Paper Group NANR 153
Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM. ECNU at SemEval-2018 Task 3: Exploration on Irony Detection from Tweets via Machine Learning and Deep Learning Methods. Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs. Divide and Conquer for Full-Resolution Light Field Deblurring. Code- …
Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
| Title | Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM |
| Authors | Yukun Ma, Haiyun Peng, Erik Cambria |
| Abstract | Analyzing people’s opinions and sentiments towards certain aspects is an important task of natural language understanding. In this paper, we propose a novel solution to targeted aspect-based sentiment analysis, which tackles the challenges of both aspect-based sentiment analysis and targeted sentiment analysis by exploiting commonsense knowledge. We augment the long short-term memory (LSTM) network with a hierarchical attention mechanism consisting of a target level attention and a sentence-level attention. Commonsense knowledge of sentiment-related concepts is incorporated into the end-to-end training of a deep neural network for sentiment classification. In order to tightly integrate the commonsense knowledge into the recurrent encoder, we propose an extension of LSTM, termed Sentic LSTM. We conduct experiments on two publicly released datasets, which show that the combination of the proposed attention architecture and Sentic LSTM can outperform state-of-the-art methods in targeted aspect sentiment tasks. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2018-04-01 |
| URL | https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/16541 |
| https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16541/16152 | |
| PWC | https://paperswithcode.com/paper/targeted-aspect-based-sentiment-analysis-via |
| Repo | |
| Framework | |
ECNU at SemEval-2018 Task 3: Exploration on Irony Detection from Tweets via Machine Learning and Deep Learning Methods
| Title | ECNU at SemEval-2018 Task 3: Exploration on Irony Detection from Tweets via Machine Learning and Deep Learning Methods |
| Authors | Zhenghang Yin, Feixiang Wang, Man Lan, Wenting Wang |
| Abstract | The paper describes our submissions to task 3 in SemEval-2018. There are two subtasks: Subtask A is a binary classification task to determine whether a tweet is ironic, and Subtask B is a fine-grained classification task including four classes. To address them, we explored supervised machine learning method alone and in combination with neural networks. |
| Tasks | Feature Engineering |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1098/ |
| https://www.aclweb.org/anthology/S18-1098 | |
| PWC | https://paperswithcode.com/paper/ecnu-at-semeval-2018-task-3-exploration-on |
| Repo | |
| Framework | |
Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs
| Title | Non-Blind Deblurring: Handling Kernel Uncertainty With CNNs |
| Authors | Subeesh Vasu, Venkatesh Reddy Maligireddy, A. N. Rajagopalan |
| Abstract | Blind motion deblurring methods are primarily responsible for recovering an accurate estimate of the blur kernel. Non-blind deblurring (NBD) methods, on the other hand, attempt to faithfully restore the original image, given the blur estimate. However, NBD is quite susceptible to errors in blur kernel. In this work, we present a convolutional neural network-based approach to handle kernel uncertainty in non-blind motion deblurring. We provide multiple latent image estimates corresponding to different prior strengths obtained from a given blurry observation in order to exploit the complementarity of these inputs for improved learning. To generalize the performance to tackle arbitrary kernel noise, we train our network with a large number of real and synthetic noisy blur kernels. Our network mitigates the effects of kernel noise so as to yield detail-preserving and artifact-free restoration. Our quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method delivers state-of-the-art results. To further underscore the benefits that can be achieved from our network, we propose two adaptations of our method to improve kernel estimates, and image deblurring quality, respectively. |
| Tasks | Deblurring |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Vasu_Non-Blind_Deblurring_Handling_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Vasu_Non-Blind_Deblurring_Handling_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/non-blind-deblurring-handling-kernel |
| Repo | |
| Framework | |
Divide and Conquer for Full-Resolution Light Field Deblurring
| Title | Divide and Conquer for Full-Resolution Light Field Deblurring |
| Authors | M. R. Mahesh Mohan, A. N. Rajagopalan |
| Abstract | The increasing popularity of computational light field (LF) cameras has necessitated the need for tackling motion blur which is a ubiquitous phenomenon in hand-held photography. The state-of-the-art method for blind deblurring of LFs of general 3D scenes is limited to handling only downsampled LF, both in spatial and angular resolution. This is due to the computational overhead involved in processing data-hungry full-resolution 4D LF altogether. Moreover, the method warrants high-end GPUs for optimization and is ineffective for wide-angle settings and irregular camera motion. In this paper, we introduce a new blind motion deblurring strategy for LFs which alleviates these limitations significantly. Our model achieves this by isolating 4D LF motion blur across the 2D subaperture images, thus paving the way for independent deblurring of these subaperture images. Furthermore, our model accommodates common camera motion parameterization across the subaperture images. Consequently, blind deblurring of any single subaperture image elegantly paves the way for cost-effective non-blind deblurring of the other subaperture images. Our approach is CPU-efficient computationally and can effectively deblur full-resolution LFs. |
| Tasks | Deblurring |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Mohan_Divide_and_Conquer_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Mohan_Divide_and_Conquer_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/divide-and-conquer-for-full-resolution-light |
| Repo | |
| Framework | |
Code-Mixed Question Answering Challenge: Crowd-sourcing Data and Techniques
| Title | Code-Mixed Question Answering Challenge: Crowd-sourcing Data and Techniques |
| Authors | Ch, Khyathi u, Ekaterina Loginova, Vishal Gupta, Josef van Genabith, G{"u}nter Neumann, Manoj Chinnakotla, Eric Nyberg, Alan W. Black |
| Abstract | Code-Mixing (CM) is the phenomenon of alternating between two or more languages which is prevalent in bi- and multi-lingual communities. Most NLP applications today are still designed with the assumption of a single interaction language and are most likely to break given a CM utterance with multiple languages mixed at a morphological, phrase or sentence level. For example, popular commercial search engines do not yet fully understand the intents expressed in CM queries. As a first step towards fostering research which supports CM in NLP applications, we systematically crowd-sourced and curated an evaluation dataset for factoid question answering in three CM languages - Hinglish (Hindi+English), Tenglish (Telugu+English) and Tamlish (Tamil+English) which belong to two language families (Indo-Aryan and Dravidian). We share the details of our data collection process, techniques which were used to avoid inducing lexical bias amongst the crowd workers and other CM specific linguistic properties of the dataset. Our final dataset, which is available freely for research purposes, has 1,694 Hinglish, 2,848 Tamlish and 1,391 Tenglish factoid questions and their answers. We discuss the techniques used by the participants for the first edition of this ongoing challenge. |
| Tasks | Question Answering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3204/ |
| https://www.aclweb.org/anthology/W18-3204 | |
| PWC | https://paperswithcode.com/paper/code-mixed-question-answering-challenge-crowd |
| Repo | |
| Framework | |
Simple Fast Convolutional Feature Learning
| Title | Simple Fast Convolutional Feature Learning |
| Authors | David Macêdo, Cleber Zanchettin, Teresa Ludermir |
| Abstract | The quality of the features used in visual recognition is of fundamental importance for the overall system. For a long time, low-level hand-designed feature algorithms as SIFT and HOG have obtained the best results on image recognition. Visual features have recently been extracted from trained convolutional neural networks. Despite the high-quality results, one of the main drawbacks of this approach, when compared with hand-designed features, is the training time required during the learning process. In this paper, we propose a simple and fast way to train supervised convolutional models to feature extraction while still maintaining its high-quality. This methodology is evaluated on different datasets and compared with state-of-the-art approaches. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SyGT_6yCZ |
| https://openreview.net/pdf?id=SyGT_6yCZ | |
| PWC | https://paperswithcode.com/paper/simple-fast-convolutional-feature-learning |
| Repo | |
| Framework | |
Generating Informative Responses with Controlled Sentence Function
| Title | Generating Informative Responses with Controlled Sentence Function |
| Authors | Pei Ke, Jian Guan, Minlie Huang, Xiaoyan Zhu |
| Abstract | Sentence function is a significant factor to achieve the purpose of the speaker, which, however, has not been touched in large-scale conversation generation so far. In this paper, we present a model to generate informative responses with controlled sentence function. Our model utilizes a continuous latent variable to capture various word patterns that realize the expected sentence function, and introduces a type controller to deal with the compatibility of controlling sentence function and generating informative content. Conditioned on the latent variable, the type controller determines the type (i.e., function-related, topic, and ordinary word) of a word to be generated at each decoding position. Experiments show that our model outperforms state-of-the-art baselines, and it has the ability to generate responses with both controlled sentence function and informative content. |
| Tasks | Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1139/ |
| https://www.aclweb.org/anthology/P18-1139 | |
| PWC | https://paperswithcode.com/paper/generating-informative-responses-with |
| Repo | |
| Framework | |
Enabling Code-Mixed Translation: Parallel Corpus Creation and MT Augmentation Approach
| Title | Enabling Code-Mixed Translation: Parallel Corpus Creation and MT Augmentation Approach |
| Authors | Mrinal Dhar, Vaibhav Kumar, Manish Shrivastava |
| Abstract | Code-mixing, use of two or more languages in a single sentence, is ubiquitous; generated by multi-lingual speakers across the world. The phenomenon presents itself prominently in social media discourse. Consequently, there is a growing need for translating code-mixed hybrid language into standard languages. However, due to the lack of gold parallel data, existing machine translation systems fail to properly translate code-mixed text. In an effort to initiate the task of machine translation of code-mixed content, we present a newly created parallel corpus of code-mixed English-Hindi and English. We selected previously available English-Hindi code-mixed data as a starting point for the creation of our parallel corpus. We then chose 4 human translators, fluent in both English and Hindi, for translating the 6088 code-mixed English-Hindi sentences to English. With the help of the created parallel corpus, we analyzed the structure of English-Hindi code-mixed data and present a technique to augment run-of-the-mill machine translation (MT) approaches that can help achieve superior translations without the need for specially designed translation systems. We present an augmentation pipeline for existing MT approaches, like Phrase Based MT (Moses) and Neural MT, to improve the translation of code-mixed text. The augmentation pipeline is presented as a pre-processing step and can be plugged with any existing MT system, which we demonstrate by improving translations done by systems like Moses, Google Neural Machine Translation System (NMTS) and Bing Translator for English-Hindi code-mixed content. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3817/ |
| https://www.aclweb.org/anthology/W18-3817 | |
| PWC | https://paperswithcode.com/paper/enabling-code-mixed-translation-parallel |
| Repo | |
| Framework | |
Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage Pipelines
| Title | Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage Pipelines |
| Authors | Shuqin Xie, Zitian Chen, Chao Xu, Cewu Lu |
| Abstract | Recent advances in multi-stage algorithms have shown great promise, but two important problems still remain. First of all, at inference time, information can’t feed back from downstream to upstream. Second, at training time, end-to-end training is not possible if the overall pipeline involves non-differentiable functions, and so different stages can’t be jointly optimized. In this paper, we propose a novel environment upgrade reinforcement learning framework to solve the feedback and joint optimization problems. Our framework re-links the downstream stage to the upstream stage by a reinforcement learning agent. While training the agent to improve final performance by refining the upstream stage’s output, we also upgrade the downstream stage (environment) according to the agent’s policy. In this way, agent policy and environment are jointly optimized. We propose a training algorithm for this framework to address the different training demands of agent and environment. Experiments on instance segmentation and human pose estimation demonstrate the effectiveness of the proposed framework. |
| Tasks | Instance Segmentation, Pose Estimation, Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Xie_Environment_Upgrade_Reinforcement_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Xie_Environment_Upgrade_Reinforcement_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/environment-upgrade-reinforcement-learning |
| Repo | |
| Framework | |
Weakly Supervised Coupled Networks for Visual Sentiment Analysis
| Title | Weakly Supervised Coupled Networks for Visual Sentiment Analysis |
| Authors | Jufeng Yang, Dongyu She, Yu-Kun Lai, Paul L. Rosin, Ming-Hsuan Yang |
| Abstract | Automatic assessment of sentiment from visual content has gained considerable attention with the increasing tendency of expressing opinions on-line. In this paper, we solve the problem of visual sentiment analysis using the high-level abstraction in the recognition process. Existing methods based on convolutional neural networks learn sentiment representations from the holistic image appearance. However, different image regions can have a different influence on the intended expression. This paper presents a weakly supervised coupled convolutional network with two branches to leverage the localized information. The first branch detects a sentiment specific soft map by training a fully convolutional network with the cross spatial pooling strategy, which only requires image-level labels, thereby significantly reducing the annotation burden. The second branch utilizes both the holistic and localized information by coupling the sentiment map with deep features for robust classification. We integrate the sentiment detection and classification branches into a unified deep framework and optimize the network in an end-to-end manner. Extensive experiments on six benchmark datasets demonstrate that the proposed method performs favorably against the state-ofthe-art methods for visual sentiment analysis. |
| Tasks | Sentiment Analysis |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Yang_Weakly_Supervised_Coupled_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Weakly_Supervised_Coupled_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-coupled-networks-for-visual |
| Repo | |
| Framework | |
Enabling Deep Learning of Emotion With First-Person Seed Expressions
| Title | Enabling Deep Learning of Emotion With First-Person Seed Expressions |
| Authors | Hassan Alhuzali, Muhammad Abdul-Mageed, Lyle Ungar |
| Abstract | The computational treatment of emotion in natural language text remains relatively limited, and Arabic is no exception. This is partly due to lack of labeled data. In this work, we describe and manually validate a method for the automatic acquisition of emotion labeled data and introduce a newly developed data set for Modern Standard and Dialectal Arabic emotion detection focused at Robert Plutchik{'}s 8 basic emotion types. Using a hybrid supervision method that exploits first person emotion seeds, we show how we can acquire promising results with a deep gated recurrent neural network. Our best model reaches 70{%} \textit{F}-score, significantly (i.e., 11{%}, $p < 0.05$) outperforming a competitive baseline. Applying our method and data on an external dataset of 4 emotions released around the same time we finalized our work, we acquire 7{%} absolute gain in $F$-score over a linear SVM classifier trained on gold data, thus validating our approach. |
| Tasks | Emotion Recognition, Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1104/ |
| https://www.aclweb.org/anthology/W18-1104 | |
| PWC | https://paperswithcode.com/paper/enabling-deep-learning-of-emotion-with-first |
| Repo | |
| Framework | |
Modeling the Decline in English Passivization
| Title | Modeling the Decline in English Passivization |
| Authors | Liwen Hou, David Smith |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0304/ |
| https://www.aclweb.org/anthology/W18-0304 | |
| PWC | https://paperswithcode.com/paper/modeling-the-decline-in-english-passivization |
| Repo | |
| Framework | |
DFKI-MLT System Description for the WMT18 Automatic Post-editing Task
| Title | DFKI-MLT System Description for the WMT18 Automatic Post-editing Task |
| Authors | Daria Pylypenko, Raphael Rubino |
| Abstract | This paper presents the Automatic Post-editing (APE) systems submitted by the DFKI-MLT group to the WMT{'}18 APE shared task. Three monolingual neural sequence-to-sequence APE systems were trained using target-language data only: one using an attentional recurrent neural network architecture and two using the attention-only (\textit{transformer}) architecture. The training data was composed of machine translated (MT) output used as source to the APE model aligned with their manually post-edited version or reference translation as target. We made use of the provided training sets only and trained APE models applicable to phrase-based and neural MT outputs. Results show better performances reached by the attention-only model over the recurrent one, significant improvement over the baseline when post-editing phrase-based MT output but degradation when applied to neural MT output. |
| Tasks | Automatic Post-Editing, Machine Translation, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6469/ |
| https://www.aclweb.org/anthology/W18-6469 | |
| PWC | https://paperswithcode.com/paper/dfki-mlt-system-description-for-the-wmt18 |
| Repo | |
| Framework | |
Detecting Language Impairments in Autism: A Computational Analysis of Semi-structured Conversations with Vector Semantics
| Title | Detecting Language Impairments in Autism: A Computational Analysis of Semi-structured Conversations with Vector Semantics |
| Authors | Adam Goodkind, Michelle Lee, Gary E. Martin, Molly Losh, Klinton Bicknell |
| Abstract | |
| Tasks | Semantic Textual Similarity |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0302/ |
| https://www.aclweb.org/anthology/W18-0302 | |
| PWC | https://paperswithcode.com/paper/detecting-language-impairments-in-autism-a |
| Repo | |
| Framework | |
Linguistically-driven Framework for Computationally Efficient and Scalable Sign Recognition
| Title | Linguistically-driven Framework for Computationally Efficient and Scalable Sign Recognition |
| Authors | Dimitris Metaxas, Mark Dilsizian, Carol Neidle |
| Abstract | |
| Tasks | Time Series |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1271/ |
| https://www.aclweb.org/anthology/L18-1271 | |
| PWC | https://paperswithcode.com/paper/linguistically-driven-framework-for |
| Repo | |
| Framework | |
