Paper Group NANR 105
A Psychologically Informed Approach to CLPsych Shared Task 2018. Modeling and Prediction of Online Product Review Helpfulness: A Survey. CLaC at SMM4H Task 1, 2, and 4. Effective Attention Modeling for Aspect-Level Sentiment Classification. Temporal Hallucinating for Action Recognition With Few Still Images. Transfer Learning via Learning to Transf …
A Psychologically Informed Approach to CLPsych Shared Task 2018
| Title | A Psychologically Informed Approach to CLPsych Shared Task 2018 |
| Authors | Almog Simchon, Michael Gilead |
| Abstract | This paper describes our approach to the CLPsych 2018 Shared Task, in which we attempted to predict cross-sectional psychological health at age 11 and future psychological distress based on childhood essays. We attempted several modeling approaches and observed best cross-validated prediction accuracy with relatively simple models based on psychological theory. The models provided reasonable predictions in most outcomes. Notably, our model was especially successful in predicting out-of-sample psychological distress (across people and across time) at age 50. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0612/ |
| https://www.aclweb.org/anthology/W18-0612 | |
| PWC | https://paperswithcode.com/paper/a-psychologically-informed-approach-to |
| Repo | |
| Framework | |
Modeling and Prediction of Online Product Review Helpfulness: A Survey
| Title | Modeling and Prediction of Online Product Review Helpfulness: A Survey |
| Authors | Gerardo Ocampo Diaz, Vincent Ng |
| Abstract | As the amount of free-form user-generated reviews in e-commerce websites continues to increase, there is an increasing need for automatic mechanisms that sift through the vast amounts of user reviews and identify quality content. Review helpfulness modeling is a task which studies the mechanisms that affect review helpfulness and attempts to accurately predict it. This paper provides an overview of the most relevant work in helpfulness prediction and understanding in the past decade, discusses the insights gained from said work, and provides guidelines for future research. |
| Tasks | Recommendation Systems |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1065/ |
| https://www.aclweb.org/anthology/P18-1065 | |
| PWC | https://paperswithcode.com/paper/modeling-and-prediction-of-online-product |
| Repo | |
| Framework | |
CLaC at SMM4H Task 1, 2, and 4
| Title | CLaC at SMM4H Task 1, 2, and 4 |
| Authors | Parsa Bagherzadeh, Nadia Sheikh, Sabine Bergler |
| Abstract | CLaC Labs participated in Tasks 1, 2, and 4 using the same base architecture for all tasks with various parameter variations. This was our first exploration of this data and the SMM4H Tasks, thus a unified system was useful to compare the behavior of our architecture over the different datasets and how they interact with different linguistic features. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5920/ |
| https://www.aclweb.org/anthology/W18-5920 | |
| PWC | https://paperswithcode.com/paper/clac-at-smm4h-task-1-2-and-4 |
| Repo | |
| Framework | |
Effective Attention Modeling for Aspect-Level Sentiment Classification
| Title | Effective Attention Modeling for Aspect-Level Sentiment Classification |
| Authors | Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier |
| Abstract | Aspect-level sentiment classification aims to determine the sentiment polarity of a review sentence towards an opinion target. A sentence could contain multiple sentiment-target pairs; thus the main challenge of this task is to separate different opinion contexts for different targets. To this end, attention mechanism has played an important role in previous state-of-the-art neural models. The mechanism is able to capture the importance of each context word towards a target by modeling their semantic associations. We build upon this line of research and propose two novel approaches for improving the effectiveness of attention. First, we propose a method for target representation that better captures the semantic meaning of the opinion target. Second, we introduce an attention model that incorporates syntactic information into the attention mechanism. We experiment on attention-based LSTM (Long Short-Term Memory) models using the datasets from SemEval 2014, 2015, and 2016. The experimental results show that the conventional attention-based LSTM can be substantially improved by incorporating the two approaches. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1096/ |
| https://www.aclweb.org/anthology/C18-1096 | |
| PWC | https://paperswithcode.com/paper/effective-attention-modeling-for-aspect-level |
| Repo | |
| Framework | |
Temporal Hallucinating for Action Recognition With Few Still Images
| Title | Temporal Hallucinating for Action Recognition With Few Still Images |
| Authors | Yali Wang, Lei Zhou, Yu Qiao |
| Abstract | Action recognition in still images has been recently promoted by deep learning. However, the success of these deep models heavily depends on huge amount of training images for various action categories, which may not be available in practice. Alternatively, humans can classify new action categories after seeing few images, since we may not only compare appearance similarities between images on hand, but also attempt to recall importance motion cues from relevant action videos in our memory. To mimic this capacity, we propose a novel Hybrid Video Memory (HVM) machine, which can hallucinate temporal features of still images from video memory, in order to boost action recognition with few still images. First, we design a temporal memory module consisting of temporal hallucinating and predicting. Temporal hallucinating can generate temporal features of still images in an unsupervised manner. Hence, it can be flexibly used in realistic scenarios, where image and video categories may not be consistent. Temporal predicting can effectively infer action categories for query image, by integrating temporal features of training images and videos within a domain-adaptation manner. Second, we design a spatial memory module for spatial predicting. As spatial and temporal features are complementary to represent different actions, we apply spatial-temporal prediction fusion to further boost performance. Finally, we design a video selection module to select strongly-relevant videos as memory. In this case, we can balance the number of images and videos to reduce prediction bias as well as preserve computation efficiency. To show the effectiveness, we conduct extensive experiments on three challenging data sets, where our HVM outperforms a number of recent approaches by temporal hallucinating from video memory. |
| Tasks | Action Recognition In Still Images, Domain Adaptation, Temporal Action Localization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Temporal_Hallucinating_for_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Temporal_Hallucinating_for_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-hallucinating-for-action-recognition |
| Repo | |
| Framework | |
Transfer Learning via Learning to Transfer
| Title | Transfer Learning via Learning to Transfer |
| Authors | Ying WEI, Yu Zhang, Junzhou Huang, Qiang Yang |
| Abstract | In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain. Determining the optimal one that maximizes the performance improvement requires either exhaustive exploration or considerable expertise. Meanwhile, it is widely accepted in educational psychology that human beings improve transfer learning skills of deciding what to transfer through meta-cognitive reflection on inductive transfer learning practices. Motivated by this, we propose a novel transfer learning framework known as Learning to Transfer (L2T) to automatically determine what and how to transfer are the best by leveraging previous transfer learning experiences. We establish the L2T framework in two stages: 1) we learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer are the best for a future pair of domains by optimizing the reflection function. We also theoretically analyse the algorithmic stability and generalization bound of L2T, and empirically demonstrate its superiority over several state-of-the-art transfer learning algorithms. |
| Tasks | Transfer Learning |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2145 |
| http://proceedings.mlr.press/v80/wei18a/wei18a.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-via-learning-to-transfer |
| Repo | |
| Framework | |
Lung Tumor Location and Identification with AlexNet and a Custom CNN
| Title | Lung Tumor Location and Identification with AlexNet and a Custom CNN |
| Authors | Allison M Rossetto, Wenjin Zhou |
| Abstract | Lung cancer is the leading cause of cancer deaths in the world and early detection is a crucial part of increasing patient survival. Deep learning techniques provide us with a method of automated analysis of patient scans. In this work, we compare AlexNet, a multi-layered and highly flexible architecture, with a custom CNN to determine if lung nodules with patient scans are benign or cancerous. We have found our CNN architecture to be highly accurate (99.79%) and fast while maintaining low False Positive and False Negative rates (< 0.01% and 0.15% respectively). This is important as high false positive rates are a serious issue with lung cancer diagnosis. We have found that AlexNet is not well suited to the problem of nodule identification, though it is a good baseline comparison because of its flexibility. |
| Tasks | Lung Cancer Diagnosis |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJr4kfWCb |
| https://openreview.net/pdf?id=rJr4kfWCb | |
| PWC | https://paperswithcode.com/paper/lung-tumor-location-and-identification-with |
| Repo | |
| Framework | |
Leveraging News Sentiment to Improve Microblog Sentiment Classification in the Financial Domain
| Title | Leveraging News Sentiment to Improve Microblog Sentiment Classification in the Financial Domain |
| Authors | Tobias Daudert, Paul Buitelaar, Sapna Negi |
| Abstract | With the rising popularity of social media in the society and in research, analysing texts short in length, such as microblogs, becomes an increasingly important task. As a medium of communication, microblogs carry peoples sentiments and express them to the public. Given that sentiments are driven by multiple factors including the news media, the question arises if the sentiment expressed in news and the news article themselves can be leveraged to detect and classify sentiment in microblogs. Prior research has highlighted the impact of sentiments and opinions on the market dynamics, making the financial domain a prime case study for this approach. Therefore, this paper describes ongoing research dealing with the exploitation of news contained sentiment to improve microblog sentiment classification in a financial context. |
| Tasks | Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3107/ |
| https://www.aclweb.org/anthology/W18-3107 | |
| PWC | https://paperswithcode.com/paper/leveraging-news-sentiment-to-improve |
| Repo | |
| Framework | |
Achieving morphological agreement with Concorde
| Title | Achieving morphological agreement with Concorde |
| Authors | Daniil Polykovskiy, Dmitry Soloviev |
| Abstract | Neural conversational models are widely used in applications like personal assistants and chat bots. These models seem to give better performance when operating on word level. However, for fusion languages like French, Russian and Polish vocabulary size sometimes become infeasible since most of the words have lots of word forms. We propose a neural network architecture for transforming normalized text into a grammatically correct one. Our model efficiently employs correspondence between normalized and target words and significantly outperforms character-level models while being 2x faster in training and 20% faster at evaluation. We also propose a new pipeline for building conversational models: first generate a normalized answer and then transform it into a grammatically correct one using our network. The proposed pipeline gives better performance than character-level conversational models according to assessor testing. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HyTrSegCb |
| https://openreview.net/pdf?id=HyTrSegCb | |
| PWC | https://paperswithcode.com/paper/achieving-morphological-agreement-with |
| Repo | |
| Framework | |
Language Identification and Analysis of Code-Switched Social Media Text
| Title | Language Identification and Analysis of Code-Switched Social Media Text |
| Authors | Deepthi Mave, Suraj Maharjan, Thamar Solorio |
| Abstract | In this paper, we detail our work on comparing different word-level language identification systems for code-switched Hindi-English data and a standard Spanish-English dataset. In this regard, we build a new code-switched dataset for Hindi-English. To understand the code-switching patterns in these language pairs, we investigate different code-switching metrics. We find that the CRF model outperforms the neural network based models by a margin of 2-5 percentage points for Spanish-English and 3-5 percentage points for Hindi-English. |
| Tasks | Language Identification, Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3206/ |
| https://www.aclweb.org/anthology/W18-3206 | |
| PWC | https://paperswithcode.com/paper/language-identification-and-analysis-of-code |
| Repo | |
| Framework | |
Artwork Recognition for Panorama Images Based on Optimized ASIFT and Cubic Projection
| Title | Artwork Recognition for Panorama Images Based on Optimized ASIFT and Cubic Projection |
| Authors | Dayou, Jiang; Jongweon, Kim |
| Abstract | Few studies have been published on object recognition for panorama images. To prevent the infringement of artworks in 360-degree images, we put forward an efficient method for artworks recognition inside 360-degree images in this paper. To start with, we employed the improved cubic projection to transform the distorted panorama image. Then, we used the optimized Affine Invariant Feature Transform (ASIFT) algorithm for extracting local features of the transformed image. Finally, the feature point matching is based on one-to-one mapping constraint. The overall performance of the method is investigated on panorama dataset and the experimental results are compared with other well-known local feature extraction methods and original panorama image. The experimental results show that using the proposed method can improve around 30% of the accuracy for relatively higher distorted panorama images and reduce the computing time. |
| Tasks | Object Recognition |
| Published | 2018-02-01 |
| URL | http://www.ijmlc.org/index.php?m=content&c=index&a=show&catid=76&id=770 |
| http://www.ijmlc.org/index.php?m=content&c=index&a=show&catid=76&id=770 | |
| PWC | https://paperswithcode.com/paper/artwork-recognition-for-panorama-images-based |
| Repo | |
| Framework | |
Modeling Second-Language Learning from a Psychological Perspective
| Title | Modeling Second-Language Learning from a Psychological Perspective |
| Authors | Alex Rich, er, Pamela Osborn Popp, David Halpern, Anselm Rothe, Todd Gureckis |
| Abstract | Psychological research on learning and memory has tended to emphasize small-scale laboratory studies. However, large datasets of people using educational software provide opportunities to explore these issues from a new perspective. In this paper we describe our approach to the Duolingo Second Language Acquisition Modeling (SLAM) competition which was run in early 2018. We used a well-known class of algorithms (gradient boosted decision trees), with features partially informed by theories from the psychological literature. After detailing our modeling approach and a number of supplementary simulations, we reflect on the degree to which psychological theory aided the model, and the potential for cognitive science and predictive modeling competitions to gain from each other. |
| Tasks | Language Acquisition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0526/ |
| https://www.aclweb.org/anthology/W18-0526 | |
| PWC | https://paperswithcode.com/paper/modeling-second-language-learning-from-a |
| Repo | |
| Framework | |
Texture Mapping for 3D Reconstruction With RGB-D Sensor
| Title | Texture Mapping for 3D Reconstruction With RGB-D Sensor |
| Authors | Yanping Fu, Qingan Yan, Long Yang, Jie Liao, Chunxia Xiao |
| Abstract | Acquiring realistic texture details for 3D models is important in 3D reconstruction. However, the existence of geometric errors, caused by noisy RGB-D sensor data, always makes the color images cannot be accurately aligned onto reconstructed 3D models. In this paper, we propose a global-to-local correction strategy to obtain more desired texture mapping results. Our algorithm first adaptively selects an optimal image for each face of the 3D model, which can effectively remove blurring and ghost artifacts produced by multiple image blending. We then adopt a non-rigid global-to-local correction step to reduce the seaming effect between textures. This can effectively compensate for the texture and the geometric misalignment caused by camera pose drift and geometric errors. We evaluate the proposed algorithm in a range of complex scenes and demonstrate its effective performance in generating seamless high fidelity textures for 3D models. |
| Tasks | 3D Reconstruction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Fu_Texture_Mapping_for_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Fu_Texture_Mapping_for_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/texture-mapping-for-3d-reconstruction-with |
| Repo | |
| Framework | |
Sense-Aware Neural Models for Pun Location in Texts
| Title | Sense-Aware Neural Models for Pun Location in Texts |
| Authors | Yitao Cai, Yin Li, Xiaojun Wan |
| Abstract | A homographic pun is a form of wordplay in which one signifier (usually a word) suggests two or more meanings by exploiting polysemy for an intended humorous or rhetorical effect. In this paper, we focus on the task of pun location, which aims to identify the pun word in a given short text. We propose a sense-aware neural model to address this challenging task. Our model first obtains several WSD results for the text, and then leverages a bidirectional LSTM network to model each sequence of word senses. The outputs at each time step for different LSTM networks are then concatenated for prediction. Evaluation results on the benchmark SemEval 2017 dataset demonstrate the efficacy of our proposed model. |
| Tasks | Word Sense Disambiguation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2087/ |
| https://www.aclweb.org/anthology/P18-2087 | |
| PWC | https://paperswithcode.com/paper/sense-aware-neural-models-for-pun-location-in |
| Repo | |
| Framework | |
Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization
| Title | Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization |
| Authors | Jilei Wang, Shiying Luo, Weiyan Shi, Tao Dai, Shu-Tao Xia |
| Abstract | Learning vector space representation of words (i.e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario. Currently most cross-lingual word embedding learning models are based on sentence alignment, which inevitably introduces much noise. In this paper, we show in Chinese and Japanese, the acquisition of semantic relation among words can benefit from the large number of common characters shared by both languages; inspired by this unique feature, we design a method named CJC targeting to generate cross-lingual context of words. We combine CJC with GloVe based on matrix factorization, and then propose an integrated model named CJ-Glo. Taking two sentence-aligned models and CJ-BOC (also exploits common characters but is based on CBOW) as baseline algorithms, we compare them with CJ-Glo on a series of NLP tasks including cross-lingual synonym, word analogy and sentence alignment. The result indicates CJ-Glo achieves the best performance among these methods, and is more stable in cross-lingual tasks; moreover, compared with CJ-BOC, CJ-Glo is less sensitive to the alteration of parameters. |
| Tasks | Machine Translation, Representation Learning, Word Embeddings, Word Sense Disambiguation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3015/ |
| https://www.aclweb.org/anthology/W18-3015 | |
| PWC | https://paperswithcode.com/paper/exploiting-common-characters-in-chinese-and |
| Repo | |
| Framework | |
