Paper Group NANR 37
![Paper Group NANR 37](/2018/images/pwc/paper-all_hu5eb227011acad6b922a57ded5f50b7dc_25576_900x500_fit_q75_box.jpg)
Designing a Croatian Aspectual Derivatives Dictionary: Preliminary Stages. Building a Sentiment Corpus of Tweets in Brazilian Portuguese. Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study. Deep Neural Models of Semantic Shift. Dual-Agent Deep Reinforcement Learning for Deformabl …
Designing a Croatian Aspectual Derivatives Dictionary: Preliminary Stages
Title | Designing a Croatian Aspectual Derivatives Dictionary: Preliminary Stages |
Authors | Kristina Kocijan, Kre{\v{s}}imir {\v{S}}ojat, Dario Poljak |
Abstract | The paper focusses on derivationally connected verbs in Croatian, i.e. on verbs that share the same lexical morpheme and are derived from other verbs via prefixation, suffixation and/or stem alternations. As in other Slavic languages with rich derivational morphology, each verb is marked for aspect, either perfective or imperfective. Some verbs, mostly of foreign origin, are marked as bi-aspectual verbs. The main objective of this paper is to detect and to describe major derivational processes and affixes used in the derivation of aspectually connected verbs with NooJ. Annotated chains are exported into a format adequate for web database system and further used to enhance the aspectual and derivational information for each verb. |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-3805/ |
https://www.aclweb.org/anthology/W18-3805 | |
PWC | https://paperswithcode.com/paper/designing-a-croatian-aspectual-derivatives |
Repo | |
Framework | |
Building a Sentiment Corpus of Tweets in Brazilian Portuguese
Title | Building a Sentiment Corpus of Tweets in Brazilian Portuguese |
Authors | Henrico Brum, Maria das Gra{\c{c}}as Volpe Nunes |
Abstract | |
Tasks | Sentiment Analysis |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1658/ |
https://www.aclweb.org/anthology/L18-1658 | |
PWC | https://paperswithcode.com/paper/building-a-sentiment-corpus-of-tweets-in |
Repo | |
Framework | |
Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study
Title | Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study |
Authors | David Macêdo, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir |
Abstract | In this paper, we turn our attention to the interworking between the activation functions and the batch normalization, which is a virtually mandatory technique to train deep networks currently. We propose the activation function Displaced Rectifier Linear Unit (DReLU) by conjecturing that extending the identity function of ReLU to the third quadrant enhances compatibility with batch normalization. Moreover, we used statistical tests to compare the impact of using distinct activation functions (ReLU, LReLU, PReLU, ELU, and DReLU) on the learning speed and test accuracy performance of standardized VGG and Residual Networks state-of-the-art models. These convolutional neural networks were trained on CIFAR-100 and CIFAR-10, the most commonly used deep learning computer vision datasets. The results showed DReLU speeded up learning in all models and datasets. Besides, statistical significant performance assessments (p<0.05) showed DReLU enhanced the test accuracy presented by ReLU in all scenarios. Furthermore, DReLU showed better test accuracy than any other tested activation function in all experiments with one exception, in which case it presented the second best performance. Therefore, this work demonstrates that it is possible to increase performance replacing ReLU by an enhanced activation function. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=H1DGha1CZ |
https://openreview.net/pdf?id=H1DGha1CZ | |
PWC | https://paperswithcode.com/paper/enhancing-batch-normalized-convolutional |
Repo | |
Framework | |
Deep Neural Models of Semantic Shift
Title | Deep Neural Models of Semantic Shift |
Authors | Alex Rosenfeld, Katrin Erk |
Abstract | Diachronic distributional models track changes in word use over time. In this paper, we propose a deep neural network diachronic distributional model. Instead of modeling lexical change via a time series as is done in previous work, we represent time as a continuous variable and model a word{'}s usage as a function of time. Additionally, we have also created a novel synthetic task which measures a model{'}s ability to capture the semantic trajectory. This evaluation quantitatively measures how well a model captures the semantic trajectory of a word over time. Finally, we explore how well the derivatives of our model can be used to measure the speed of lexical change. |
Tasks | Time Series |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-1044/ |
https://www.aclweb.org/anthology/N18-1044 | |
PWC | https://paperswithcode.com/paper/deep-neural-models-of-semantic-shift |
Repo | |
Framework | |
Dual-Agent Deep Reinforcement Learning for Deformable Face Tracking
Title | Dual-Agent Deep Reinforcement Learning for Deformable Face Tracking |
Authors | Minghao Guo, Jiwen Lu, Jie Zhou |
Abstract | In this paper, we propose a dual-agent deep reinforcement learning (DADRL) method for deformable face tracking, which generates bounding boxes and detects facial landmarks interactively from face videos. Most existing deformable face tracking methods learn models for these two tasks individually, and perform these two procedures subsequently during the testing phase, which ignore the intrinsic connections of these two tasks. Motivated by the fact that the performance of facial landmark detection depends heavily on the accuracy of the generated bounding boxes, we exploit the interactions of these two tasks in probabilistic manner by following a Bayesian model and propose a unified framework for simultaneous bounding box tracking and landmark detection. By formulating it as a Markov decision process, we define two agents to exploit the relationships and pass messages via an adaptive sequence of actions under a deep reinforcement learning framework to iteratively adjust the positions of the bounding boxes and facial landmarks. Our proposed DADRL achieves performance improvements over the state-of-the-art deformable face tracking methods on the most challenging category of the 300-VW dataset. |
Tasks | Facial Landmark Detection |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Minghao_Guo_Dual-Agent_Deep_Reinforcement_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Minghao_Guo_Dual-Agent_Deep_Reinforcement_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/dual-agent-deep-reinforcement-learning-for |
Repo | |
Framework | |
Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20,000 English Words
Title | Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20,000 English Words |
Authors | Saif Mohammad |
Abstract | Words play a central role in language and thought. Factor analysis studies have shown that the primary dimensions of meaning are valence, arousal, and dominance (VAD). We present the NRC VAD Lexicon, which has human ratings of valence, arousal, and dominance for more than 20,000 English words. We use Best{–}Worst Scaling to obtain fine-grained scores and address issues of annotation consistency that plague traditional rating scale methods of annotation. We show that the ratings obtained are vastly more reliable than those in existing lexicons. We also show that there exist statistically significant differences in the shared understanding of valence, arousal, and dominance across demographic variables such as age, gender, and personality. |
Tasks | Emotion Recognition |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-1017/ |
https://www.aclweb.org/anthology/P18-1017 | |
PWC | https://paperswithcode.com/paper/obtaining-reliable-human-ratings-of-valence |
Repo | |
Framework | |
CogCompTime: A Tool for Understanding Time in Natural Language
Title | CogCompTime: A Tool for Understanding Time in Natural Language |
Authors | Qiang Ning, Ben Zhou, Zhili Feng, Haoruo Peng, Dan Roth |
Abstract | Automatic extraction of temporal information is important for natural language understanding. It involves two basic tasks: (1) Understanding time expressions that are mentioned explicitly in text (e.g., February 27, 1998 or tomorrow), and (2) Understanding temporal information that is conveyed implicitly via relations. This paper introduces CogCompTime, a system that has these two important functionalities. It incorporates the most recent progress, achieves state-of-the-art performance, and is publicly available at \url{http://cogcomp.org/page/publication_view/844}. |
Tasks | Question Answering |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/D18-2013/ |
https://www.aclweb.org/anthology/D18-2013 | |
PWC | https://paperswithcode.com/paper/cogcomptime-a-tool-for-understanding-time-in |
Repo | |
Framework | |
Creating dialect sub-corpora by clustering: a case in Japanese for an adaptive method
Title | Creating dialect sub-corpora by clustering: a case in Japanese for an adaptive method |
Authors | Yo Sato, Kevin Heffernan |
Abstract | |
Tasks | Language Modelling |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1571/ |
https://www.aclweb.org/anthology/L18-1571 | |
PWC | https://paperswithcode.com/paper/creating-dialect-sub-corpora-by-clustering-a |
Repo | |
Framework | |
LCQMC:A Large-scale Chinese Question Matching Corpus
Title | LCQMC:A Large-scale Chinese Question Matching Corpus |
Authors | Xin Liu, Qingcai Chen, Chong Deng, Huajun Zeng, Jing Chen, Dongfang Li, Buzhou Tang |
Abstract | The lack of large-scale question matching corpora greatly limits the development of matching methods in question answering (QA) system, especially for non-English languages. To ameliorate this situation, in this paper, we introduce a large-scale Chinese question matching corpus (named LCQMC), which is released to the public1. LCQMC is more general than paraphrase corpus as it focuses on intent matching rather than paraphrase. How to collect a large number of question pairs in variant linguistic forms, which may present the same intent, is the key point for such corpus construction. In this paper, we first use a search engine to collect large-scale question pairs related to high-frequency words from various domains, then filter irrelevant pairs by the Wasserstein distance, and finally recruit three annotators to manually check the left pairs. After this process, a question matching corpus that contains 260,068 question pairs is constructed. In order to verify the LCQMC corpus, we split it into three parts, i.e., a training set containing 238,766 question pairs, a development set with 8,802 question pairs, and a test set with 12,500 question pairs, and test several well-known sentence matching methods on it. The experimental results not only demonstrate the good quality of LCQMC but also provide solid baseline performance for further researches on this corpus. |
Tasks | Information Retrieval, Machine Translation, Paraphrase Identification, Question Answering |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1166/ |
https://www.aclweb.org/anthology/C18-1166 | |
PWC | https://paperswithcode.com/paper/lcqmca-large-scale-chinese-question-matching |
Repo | |
Framework | |
A Morphological Analyzer for St. Lawrence Island / Central Siberian Yupik
Title | A Morphological Analyzer for St. Lawrence Island / Central Siberian Yupik |
Authors | Emily Chen, Lane Schwartz |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1416/ |
https://www.aclweb.org/anthology/L18-1416 | |
PWC | https://paperswithcode.com/paper/a-morphological-analyzer-for-st-lawrence |
Repo | |
Framework | |
Linking News Sentiment to Microblogs: A Distributional Semantics Approach to Enhance Microblog Sentiment Classification
Title | Linking News Sentiment to Microblogs: A Distributional Semantics Approach to Enhance Microblog Sentiment Classification |
Authors | Tobias Daudert, Paul Buitelaar |
Abstract | Social media{'}s popularity in society and research is gaining momentum and simultaneously increasing the importance of short textual content such as microblogs. Microblogs are affected by many factors including the news media, therefore, we exploit sentiments conveyed from news to detect and classify sentiment in microblogs. Given that texts can deal with the same entity but might not be vastly related when it comes to sentiment, it becomes necessary to introduce further measures ensuring the relatedness of texts while leveraging the contained sentiments. This paper describes ongoing research introducing distributional semantics to improve the exploitation of news-contained sentiment to enhance microblog sentiment classification. |
Tasks | Sentiment Analysis, Word Embeddings |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-6216/ |
https://www.aclweb.org/anthology/W18-6216 | |
PWC | https://paperswithcode.com/paper/linking-news-sentiment-to-microblogs-a |
Repo | |
Framework | |
NEUROSENT-PDI at SemEval-2018 Task 7: Discovering Textual Relations With a Neural Network Model
Title | NEUROSENT-PDI at SemEval-2018 Task 7: Discovering Textual Relations With a Neural Network Model |
Authors | Mauro Dragoni |
Abstract | Discovering semantic relations within textual documents is a timely topic worthy of investigation. Natural language processing strategies are generally used for linking chunks of text in order to extract information that can be exploited by semantic search engines for performing complex queries. The scientific domain is an interesting area where these techniques can be applied. In this paper, we describe a system based on neural networks applied to the SemEval 2018 Task 7. The system relies on the use of word embeddings for composing the vectorial representation of text chunks. Such representations are used for feeding a neural network aims to learn the structure of paths connecting chunks associated with a specific relation. Preliminary results demonstrated the suitability of the proposed approach encouraging the investigation of this research direction. |
Tasks | Relation Extraction, Word Embeddings |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1136/ |
https://www.aclweb.org/anthology/S18-1136 | |
PWC | https://paperswithcode.com/paper/neurosent-pdi-at-semeval-2018-task-7 |
Repo | |
Framework | |
Manual vs Automatic Bitext Extraction
Title | Manual vs Automatic Bitext Extraction |
Authors | Aibek Makazhanov, Bagdat Myrzakhmetov, Zhenisbek Assylbekov |
Abstract | |
Tasks | Machine Translation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1606/ |
https://www.aclweb.org/anthology/L18-1606 | |
PWC | https://paperswithcode.com/paper/manual-vs-automatic-bitext-extraction |
Repo | |
Framework | |
Evaluation of Machine Translation Performance Across Multiple Genres and Languages
Title | Evaluation of Machine Translation Performance Across Multiple Genres and Languages |
Authors | Marlies van der Wees, Arianna Bisazza, Christof Monz |
Abstract | |
Tasks | Machine Translation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1604/ |
https://www.aclweb.org/anthology/L18-1604 | |
PWC | https://paperswithcode.com/paper/evaluation-of-machine-translation-performance |
Repo | |
Framework | |
Multi-lingual Argumentative Corpora in English, Turkish, Greek, Albanian, Croatian, Serbian, Macedonian, Bulgarian, Romanian and Arabic
Title | Multi-lingual Argumentative Corpora in English, Turkish, Greek, Albanian, Croatian, Serbian, Macedonian, Bulgarian, Romanian and Arabic |
Authors | Alfred Sliwa, Yuan Ma, Ruishen Liu, Niravkumar Borad, Seyedeh Ziyaei, Mina Ghobadi, Firas Sabbah, Ahmet Aker |
Abstract | |
Tasks | Argument Mining, Decision Making |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1617/ |
https://www.aclweb.org/anthology/L18-1617 | |
PWC | https://paperswithcode.com/paper/multi-lingual-argumentative-corpora-in |
Repo | |
Framework | |