Paper Group NANR 268
Phone Merging For Code-Switched Speech Recognition. KDE-AFFECT at SemEval-2018 Task 1: Estimation of Affects in Tweet by Using Convolutional Neural Network for n-gram. RNN for Affects at SemEval-2018 Task 1: Formulating Affect Identification as a Binary Classification Problem. Predicting Multiple Actions for Stochastic Continuous Control. An Ensemb …
Phone Merging For Code-Switched Speech Recognition
Title | Phone Merging For Code-Switched Speech Recognition |
Authors | Sunit Sivasankaran, Brij Mohan Lal Srivastava, Sunayana Sitaram, Kalika Bali, Monojit Choudhury |
Abstract | Speakers in multilingual communities often switch between or mix multiple languages in the same conversation. Automatic Speech Recognition (ASR) of code-switched speech faces many challenges including the influence of phones of different languages on each other. This paper shows evidence that phone sharing between languages improves the Acoustic Model performance for Hindi-English code-switched speech. We compare baseline system built with separate phones for Hindi and English with systems where the phones were manually merged based on linguistic knowledge. Encouraged by the improved ASR performance after manually merging the phones, we further investigate multiple data-driven methods to identify phones to be merged across the languages. We show detailed analysis of automatic phone merging in this language pair and the impact it has on individual phone accuracies and WER. Though the best performance gain of 1.2{%} WER was observed with manually merged phones, we show experimentally that the manual phone merge is not optimal. |
Tasks | Speech Recognition |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-3202/ |
https://www.aclweb.org/anthology/W18-3202 | |
PWC | https://paperswithcode.com/paper/phone-merging-for-code-switched-speech |
Repo | |
Framework | |
KDE-AFFECT at SemEval-2018 Task 1: Estimation of Affects in Tweet by Using Convolutional Neural Network for n-gram
Title | KDE-AFFECT at SemEval-2018 Task 1: Estimation of Affects in Tweet by Using Convolutional Neural Network for n-gram |
Authors | Masaki Aono, Shinnosuke Himeno |
Abstract | This paper describes our approach to SemEval-2018 Task1: Estimation of Affects in Tweet for 1a and 2a. Our team KDE-AFFECT employs several methods including one-dimensional Convolutional Neural Network for $n$-grams, together with word embedding and other preprocessing such as vocabulary unification and Emoji conversion into four emotional words. |
Tasks | Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1022/ |
https://www.aclweb.org/anthology/S18-1022 | |
PWC | https://paperswithcode.com/paper/kde-affect-at-semeval-2018-task-1-estimation |
Repo | |
Framework | |
RNN for Affects at SemEval-2018 Task 1: Formulating Affect Identification as a Binary Classification Problem
Title | RNN for Affects at SemEval-2018 Task 1: Formulating Affect Identification as a Binary Classification Problem |
Authors | Aysu Ezen-Can, Ethem F. Can |
Abstract | Written communication lacks the multimodal features such as posture, gesture and gaze that make it easy to model affective states. Especially in social media such as Twitter, due to the space constraints, the sources of information that can be mined are even more limited due to character limitations. These limitations constitute a challenge for understanding short social media posts. In this paper, we present an approach that utilizes multiple binary classifiers that represent different affective categories to model Twitter posts (e.g., tweets). We train domain-independent recurrent neural network models without any outside information such as affect lexicons. We then use these domain independent binary ranking models to evaluate the applicability of such deep learning models on the affect identification task. This approach allows different model architectures and parameter settings for each affect category instead of building one single multi-label classifier. The contributions of this paper are two-folds: we show that modeling tweets with a small training set is possible with the use of RNNs and we also prove that formulating affect identification as a binary classification task is highly effective. |
Tasks | Action Recognition In Videos, Temporal Action Localization |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1023/ |
https://www.aclweb.org/anthology/S18-1023 | |
PWC | https://paperswithcode.com/paper/rnn-for-affects-at-semeval-2018-task-1 |
Repo | |
Framework | |
Predicting Multiple Actions for Stochastic Continuous Control
Title | Predicting Multiple Actions for Stochastic Continuous Control |
Authors | Sanjeev Kumar, Christian Rupprecht, Federico Tombari, Gregory D. Hager |
Abstract | We introduce a new approach to estimate continuous actions using actor-critic algorithms for reinforcement learning problems. Policy gradient methods usually predict one continuous action estimate or parameters of a presumed distribution (most commonly Gaussian) for any given state which might not be optimal as it may not capture the complete description of the target distribution. Our approach instead predicts M actions with the policy network (actor) and then uniformly sample one action during training as well as testing at each state. This allows the agent to learn a simple stochastic policy that has an easy to compute expected return. In all experiments, this facilitates better exploration of the state space during training and converges to a better policy. |
Tasks | Continuous Control, Policy Gradient Methods |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=SJgf6Z-0W |
https://openreview.net/pdf?id=SJgf6Z-0W | |
PWC | https://paperswithcode.com/paper/predicting-multiple-actions-for-stochastic |
Repo | |
Framework | |
An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems.
Title | An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems. |
Authors | Yiping Song, Rui Yan, Cheng-Te Li, Jian-Yun Nie, Ming Zhang, Dongyan Zhao |
Abstract | Human-computer conversation systems have attracted much attention in Natural Language Processing. Conversation systems can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (namely a query) in a large conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based conversation system. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble system outperforms each single module by a large margin. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=Sk03Yi10Z |
https://openreview.net/pdf?id=Sk03Yi10Z | |
PWC | https://paperswithcode.com/paper/an-ensemble-of-retrieval-based-and-generation |
Repo | |
Framework | |
Importance of Self-Attention for Sentiment Analysis
Title | Importance of Self-Attention for Sentiment Analysis |
Authors | Ga{"e}l Letarte, Fr{'e}d{'e}rik Paradis, Philippe Gigu{`e}re, Fran{\c{c}}ois Laviolette |
Abstract | Despite their superior performance, deep learning models often lack interpretability. In this paper, we explore the modeling of insightful relations between words, in order to understand and enhance predictions. To this effect, we propose the Self-Attention Network (SANet), a flexible and interpretable architecture for text classification. Experiments indicate that gains obtained by self-attention is task-dependent. For instance, experiments on sentiment analysis tasks showed an improvement of around 2{%} when using self-attention compared to a baseline without attention, while topic classification showed no gain. Interpretability brought forward by our architecture highlighted the importance of neighboring word interactions to extract sentiment. |
Tasks | Decision Making, Image Captioning, Language Modelling, Machine Translation, Sentiment Analysis, Text Classification, Word Embeddings |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-5429/ |
https://www.aclweb.org/anthology/W18-5429 | |
PWC | https://paperswithcode.com/paper/importance-of-self-attention-for-sentiment |
Repo | |
Framework | |
ISCLAB at SemEval-2018 Task 1: UIR-Miner for Affect in Tweets
Title | ISCLAB at SemEval-2018 Task 1: UIR-Miner for Affect in Tweets |
Authors | Meng Li, Zhenyuan Dong, Zhihao Fan, Kongming Meng, Jinghua Cao, Guanqi Ding, Yuhan Liu, Jiawei Shan, Binyang Li |
Abstract | This paper presents a UIR-Miner system for emotion and sentiment analysis evaluation in Twitter in SemEval 2018. Our system consists of three main modules: preprocessing module, stacking module to solve the intensity prediction of emotion and sentiment, LSTM network module to solve multi-label classification, and the hierarchical attention network module for solving emotion and sentiment classification problem. According to the metrics of SemEval 2018, our system gets the final scores of 0.636, 0.531, 0.731, 0.708, and 0.408 on 5 subtasks, respectively. |
Tasks | Emotion Classification, Multi-Label Classification, Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1042/ |
https://www.aclweb.org/anthology/S18-1042 | |
PWC | https://paperswithcode.com/paper/isclab-at-semeval-2018-task-1-uir-miner-for |
Repo | |
Framework | |
TCS Research at SemEval-2018 Task 1: Learning Robust Representations using Multi-Attention Architecture
Title | TCS Research at SemEval-2018 Task 1: Learning Robust Representations using Multi-Attention Architecture |
Authors | Hardik Meisheri, Lipika Dey |
Abstract | This paper presents system description of our submission to the SemEval-2018 task-1: Affect in tweets for the English language. We combine three different features generated using deep learning models and traditional methods in support vector machines to create a unified ensemble system. A robust representation of a tweet is learned using a multi-attention based architecture which uses a mixture of different pre-trained embeddings. In addition to this analysis of different features is also presented. Our system ranked 2nd, 5th, and 7th in different subtasks among 75 teams. |
Tasks | Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1043/ |
https://www.aclweb.org/anthology/S18-1043 | |
PWC | https://paperswithcode.com/paper/tcs-research-at-semeval-2018-task-1-learning |
Repo | |
Framework | |
Seeking the Ideal Narrative Model for Computer-Generated Narratives
Title | Seeking the Ideal Narrative Model for Computer-Generated Narratives |
Authors | Mariana Ferreira, Hugo Gon{\c{c}}alo Oliveira |
Abstract | |
Tasks | Text Generation |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-6602/ |
https://www.aclweb.org/anthology/W18-6602 | |
PWC | https://paperswithcode.com/paper/seeking-the-ideal-narrative-model-for |
Repo | |
Framework | |
Developing the Bangla RST Discourse Treebank
Title | Developing the Bangla RST Discourse Treebank |
Authors | Debopam Das, Manfred Stede |
Abstract | |
Tasks | Machine Translation, Sentiment Analysis, Text Generation, Text Summarization |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1288/ |
https://www.aclweb.org/anthology/L18-1288 | |
PWC | https://paperswithcode.com/paper/developing-the-bangla-rst-discourse-treebank |
Repo | |
Framework | |
SSN MLRG1 at SemEval-2018 Task 1: Emotion and Sentiment Intensity Detection Using Rule Based Feature Selection
Title | SSN MLRG1 at SemEval-2018 Task 1: Emotion and Sentiment Intensity Detection Using Rule Based Feature Selection |
Authors | Angel Deborah S, Rajalakshmi S, S Milton Rajendram, Mirnalinee T T |
Abstract | The system developed by the SSN MLRG1 team for Semeval-2018 task 1 on affect in tweets uses rule based feature selection and one-hot encoding to generate the input feature vector. Multilayer Perceptron was used to build the model for emotion intensity ordinal classification, sentiment analysis ordinal classification and emotion classfication subtasks. Support Vector Machine was used to build the model for emotion intensity regression and sentiment intensity regression subtasks. |
Tasks | Feature Selection, Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1048/ |
https://www.aclweb.org/anthology/S18-1048 | |
PWC | https://paperswithcode.com/paper/ssn-mlrg1-at-semeval-2018-task-1-emotion-and |
Repo | |
Framework | |
TeamCEN at SemEval-2018 Task 1: Global Vectors Representation in Emotion Detection
Title | TeamCEN at SemEval-2018 Task 1: Global Vectors Representation in Emotion Detection |
Authors | Anon George, Barathi Ganesh H. B., An Kumar M, , Soman K P |
Abstract | Emotions are a way of expressing human sentiments. In the modern era, social media is a platform where we convey our emotions. These emotions can be joy, anger, sadness and fear. Understanding the emotions from the written sentences is an interesting part in knowing about the writer. In the amount of digital language shared through social media, a considerable amount of data reflects the sentiment or emotion towards some product, person and organization. Since these texts are from users with diverse social aspects, these texts can be used to enrich the application related to the business intelligence. More than the sentiment, identification of intensity of the sentiment will enrich the performance of the end application. In this paper we experimented the intensity prediction as a text classification problem that evaluates the distributed representation text using aggregated sum and dimensionality reduction of the glove vectors of the words present in the respective texts . |
Tasks | Dimensionality Reduction, Text Classification |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1050/ |
https://www.aclweb.org/anthology/S18-1050 | |
PWC | https://paperswithcode.com/paper/teamcen-at-semeval-2018-task-1-global-vectors |
Repo | |
Framework | |
Neural Graph Matching Networks for Fewshot 3D Action Recognition
Title | Neural Graph Matching Networks for Fewshot 3D Action Recognition |
Authors | Michelle Guo, Edward Chou, De-An Huang, Shuran Song, Serena Yeung, Li Fei-Fei |
Abstract | We propose Neural Graph Matching (NGM) Networks, a novel framework that can learn to recognize a previous unseen 3D action class with only a few examples. We achieve this by leveraging the inherent structure of 3D data through a graphical representation. This allows us to modularize our model and lead to strong data-efficiency in few-shot learning. More specifically, NGM Networks jointly learn a graph generator and a graph matching metric function in a end-to-end fashion to directly optimize the few-shot learning objective. We evaluate NGM on two 3D action recognition datasets, CAD-120 and PiGraphs, and show that learning to generate and match graphs both lead to significant improvement of few-shot 3D action recognition over the holistic baselines. |
Tasks | 3D Human Action Recognition, Few-Shot Learning, Graph Matching, Skeleton Based Action Recognition, Temporal Action Localization |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Michelle_Guo_Neural_Graph_Matching_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Michelle_Guo_Neural_Graph_Matching_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/neural-graph-matching-networks-for-fewshot-3d |
Repo | |
Framework | |
Matching Adversarial Networks
Title | Matching Adversarial Networks |
Authors | Gellért Máttyus, Raquel Urtasun |
Abstract | Generative Adversarial Nets (GANs) and Conditonal GANs (CGANs) show that using a trained network as loss function (discriminator) enables to synthesize highly structured outputs (e.g. natural images). However, applying a discriminator network as a universal loss function for common supervised tasks (e.g. semantic segmentation, line detection, depth estimation) is considerably less successful. We argue that the main difficulty of applying CGANs to supervised tasks is that the generator training consists of optimizing a loss function that does not depend directly on the ground truth labels. To overcome this, we propose to replace the discriminator with a matching network taking into account both the ground truth outputs as well as the generated examples. As a consequence, the generator loss function also depends on the targets of the training examples, thus facilitating learning. We demonstrate on three computer vision tasks that this approach can significantly outperform CGANs achieving comparable or superior results to task-specific solutions and results in stable training. Importantly, this is a general approach that does not require the use of task-specific loss functions. |
Tasks | Depth Estimation, Semantic Segmentation |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Mattyus_Matching_Adversarial_Networks_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Mattyus_Matching_Adversarial_Networks_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/matching-adversarial-networks |
Repo | |
Framework | |
TeamUNCC at SemEval-2018 Task 1: Emotion Detection in English and Arabic Tweets using Deep Learning
Title | TeamUNCC at SemEval-2018 Task 1: Emotion Detection in English and Arabic Tweets using Deep Learning |
Authors | Malak Abdullah, Samira Shaikh |
Abstract | Task 1 in the International Workshop SemEval 2018, Affect in Tweets, introduces five subtasks (El-reg, El-oc, V-reg, V-oc, and E-c) to detect the intensity of emotions in English, Arabic, and Spanish tweets. This paper describes TeamUNCC{'}s system to detect emotions in English and Arabic tweets. Our approach is novel in that we present the same architecture for all the five subtasks in both English and Arabic. The main input to the system is a combination of word2vec and doc2vec embeddings and a set of psycholinguistic features (e.g. from AffectTweets Weka-package). We apply a fully connected neural network architecture and obtain performance results that show substantial improvements in Spearman correlation scores over the baseline models provided by Task 1 organizers, (ranging from 0.03 to 0.23). TeamUNCC{'}s system ranks third in subtask El-oc and fourth in other subtasks for Arabic tweets. |
Tasks | Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1053/ |
https://www.aclweb.org/anthology/S18-1053 | |
PWC | https://paperswithcode.com/paper/teamuncc-at-semeval-2018-task-1-emotion |
Repo | |
Framework | |