Paper Group NANR 58
PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags. OpenSubtitles2018: Statistical Rescoring of Sentence Alignments in Large, Noisy Parallel Corpora. Universal Agent for Disentangling Environments and Tasks. Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere. A Bilingual Interactive Huma …
PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags
Title | PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags |
Authors | Ji Ho Park, Peng Xu, Pascale Fung |
Abstract | This paper describes our system that has been submitted to SemEval-2018 Task 1: Affect in Tweets (AIT) to solve five subtasks. We focus on modeling both sentence and word level representations of emotion inside texts through large distantly labeled corpora with emojis and hashtags. We transfer the emotional knowledge by exploiting neural network models as feature extractors and use these representations for traditional machine learning models such as support vector regression (SVR) and logistic regression to solve the competition tasks. Our system is placed among the Top3 for all subtasks we participated. |
Tasks | Emotion Classification, Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1039/ |
https://www.aclweb.org/anthology/S18-1039 | |
PWC | https://paperswithcode.com/paper/plusemo2vec-at-semeval-2018-task-1-exploiting-1 |
Repo | |
Framework | |
OpenSubtitles2018: Statistical Rescoring of Sentence Alignments in Large, Noisy Parallel Corpora
Title | OpenSubtitles2018: Statistical Rescoring of Sentence Alignments in Large, Noisy Parallel Corpora |
Authors | Pierre Lison, J{"o}rg Tiedemann, Milen Kouylekov |
Abstract | |
Tasks | Machine Translation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1275/ |
https://www.aclweb.org/anthology/L18-1275 | |
PWC | https://paperswithcode.com/paper/opensubtitles2018-statistical-rescoring-of |
Repo | |
Framework | |
Universal Agent for Disentangling Environments and Tasks
Title | Universal Agent for Disentangling Environments and Tasks |
Authors | Jiayuan Mao, Honghua Dong, Joseph J. Lim |
Abstract | Recent state-of-the-art reinforcement learning algorithms are trained under the goal of excelling in one specific task. Hence, both environment and task specific knowledge are entangled into one framework. However, there are often scenarios where the environment (e.g. the physical world) is fixed while only the target task changes. Hence, borrowing the idea from hierarchical reinforcement learning, we propose a framework that disentangles task and environment specific knowledge by separating them into two units. The environment-specific unit handles how to move from one state to the target state; and the task-specific unit plans for the next target state given a specific task. The extensive results in simulators indicate that our method can efficiently separate and learn two independent units, and also adapt to a new task more efficiently than the state-of-the-art methods. |
Tasks | Hierarchical Reinforcement Learning |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=B1mvVm-C- |
https://openreview.net/pdf?id=B1mvVm-C- | |
PWC | https://paperswithcode.com/paper/universal-agent-for-disentangling |
Repo | |
Framework | |
Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere
Title | Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere |
Authors | Yanjun Li, Yoram Bresler |
Abstract | Multichannel blind deconvolution is the problem of recovering an unknown signal $f$ and multiple unknown channels $x_i$ from convolutional measurements $y_i=x_i \circledast f$ ($i=1,2,\dots,N$). We consider the case where the $x_i$'s are sparse, and convolution with $f$ is invertible. Our nonconvex optimization formulation solves for a filter $h$ on the unit sphere that produces sparse output $y_i\circledast h$. Under some technical assumptions, we show that all local minima of the objective function correspond to the inverse filter of $f$ up to an inherent sign and shift ambiguity, and all saddle points have strictly negative curvatures. This geometric structure allows successful recovery of $f$ and $x_i$ using a simple manifold gradient descent algorithm with random initialization. Our theoretical findings are complemented by numerical experiments, which demonstrate superior performance of the proposed approach over the previous methods. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7390-global-geometry-of-multichannel-sparse-blind-deconvolution-on-the-sphere |
http://papers.nips.cc/paper/7390-global-geometry-of-multichannel-sparse-blind-deconvolution-on-the-sphere.pdf | |
PWC | https://paperswithcode.com/paper/global-geometry-of-multichannel-sparse-blind-1 |
Repo | |
Framework | |
A Bilingual Interactive Human Avatar Dialogue System
Title | A Bilingual Interactive Human Avatar Dialogue System |
Authors | Dana Abu Ali, Muaz Ahmad, Hayat Al Hassan, Paula Dozsa, Ming Hu, Jose Varias, Nizar Habash |
Abstract | This demonstration paper presents a bilingual (Arabic-English) interactive human avatar dialogue system. The system is named TOIA (time-offset interaction application), as it simulates face-to-face conversations between humans using digital human avatars recorded in the past. TOIA is a conversational agent, similar to a chat bot, except that it is based on an actual human being and can be used to preserve and tell stories. The system is designed to allow anybody, simply using a laptop, to create an avatar of themselves, thus facilitating cross-cultural and cross-generational sharing of narratives to wider audiences. The system currently supports monolingual and cross-lingual dialogues in Arabic and English, but can be extended to other languages. |
Tasks | Answer Selection, Speech Recognition |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-5027/ |
https://www.aclweb.org/anthology/W18-5027 | |
PWC | https://paperswithcode.com/paper/a-bilingual-interactive-human-avatar-dialogue |
Repo | |
Framework | |
Learning Sentence Representations over Tree Structures for Target-Dependent Classification
Title | Learning Sentence Representations over Tree Structures for Target-Dependent Classification |
Authors | Junwen Duan, Xiao Ding, Ting Liu |
Abstract | Target-dependent classification tasks, such as aspect-level sentiment analysis, perform fine-grained classifications towards specific targets. Semantic compositions over tree structures are promising for such tasks, as they can potentially capture long-distance interactions between targets and their contexts. However, previous work that operates on tree structures resorts to syntactic parsers or Treebank annotations, which are either subject to noise in informal texts or highly expensive to obtain. To address above issues, we propose a reinforcement learning based approach, which automatically induces target-specific sentence representations over tree structures. The underlying model is a RNN encoder-decoder that explores possible binary tree structures and a reward mechanism that encourages structures that improve performances on downstream tasks. We evaluate our approach on two benchmark tasks: firm-specific cumulative abnormal return prediction (based on formal news texts) and aspect-level sentiment analysis (based on informal social media texts). Experimental results show that our model gives superior performances compared to previous work that operates on parsed trees. Moreover, our approach gives some intuitions on how target-specific sentence representations can be achieved from its word constituents. |
Tasks | Information Retrieval, Sentiment Analysis, Stance Detection |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-1051/ |
https://www.aclweb.org/anthology/N18-1051 | |
PWC | https://paperswithcode.com/paper/learning-sentence-representations-over-tree |
Repo | |
Framework | |
Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices
Title | Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices |
Authors | Jinhwan Park, Yoonho Boo, Iksoo Choi, Sungho Shin, Wonyong Sung |
Abstract | Real-time automatic speech recognition (ASR) on mobile and embedded devices has been of great interests for many years. We present real-time speech recognition on smartphones or embedded systems by employing recurrent neural network (RNN) based acoustic models, RNN based language models, and beam-search decoding. The acoustic model is end-to-end trained with connectionist temporal classification (CTC) loss. The RNN implementation on embedded devices can suffer from excessive DRAM accesses because the parameter size of a neural network usually exceeds that of the cache memory and the parameters are used only once for each time step. To remedy this problem, we employ a multi-time step parallelization approach that computes multiple output samples at a time with the parameters fetched from the DRAM. Since the number of DRAM accesses can be reduced in proportion to the number of parallelization steps, we can achieve a high processing speed. However, conventional RNNs, such as long short-term memory (LSTM) or gated recurrent unit (GRU), do not permit multi-time step parallelization. We construct an acoustic model by combining simple recurrent units (SRUs) and depth-wise 1-dimensional convolution layers for multi-time step parallelization. Both the character and word piece models are developed for acoustic modeling, and the corresponding RNN based language models are used for beam search decoding. We achieve a competitive WER for WSJ corpus using the entire model size of around 15MB and achieve real-time speed using only a single core ARM without GPU or special hardware. |
Tasks | Speech Recognition |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8261-fully-neural-network-based-speech-recognition-on-mobile-and-embedded-devices |
http://papers.nips.cc/paper/8261-fully-neural-network-based-speech-recognition-on-mobile-and-embedded-devices.pdf | |
PWC | https://paperswithcode.com/paper/fully-neural-network-based-speech-recognition |
Repo | |
Framework | |
Twitter Geolocation using Knowledge-Based Methods
Title | Twitter Geolocation using Knowledge-Based Methods |
Authors | Taro Miyazaki, Afshin Rahimi, Trevor Cohn, Timothy Baldwin |
Abstract | Automatic geolocation of microblog posts from their text content is particularly difficult because many location-indicative terms are rare terms, notably entity names such as locations, people or local organisations. Their low frequency means that key terms observed in testing are often unseen in training, such that standard classifiers are unable to learn weights for them. We propose a method for reasoning over such terms using a knowledge base, through exploiting their relations with other entities. Our technique uses a graph embedding over the knowledge base, which we couple with a text representation to learn a geolocation classifier, trained end-to-end. We show that our method improves over purely text-based methods, which we ascribe to more robust treatment of low-count and out-of-vocabulary entities. |
Tasks | Entity Linking, Graph Embedding, Stock Market Prediction |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-6102/ |
https://www.aclweb.org/anthology/W18-6102 | |
PWC | https://paperswithcode.com/paper/twitter-geolocation-using-knowledge-based |
Repo | |
Framework | |
A vision-grounded dataset for predicting typical locations for verbs
Title | A vision-grounded dataset for predicting typical locations for verbs |
Authors | Nelson Mukuze, Anna Rohrbach, Vera Demberg, Bernt Schiele |
Abstract | |
Tasks | Common Sense Reasoning, Image Captioning |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1570/ |
https://www.aclweb.org/anthology/L18-1570 | |
PWC | https://paperswithcode.com/paper/a-vision-grounded-dataset-for-predicting |
Repo | |
Framework | |
Hybrid Attention based Multimodal Network for Spoken Language Classification
Title | Hybrid Attention based Multimodal Network for Spoken Language Classification |
Authors | Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, Ivan Marsic |
Abstract | We examine the utility of linguistic content and vocal characteristics for multimodal deep learning in human spoken language understanding. We present a deep multimodal network with both feature attention and modality attention to classify utterance-level speech data. The proposed hybrid attention architecture helps the system focus on learning informative representations for both modality-specific feature extraction and model fusion. The experimental results show that our system achieves state-of-the-art or competitive results on three published multimodal datasets. We also demonstrated the effectiveness and generalization of our system on a medical speech dataset from an actual trauma scenario. Furthermore, we provided a detailed comparison and analysis of traditional approaches and deep learning methods on both feature extraction and fusion. |
Tasks | Emotion Recognition, Sentiment Analysis, Spoken Language Understanding |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1201/ |
https://www.aclweb.org/anthology/C18-1201 | |
PWC | https://paperswithcode.com/paper/hybrid-attention-based-multimodal-network-for |
Repo | |
Framework | |
Dialogue Scenario Collection of Persuasive Dialogue with Emotional Expressions via Crowdsourcing
Title | Dialogue Scenario Collection of Persuasive Dialogue with Emotional Expressions via Crowdsourcing |
Authors | Koichiro Yoshino, Yoko Ishikawa, Masahiro Mizukami, Yu Suzuki, Sakriani Sakti, Satoshi Nakamura |
Abstract | |
Tasks | Dialogue Management |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1194/ |
https://www.aclweb.org/anthology/L18-1194 | |
PWC | https://paperswithcode.com/paper/dialogue-scenario-collection-of-persuasive |
Repo | |
Framework | |
Proceedings of the Workshop on Computational Semantics beyond Events and Roles
Title | Proceedings of the Workshop on Computational Semantics beyond Events and Roles |
Authors | |
Abstract | |
Tasks | |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-1300/ |
https://www.aclweb.org/anthology/W18-1300 | |
PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-computational-6 |
Repo | |
Framework | |
A Review on Deep Learning Techniques Applied to Answer Selection
Title | A Review on Deep Learning Techniques Applied to Answer Selection |
Authors | Tuan Manh Lai, Trung Bui, Sheng Li |
Abstract | Given a question and a set of candidate answers, answer selection is the task of identifying which of the candidates answers the question correctly. It is an important problem in natural language processing, with applications in many areas. Recently, many deep learning based methods have been proposed for the task. They produce impressive performance without relying on any feature engineering or expensive external resources. In this paper, we aim to provide a comprehensive review on deep learning methods applied to answer selection. |
Tasks | Answer Selection, Community Question Answering, Feature Engineering, Open-Domain Question Answering, Question Answering, Word Embeddings |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1181/ |
https://www.aclweb.org/anthology/C18-1181 | |
PWC | https://paperswithcode.com/paper/a-review-on-deep-learning-techniques-applied-1 |
Repo | |
Framework | |
Can adult mental health be predicted by childhood future-self narratives? Insights from the CLPsych 2018 Shared Task
Title | Can adult mental health be predicted by childhood future-self narratives? Insights from the CLPsych 2018 Shared Task |
Authors | Kylie Radford, Louise Lavrencic, Ruth Peters, Kim Kiely, Ben Hachey, Scott Nowson, Will Radford |
Abstract | The CLPsych 2018 Shared Task B explores how childhood essays can predict psychological distress throughout the author{'}s life. Our main aim was to build tools to help our psychologists understand the data, propose features and interpret predictions. We submitted two linear regression models: ModelA uses simple demographic and word-count features, while ModelB uses linguistic, entity, typographic, expert-gazetteer, and readability features. Our models perform best at younger prediction ages, with our best unofficial score at 23 of 0.426 disattenuated Pearson correlation. This task is challenging and although predictive performance is limited, we propose that tight integration of expertise across computational linguistics and clinical psychology is a productive direction. |
Tasks | Epidemiology |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0614/ |
https://www.aclweb.org/anthology/W18-0614 | |
PWC | https://paperswithcode.com/paper/can-adult-mental-health-be-predicted-by |
Repo | |
Framework | |
TriMED: A Multilingual Terminological Database
Title | TriMED: A Multilingual Terminological Database |
Authors | Federica Vezzani, Giorgio Maria Di Nunzio, Genevi{`e}ve Henrot |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1691/ |
https://www.aclweb.org/anthology/L18-1691 | |
PWC | https://paperswithcode.com/paper/trimed-a-multilingual-terminological-database |
Repo | |
Framework | |