Paper Group NANR 170
Using Automated Metaphor Identification to Aid in Detection and Prediction of First-Episode Schizophrenia. Delexicalized transfer parsing for low-resource languages using transformed and combined treebanks. Incorporating Metadata into Content-Based User Embeddings. Quantitative Characterization of Code Switching Patterns in Complex Multi-Party Conv …
Using Automated Metaphor Identification to Aid in Detection and Prediction of First-Episode Schizophrenia
| Title | Using Automated Metaphor Identification to Aid in Detection and Prediction of First-Episode Schizophrenia |
| Authors | E. Dar{'\i}o Guti{'e}rrez, Guillermo Cecchi, Cheryl Corcoran, Philip Corlett |
| Abstract | The diagnosis of serious mental health conditions such as schizophrenia is based on the judgment of clinicians whose training takes several years, and cannot be easily formalized into objective measures. However, previous research suggests there are disturbances in aspects of the language use of patients with schizophrenia. Using metaphor-identification and sentiment-analysis algorithms to automatically generate features, we create a classifier, that, with high accuracy, can predict which patients will develop (or currently suffer from) schizophrenia. To our knowledge, this study is the first to demonstrate the utility of automated metaphor identification algorithms for detection or prediction of disease. |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1316/ |
| https://www.aclweb.org/anthology/D17-1316 | |
| PWC | https://paperswithcode.com/paper/using-automated-metaphor-identification-to |
| Repo | |
| Framework | |
Delexicalized transfer parsing for low-resource languages using transformed and combined treebanks
| Title | Delexicalized transfer parsing for low-resource languages using transformed and combined treebanks |
| Authors | Ayan Das, Affan Zaffar, Sudeshna Sarkar |
| Abstract | This paper describes our dependency parsing system in CoNLL-2017 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. We primarily focus on the low-resource languages (surprise languages). We have developed a framework to combine multiple treebanks to train parsers for low resource languages by delexicalization method. We have applied transformation on source language treebanks based on syntactic features of the low-resource language to improve performance of the parser. In the official evaluation, our system achieves an macro-averaged LAS score of 67.61 and 37.16 on the entire blind test data and the surprise language test data respectively. |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Machine Translation, Question Answering, Semantic Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3019/ |
| https://www.aclweb.org/anthology/K17-3019 | |
| PWC | https://paperswithcode.com/paper/delexicalized-transfer-parsing-for-low |
| Repo | |
| Framework | |
Incorporating Metadata into Content-Based User Embeddings
| Title | Incorporating Metadata into Content-Based User Embeddings |
| Authors | Linzi Xing, Michael J. Paul |
| Abstract | Low-dimensional vector representations of social media users can benefit applications like recommendation systems and user attribute inference. Recent work has shown that user embeddings can be improved by combining different types of information, such as text and network data. We propose a data augmentation method that allows novel feature types to be used within off-the-shelf embedding models. Experimenting with the task of friend recommendation on a dataset of 5,019 Twitter users, we show that our approach can lead to substantial performance gains with the simple addition of network and geographic features. |
| Tasks | Data Augmentation, Recommendation Systems |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4406/ |
| https://www.aclweb.org/anthology/W17-4406 | |
| PWC | https://paperswithcode.com/paper/incorporating-metadata-into-content-based |
| Repo | |
| Framework | |
Quantitative Characterization of Code Switching Patterns in Complex Multi-Party Conversations: A Case Study on Hindi Movie Scripts
| Title | Quantitative Characterization of Code Switching Patterns in Complex Multi-Party Conversations: A Case Study on Hindi Movie Scripts |
| Authors | Adithya Pratapa, Monojit Choudhury |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7510/ |
| https://www.aclweb.org/anthology/W17-7510 | |
| PWC | https://paperswithcode.com/paper/quantitative-characterization-of-code |
| Repo | |
| Framework | |
SWEGRAM – A Web-Based Tool for Automatic Annotation and Analysis of Swedish Texts
| Title | SWEGRAM – A Web-Based Tool for Automatic Annotation and Analysis of Swedish Texts |
| Authors | Jesper N{"a}sman, Be{'a}ta Megyesi, Anne Palm{'e}r |
| Abstract | |
| Tasks | Dependency Parsing, Part-Of-Speech Tagging, Tokenization |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0216/ |
| https://www.aclweb.org/anthology/W17-0216 | |
| PWC | https://paperswithcode.com/paper/swegram-axtendash-a-web-based-tool-for |
| Repo | |
| Framework | |
Reasoning with Sets to Solve Simple Word Problems Automatically
| Title | Reasoning with Sets to Solve Simple Word Problems Automatically |
| Authors | Sowmya S Sundaram, Deepak Khemani |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7524/ |
| https://www.aclweb.org/anthology/W17-7524 | |
| PWC | https://paperswithcode.com/paper/reasoning-with-sets-to-solve-simple-word |
| Repo | |
| Framework | |
From Raw Text to Universal Dependencies - Look, No Tags!
| Title | From Raw Text to Universal Dependencies - Look, No Tags! |
| Authors | Miryam de Lhoneux, Yan Shao, Ali Basirat, Eliyahu Kiperwasser, Sara Stymne, Yoav Goldberg, Joakim Nivre |
| Abstract | We present the Uppsala submission to the CoNLL 2017 shared task on parsing from raw text to universal dependencies. Our system is a simple pipeline consisting of two components. The first performs joint word and sentence segmentation on raw text; the second predicts dependency trees from raw words. The parser bypasses the need for part-of-speech tagging, but uses word embeddings based on universal tag distributions. We achieved a macro-averaged LAS F1 of 65.11 in the official test run, which improved to 70.49 after bug fixes. We obtained the 2nd best result for sentence segmentation with a score of 89.03. |
| Tasks | Dependency Parsing, Part-Of-Speech Tagging, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3022/ |
| https://www.aclweb.org/anthology/K17-3022 | |
| PWC | https://paperswithcode.com/paper/from-raw-text-to-universal-dependencies-look |
| Repo | |
| Framework | |
Cross Linguistic Variations in Discourse Relations among Indian Languages
| Title | Cross Linguistic Variations in Discourse Relations among Indian Languages |
| Authors | Sindhuja Gopalan, Lakshmi S, Sobha Lalitha Devi |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7549/ |
| https://www.aclweb.org/anthology/W17-7549 | |
| PWC | https://paperswithcode.com/paper/cross-linguistic-variations-in-discourse |
| Repo | |
| Framework | |
Linguistic approach based Transfer Learning for Sentiment Classification in Hindi
| Title | Linguistic approach based Transfer Learning for Sentiment Classification in Hindi |
| Authors | Vartika Rai, Sakshee Vijay, Dipti Misra |
| Abstract | |
| Tasks | Sentiment Analysis, Transfer Learning |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7546/ |
| https://www.aclweb.org/anthology/W17-7546 | |
| PWC | https://paperswithcode.com/paper/linguistic-approach-based-transfer-learning |
| Repo | |
| Framework | |
The Relation of Form and Function in Linguistic Theory and in a Multilayer Treebank
| Title | The Relation of Form and Function in Linguistic Theory and in a Multilayer Treebank |
| Authors | Eduard Bej{\v{c}}ek, Eva Haji{\v{c}}ov{'a}, Marie Mikulov{'a}, Jarmila Panevov{'a} |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7609/ |
| https://www.aclweb.org/anthology/W17-7609 | |
| PWC | https://paperswithcode.com/paper/the-relation-of-form-and-function-in |
| Repo | |
| Framework | |
Variational Laws of Visual Attention for Dynamic Scenes
| Title | Variational Laws of Visual Attention for Dynamic Scenes |
| Authors | Dario Zanca, Marco Gori |
| Abstract | Computational models of visual attention are at the crossroad of disciplines like cognitive science, computational neuroscience, and computer vision. This paper proposes a model of attentional scanpath that is based on the principle that there are foundational laws that drive the emergence of visual attention. We devise variational laws of the eye-movement that rely on a generalized view of the Least Action Principle in physics. The potential energy captures details as well as peripheral visual features, while the kinetic energy corresponds with the classic interpretation in analytic mechanics. In addition, the Lagrangian contains a brightness invariance term, which characterizes significantly the scanpath trajectories. We obtain differential equations of visual attention as the stationary point of the generalized action, and we propose an algorithm to estimate the model parameters. Finally, we report experimental results to validate the model in tasks of saliency detection. |
| Tasks | Saliency Detection |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6972-variational-laws-of-visual-attention-for-dynamic-scenes |
| http://papers.nips.cc/paper/6972-variational-laws-of-visual-attention-for-dynamic-scenes.pdf | |
| PWC | https://paperswithcode.com/paper/variational-laws-of-visual-attention-for |
| Repo | |
| Framework | |
Knowledge Tracing in Sequential Learning of Inflected Vocabulary
| Title | Knowledge Tracing in Sequential Learning of Inflected Vocabulary |
| Authors | Adithya Renduchintala, Philipp Koehn, Jason Eisner |
| Abstract | We present a feature-rich knowledge tracing method that captures a student{'}s acquisition and retention of knowledge during a foreign language phrase learning task. We model the student{'}s behavior as making predictions under a log-linear model, and adopt a neural gating mechanism to model how the student updates their log-linear parameters in response to feedback. The gating mechanism allows the model to learn complex patterns of retention and acquisition for each feature, while the log-linear parameterization results in an interpretable knowledge state. We collect human data and evaluate several versions of the model. |
| Tasks | Knowledge Tracing, Structured Prediction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1025/ |
| https://www.aclweb.org/anthology/K17-1025 | |
| PWC | https://paperswithcode.com/paper/knowledge-tracing-in-sequential-learning-of |
| Repo | |
| Framework | |
A Semi-universal Pipelined Approach to the CoNLL 2017 UD Shared Task
| Title | A Semi-universal Pipelined Approach to the CoNLL 2017 UD Shared Task |
| Authors | Hiroshi Kanayama, Masayasu Muraoka, Katsumasa Yoshikawa |
| Abstract | This paper presents our system submitted for the CoNLL 2017 Shared Task, {``}Multilingual Parsing from Raw Text to Universal Dependencies.{''} We ran the system for all languages with our own fully pipelined components without relying on re-trained baseline systems. To train the dependency parser, we used only the universal part-of-speech tags and distance between words, and applied deterministic rules to assign dependency labels. The simple and delexicalized models are suitable for cross-lingual transfer approaches and a universal language model. Experimental results show that our model performed well in some metrics and leads discussion on topics such as contribution of each component and on syntactic similarities among languages. | |
| Tasks | Cross-Lingual Transfer, Language Modelling, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3028/ |
| https://www.aclweb.org/anthology/K17-3028 | |
| PWC | https://paperswithcode.com/paper/a-semi-universal-pipelined-approach-to-the |
| Repo | |
| Framework | |
Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval
| Title | Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval |
| Authors | ErkunYang, 1 ChengDeng, 1 WeiLiu, 2 XianglongLiu, 3 DachengTao, 4 XinboGao1 |
| Abstract | With benefits of low storage cost and fast query speed, crossmodal hashing has received considerable attention recently. However,almostallexistingmethodsoncross-modalhashing cannot obtain powerful hash codes due to directly utilizing hand-crafted features or ignoring heterogeneous correlations acrossdifferentmodalities,whichwillgreatlydegradetheretrieval performance. In this paper, we propose a novel deep cross-modal hashing method to generate compact hash codes through an end-to-end deep learning architecture, which can effectively capture the intrinsic relationships between various modalities. Our architecture integrates different types of pairwise constraints to encourage the similarities of the hash codes from an intra-modal view and an inter-modal view, respectively. Moreover, additional decorrelation constraints are introduced to this architecture, thus enhancing the discriminative ability of each hash bit. Extensive experiments show that our proposed method yields state-of-the-art results on two cross-modal retrieval datasets. |
| Tasks | Cross-Modal Retrieval |
| Published | 2017-02-12 |
| URL | https://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14326/13959 |
| https://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14326/13959 | |
| PWC | https://paperswithcode.com/paper/pairwise-relationship-guided-deep-hashing-for |
| Repo | |
| Framework | |
Energy-Efficient Many-objective Virtual Machine Placement Optimization in a Cloud Computing Environment
| Title | Energy-Efficient Many-objective Virtual Machine Placement Optimization in a Cloud Computing Environment |
| Authors | Xin Ye 1, Yanli Yin1, Lan Lan |
| Abstract | Cloud data centres are faced with the serious problem of increasing energy consumption. Thus, the problem of virtual machine placement for energy saving is becoming a critical issue. Considering various requirements of cloud providers and users, a many-objective virtual machine placement model is built to minimize energy consumption and maximize load balance, resource utilization, and robustness. An EEKnEA (Energy-Efficient KnEA) algorithm is proposed to address this problem. EEKnEA is improved by proposing an Energy-Efficient-oriented Population Initialization Strategy (EEPIS) based on the KnEA (Knee Point-Driven Evolutionary Algorithm), which is a high-performance algorithm for many-objective problems. The proposed model and performance of EEKnEA are evaluated in comparison to KnEA and other algorithms. Experimental results show that the proposed model is reasonable, and the EEKnEA algorithm outperforms its counterparts on this type of problem in terms of energy saving, load balance and robustness. |
| Tasks | |
| Published | 2017-07-31 |
| URL | https://ieeexplore.ieee.org/abstract/document/7997707 |
| https://ieeexplore.ieee.org/abstract/document/7997707 | |
| PWC | https://paperswithcode.com/paper/energy-efficient-many-objective-virtual |
| Repo | |
| Framework | |
