analysis-of-prerequisite-skills-for |
| Repo | |
| Framework | |
YSDA Participation in the WMT’16 Quality Estimation Shared Task
| Title | YSDA Participation in the WMT’16 Quality Estimation Shared Task |
| Authors | Anna Kozlova, Mariya Shmatova, Anton Frolov |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2385/ |
| https://www.aclweb.org/anthology/W16-2385 | |
| PWC | https://paperswithcode.com/paper/ysda-participation-in-the-wmt16-quality |
| Repo | |
| Framework | |
Deep neural networks for learning graph representations
| Title | Deep neural networks for learning graph representations |
| Authors | Shaosheng Cao, Wei Lu, Qiongkai Xu |
| Abstract | In this paper, we propose a novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information. Different from other previous research efforts, we adopt a random surfing model to capture graph structural information directly, instead of using the sampling-based method for generating linear sequences proposed by Perozzi et al. (2014). The advantages of our approach will be illustrated from both theorical and empirical perspectives. We also give a new perspective for the matrix factorization method proposed by Levy and Goldberg (2014), in which the pointwise mutual information (PMI) matrix is considered as an analytical solution to the objective function of the skip-gram model with negative sampling proposed by Mikolov et al. (2013). Unlike their approach which involves the use of the SVD for finding the low-dimensitonal projections from the PMI matrix, however, the stacked denoising autoencoder is introduced in our model to extract complex features and model non-linearities. To demonstrate the effectiveness of our model, we conduct experiments on clustering and visualization tasks, employing the learned vertex representations as features. Empirical results on datasets of varying sizes show that our model outperforms other stat-of-the-art models in such tasks. |
| Tasks | Denoising, Graph Clustering |
| Published | 2016-02-21 |
| URL | https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12423 |
| https://pdfs.semanticscholar.org/1a37/f07606d60df365d74752857e8ce909f700b3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-networks-for-learning-graph |
| Repo | |
| Framework | |
Synchronous Context-Free Grammars and Optimal Parsing Strategies
| Title | Synchronous Context-Free Grammars and Optimal Parsing Strategies |
| Authors | Daniel Gildea, Giorgio Satta |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/J16-2002/ |
| https://www.aclweb.org/anthology/J16-2002 | |
| PWC | https://paperswithcode.com/paper/synchronous-context-free-grammars-and-optimal |
| Repo | |
| Framework | |
A Pipeline Japanese Entity Linking System with Embedding Features
| Title | A Pipeline Japanese Entity Linking System with Embedding Features |
| Authors | Shuangshuang Zhou |
| Abstract | |
| Tasks | Coreference Resolution, Entity Linking, Information Retrieval, Knowledge Base Population, Named Entity Recognition, Question Answering |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-2025/ |
| https://www.aclweb.org/anthology/Y16-2025 | |
| PWC | https://paperswithcode.com/paper/a-pipeline-japanese-entity-linking-system |
| Repo | |
| Framework | |
Modeling language evolution with codes that utilize context and phonetic features
| Title | Modeling language evolution with codes that utilize context and phonetic features |
| Authors | Javad Nouri, Roman Yangarber |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-1014/ |
| https://www.aclweb.org/anthology/K16-1014 | |
| PWC | https://paperswithcode.com/paper/modeling-language-evolution-with-codes-that |
| Repo | |
| Framework | |
Content Selection through Paraphrase Detection: Capturing different Semantic Realisations of the Same Idea
| Title | Content Selection through Paraphrase Detection: Capturing different Semantic Realisations of the Same Idea |
| Authors | Elena Lloret, Claire Gardent |
| Abstract | |
| Tasks | Paraphrase Identification, Semantic Textual Similarity, Text Generation, Word Embeddings |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3505/ |
| https://www.aclweb.org/anthology/W16-3505 | |
| PWC | https://paperswithcode.com/paper/content-selection-through-paraphrase |
| Repo | |
| Framework | |
Event Detection and Co-reference with Minimal Supervision
| Title | Event Detection and Co-reference with Minimal Supervision |
| Authors | Haoruo Peng, Yangqiu Song, Dan Roth |
| Abstract | |
| Tasks | Semantic Role Labeling, Semantic Textual Similarity |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1038/ |
| https://www.aclweb.org/anthology/D16-1038 | |
| PWC | https://paperswithcode.com/paper/event-detection-and-co-reference-with-minimal |
| Repo | |
| Framework | |
Why Do They Leave: Modeling Participation in Online Depression Forums
| Title | Why Do They Leave: Modeling Participation in Online Depression Forums |
| Authors | Farig Sadeque, Ted Pedersen, Thamar Solorio, Prasha Shrestha, Nicolas Rey-Villamizar, Steven Bethard |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-6203/ |
| https://www.aclweb.org/anthology/W16-6203 | |
| PWC | https://paperswithcode.com/paper/why-do-they-leave-modeling-participation-in |
| Repo | |
| Framework | |
Selecting Sentences versus Selecting Tree Constituents for Automatic Question Ranking
| Title | Selecting Sentences versus Selecting Tree Constituents for Automatic Question Ranking |
| Authors | Alberto Barr{'o}n-Cede{~n}o, Giovanni Da San Martino, Salvatore Romeo, Aless Moschitti, ro |
| Abstract | Community question answering (cQA) websites are focused on users who query questions onto an online forum, expecting for other users to provide them answers or suggestions. Unlike other social media, the length of the posted queries has no limits and queries tend to be multi-sentence elaborations combining context, actual questions, and irrelevant information. We approach the problem of question ranking: given a user{'}s new question, to retrieve those previously-posted questions which could be equivalent, or highly relevant. This could prevent the posting of nearly-duplicate questions and provide the user with instantaneous answers. For the first time in cQA, we address the selection of relevant text {—}both at sentence- and at constituent-level{—} for parse tree-based representations. Our supervised models for text selection boost the performance of a tree kernel-based machine learning model, allowing it to overtake the current state of the art on a recently released cQA evaluation framework. |
| Tasks | Community Question Answering, Machine Translation, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1237/ |
| https://www.aclweb.org/anthology/C16-1237 | |
| PWC | https://paperswithcode.com/paper/selecting-sentences-versus-selecting-tree |
| Repo | |
| Framework | |
