Paper Group NANR 68
Multi-Task Stance Detection with Sentiment and Stance Lexicons. Embedding English to Welsh MT in a Private Company. Transition-Based Coding and Formal Language Theory for Ordered Digraphs. A Modeling Study of the Effects of Surprisal and Entropy in Perceptual Decision Making of an Adaptive Agent. Detecting Adverse Drug Reactions from Biomedical Tex …
Multi-Task Stance Detection with Sentiment and Stance Lexicons
| Title | Multi-Task Stance Detection with Sentiment and Stance Lexicons |
| Authors | Yingjie Li, Cornelia Caragea |
| Abstract | Stance detection aims to detect whether the opinion holder is in support of or against a given target. Recent works show improvements in stance detection by using either the attention mechanism or sentiment information. In this paper, we propose a multi-task framework that incorporates target-specific attention mechanism and at the same time takes sentiment classification as an auxiliary task. Moreover, we used a sentiment lexicon and constructed a stance lexicon to provide guidance for the attention layer. Experimental results show that the proposed model significantly outperforms state-of-the-art deep learning methods on the SemEval-2016 dataset. |
| Tasks | Sentiment Analysis, Stance Detection |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1657/ |
| https://www.aclweb.org/anthology/D19-1657 | |
| PWC | https://paperswithcode.com/paper/multi-task-stance-detection-with-sentiment |
| Repo | |
| Framework | |
Embedding English to Welsh MT in a Private Company
| Title | Embedding English to Welsh MT in a Private Company |
| Authors | Myfyr Prys, Dewi Bryn Jones |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6906/ |
| https://www.aclweb.org/anthology/W19-6906 | |
| PWC | https://paperswithcode.com/paper/embedding-english-to-welsh-mt-in-a-private |
| Repo | |
| Framework | |
Transition-Based Coding and Formal Language Theory for Ordered Digraphs
| Title | Transition-Based Coding and Formal Language Theory for Ordered Digraphs |
| Authors | Anssi Yli-Jyr{"a} |
| Abstract | Transition-based parsing of natural language uses transition systems to build directed annotation graphs (digraphs) for sentences. In this paper, we define, for an arbitrary ordered digraph, a unique decomposition and a corresponding linear encoding that are associated bijectively with each other via a new transition system. These results give us an efficient and succinct representation for digraphs and sets of digraphs. Based on the system and our analysis of its syntactic properties, we give structural bounds under which the set of encoded digraphs is restricted and becomes a context-free or a regular string language. The context-free restriction is essentially a superset of the encodings used previously to characterize properties of noncrossing digraphs and to solve maximal subgraphs problems. The regular restriction with a tight bound is shown to capture the Universal Dependencies v2.4 treebanks in linguistics. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-3115/ |
| https://www.aclweb.org/anthology/W19-3115 | |
| PWC | https://paperswithcode.com/paper/transition-based-coding-and-formal-language |
| Repo | |
| Framework | |
A Modeling Study of the Effects of Surprisal and Entropy in Perceptual Decision Making of an Adaptive Agent
| Title | A Modeling Study of the Effects of Surprisal and Entropy in Perceptual Decision Making of an Adaptive Agent |
| Authors | Pyeong Whan Cho, Richard Lewis |
| Abstract | Processing difficulty in online language comprehension has been explained in terms of surprisal and entropy reduction. Although both hypotheses have been supported by experimental data, we do not fully understand their relative contributions on processing difficulty. To develop a better understanding, we propose a mechanistic model of perceptual decision making that interacts with a simulated task environment with temporal dynamics. The proposed model collects noisy bottom-up evidence over multiple timesteps, integrates it with its top-down expectation, and makes perceptual decisions, producing processing time data directly without relying on any linking hypothesis. Temporal dynamics in the task environment was determined by a simple finite-state grammar, which was designed to create the situations where the surprisal and entropy reduction hypotheses predict different patterns. After the model was trained to maximize rewards, the model developed an adaptive policy and both surprisal and entropy effects were observed especially in a measure reflecting earlier processing. |
| Tasks | Decision Making |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2906/ |
| https://www.aclweb.org/anthology/W19-2906 | |
| PWC | https://paperswithcode.com/paper/a-modeling-study-of-the-effects-of-surprisal |
| Repo | |
| Framework | |
Detecting Adverse Drug Reactions from Biomedical Texts with Neural Networks
| Title | Detecting Adverse Drug Reactions from Biomedical Texts with Neural Networks |
| Authors | Ilseyar Alimova, Elena Tutubalina |
| Abstract | Detection of adverse drug reactions in postapproval periods is a crucial challenge for pharmacology. Social media and electronic clinical reports are becoming increasingly popular as a source for obtaining health related information. In this work, we focus on extraction information of adverse drug reactions from various sources of biomedical textbased information, including biomedical literature and social media. We formulate the problem as a binary classification task and compare the performance of four state-of-the-art attention-based neural networks in terms of the F-measure. We show the effectiveness of these methods on four different benchmarks. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2058/ |
| https://www.aclweb.org/anthology/P19-2058 | |
| PWC | https://paperswithcode.com/paper/detecting-adverse-drug-reactions-from |
| Repo | |
| Framework | |
What does Neural Bring? Analysing Improvements in Morphosyntactic Annotation and Lemmatisation of Slovenian, Croatian and Serbian
| Title | What does Neural Bring? Analysing Improvements in Morphosyntactic Annotation and Lemmatisation of Slovenian, Croatian and Serbian |
| Authors | Nikola Ljube{\v{s}}i{'c}, Kaja Dobrovoljc |
| Abstract | We present experiments on Slovenian, Croatian and Serbian morphosyntactic annotation and lemmatisation between the former state-of-the-art for these three languages and one of the best performing systems at the CoNLL 2018 shared task, the Stanford NLP neural pipeline. Our experiments show significant improvements in morphosyntactic annotation, especially on categories where either semantic knowledge is needed, available through word embeddings, or where long-range dependencies have to be modelled. On the other hand, on the task of lemmatisation no improvements are obtained with the neural solution, mostly due to the heavy dependence of the task on the lookup in an external lexicon, but also due to obvious room for improvements in the Stanford NLP pipeline{'}s lemmatisation. |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3704/ |
| https://www.aclweb.org/anthology/W19-3704 | |
| PWC | https://paperswithcode.com/paper/what-does-neural-bring-analysing-improvements |
| Repo | |
| Framework | |
Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization
| Title | Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization |
| Authors | Huazhe Xu *1, Boyuan Chen *1, Yang Gao1, and Trevor Darrell1 |
| Abstract | Abstract Humans can learn task-agnostic priors from interactive experience and utilize the priors for novel tasks without any finetuning. In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that can learn task-agnostic semantics and dynamics priors from arbitrary quality interactions under sparse reward and then plan on unseen tasks in zero-shot condition. The framework finds a neural score function for local regional state and action pairs that can be aggregated to approximate the quality of a full trajectory; moreover, a dynamics model that is learned with selfsupervision can be incorporated for planning. Many previous works that leverage interactive data for policy learning either need massive on-policy environmental interactions or assume access to expert data while we can achieve the similar goal with pure off-policy imperfect data. Instantiating our framework results in a generalizable policy to unseen tasks. Experiments demonstrate that the proposed method can outperform baseline methods on a wide range of applications including gridworld, robotics tasks and video games. |
| Tasks | |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.08143 |
| https://arxiv.org/abs/1910.08143 | |
| PWC | https://paperswithcode.com/paper/scoring-aggregating-planning-learning-task-1 |
| Repo | |
| Framework | |
NSIT@NLP4IF-2019: Propaganda Detection from News Articles using Transfer Learning
| Title | NSIT@NLP4IF-2019: Propaganda Detection from News Articles using Transfer Learning |
| Authors | Kartik Aggarwal, Anubhav Sadana |
| Abstract | In this paper, we describe our approach and system description for NLP4IF 2019 Workshop: Shared Task on Fine-Grained Propaganda Detection. Given a sentence from a news article, the task is to detect whether the sentence contains a propagandistic agenda or not. The main contribution of our work is to evaluate the effectiveness of various transfer learning approaches like ELMo, BERT, and RoBERTa for propaganda detection. We show the use of Document Embeddings on the top of Stacked Embeddings combined with LSTM for identification of propagandistic context in the sentence. We further provide analysis of these models to show the effect of oversampling on the provided dataset. In the final test-set evaluation, our system ranked 21st with F1-score of 0.43 in the SLC Task. |
| Tasks | Transfer Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5021/ |
| https://www.aclweb.org/anthology/D19-5021 | |
| PWC | https://paperswithcode.com/paper/nsitnlp4if-2019-propaganda-detection-from |
| Repo | |
| Framework | |
A Pregroup Representation of Word Order Alternation Using Hindi Syntax
| Title | A Pregroup Representation of Word Order Alternation Using Hindi Syntax |
| Authors | Alok Debnath, Manish Shrivastava |
| Abstract | Pregroup calculus has been used for the representation of free word order languages (Sanskrit and Hungarian), using a construction called precyclicity. However, restricted word order alternation has not been handled before. This paper aims at introducing and formally expressing three methods of representing word order alternation in the pregroup representation of any language. This paper describes the word order alternation patterns of Hindi, and creates a basic pregroup representation for the language. In doing so, the shortcoming of correct reductions for ungrammatical sentences due to the current apparatus is highlighted, and the aforementioned methods are invoked for a grammatically accurate representation of restricted word order alternation. The replicability of these methods is explained in the representation of adverbs and prepositional phrases in English. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-3017/ |
| https://www.aclweb.org/anthology/N19-3017 | |
| PWC | https://paperswithcode.com/paper/a-pregroup-representation-of-word-order |
| Repo | |
| Framework | |
The R2I_LIS Team Proposes Majority Vote for VarDial’s MRC Task
| Title | The R2I_LIS Team Proposes Majority Vote for VarDial’s MRC Task |
| Authors | Adrian-Gabriel Chifu |
| Abstract | This article presents the model that generated the runs submitted by the R2I{_}LIS team to the VarDial2019 evaluation campaign, more particularly, to the binary classification by dialect sub-task of the Moldavian vs. Romanian Cross-dialect Topic identification (MRC) task. The team proposed a majority vote-based model, between five supervised machine learning models, trained on forty manually-crafted features. One of the three submitted runs was ranked second at the binary classification sub-task, with a performance of 0.7963, in terms of macro-F1 measure. The other two runs were ranked third and fourth, respectively. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1414/ |
| https://www.aclweb.org/anthology/W19-1414 | |
| PWC | https://paperswithcode.com/paper/the-r2i_lis-team-proposes-majority-vote-for |
| Repo | |
| Framework | |
Adversarial Vulnerability of Neural Networks Increases with Input Dimension
| Title | Adversarial Vulnerability of Neural Networks Increases with Input Dimension |
| Authors | Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou, Bernhard Schölkopf, David Lopez-Paz |
| Abstract | Over the past four years, neural networks have been proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs. For most current network architectures, we prove that the L1-norm of these gradients grows as the square root of the input size. These nets therefore become increasingly vulnerable with growing image size. Our proofs rely on the network’s weight distribution at initialization, but extensive experiments confirm that our conclusions still hold after usual training. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1MzKs05F7 |
| https://openreview.net/pdf?id=H1MzKs05F7 | |
| PWC | https://paperswithcode.com/paper/adversarial-vulnerability-of-neural-networks-1 |
| Repo | |
| Framework | |
Syntax-Ignorant N-gram Embeddings for Sentiment Analysis of Arabic Dialects
| Title | Syntax-Ignorant N-gram Embeddings for Sentiment Analysis of Arabic Dialects |
| Authors | Hala Mulki, Hatem Haddad, Mourad Gridach, Ismail Babao{\u{g}}lu |
| Abstract | Arabic sentiment analysis models have employed compositional embedding features to represent the Arabic dialectal content. These embeddings are usually composed via ordered, syntax-aware composition functions and learned within deep neural frameworks. With the free word order and the varying syntax nature across the different Arabic dialects, a sentiment analysis system developed for one dialect might not be efficient for the others. Here we present syntax-ignorant n-gram embeddings to be used in sentiment analysis of several Arabic dialects. The proposed embeddings were composed and learned using an unordered composition function and a shallow neural model. Five datasets of different dialects were used to evaluate the produced embeddings in the sentiment analysis task. The obtained results revealed that, our syntax-ignorant embeddings could outperform word2vec model and doc2vec both variant models in addition to hand-crafted system baselines, while a competent performance was noticed towards baseline systems that adopted more complicated neural architectures. |
| Tasks | Arabic Sentiment Analysis, Sentiment Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4604/ |
| https://www.aclweb.org/anthology/W19-4604 | |
| PWC | https://paperswithcode.com/paper/syntax-ignorant-n-gram-embeddings-for |
| Repo | |
| Framework | |
A multi-objective optimization approach for brain MRI segmentation using fuzzy entropy clustering and region-based active contour methods
| Title | A multi-objective optimization approach for brain MRI segmentation using fuzzy entropy clustering and region-based active contour methods |
| Authors | Thuy Xuan Pham, Patrick Siarry⁎, Hamouche Oulhadj |
| Abstract | In this paper, we present a new multi-objective optimization approach for segmentation of Magnetic Resonance Imaging (MRI) of the human brain. The proposed algorithm not only takes advantages but also solves major drawbacks of two well-known complementary techniques, called fuzzy entropy clustering method and regionbased active contour method, using multi-objective particle swarm optimization (MOPSO) approach. In order to obtain accurate segmentation results, firstly, two fitness functions with independent characteristics, compactness and separation, are derived from kernelized fuzzy entropy clustering with local spatial information and bias correction (KFECSB) and a novel adaptive energy weight combined with global and local fitting energy active contour (AWGLAC) model. Then, they are simultaneously optimized to finally produce a set of non-dominated solutions, from which L2-metric method is used to select the best trade-off solution. Our algorithm is both verified and compared with other state-of-the-art methods using simulated MR images and real MR images from the McConnell Brain Imaging Center (BrainWeb) and the Internet Brain Segmentation Repository (IBSR), respectively. The experimental results demonstrate that the proposed technique achieves superior segmentation performance in terms of accuracy and robustness. 1. Introduction Image segmentation is the process of partitioning an image space into non-overlapped meaningful homogeneous regions or objects, according to given quantitative criteria: gray level, color, texture or combination of them [1]. For medical image analysis, the success of an image analysis system depends heavily on the quality of segmentation. We can find it in many real-life applications, for instance, in neurodegenerative disorders such as Alzheimer’s disease, in movement disorders such as Parkinson’s or Parkinson related syndrome, in congential brain malformations or perinatal brain damage, or in post-traumatic syndrome. However, the input MR brain images, which contain complex structures, are inherently noisy and often corrupted by intensity non-uniformity |
| Tasks | Brain Segmentation, Semantic Segmentation |
| Published | 2019-05-04 |
| URL | https://doi.org/10.1016/j.mri.2019.05.009 |
| https://doi.org/10.1016/j.mri.2019.05.009 | |
| PWC | https://paperswithcode.com/paper/a-multi-objective-optimization-approach-for |
| Repo | |
| Framework | |
Proceedings of the 5th Workshop on Semantic Deep Learning (SemDeep-5)
| Title | Proceedings of the 5th Workshop on Semantic Deep Learning (SemDeep-5) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5800/ |
| https://www.aclweb.org/anthology/W19-5800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-5th-workshop-on-semantic |
| Repo | |
| Framework | |
The SMarT Classifier for Arabic Fine-Grained Dialect Identification
| Title | The SMarT Classifier for Arabic Fine-Grained Dialect Identification |
| Authors | Karima Meftouh, Karima Abidi, Salima Harrat, Kamel Smaili |
| Abstract | This paper describes the approach adopted by the SMarT research group to build a dialect identification system in the framework of the Madar shared task on Arabic fine-grained dialect identification. We experimented several approaches, but we finally decided to use a Multinomial Naive Bayes classifier based on word and character ngrams in addition to the language model probabilities. We achieved a score of 67.73{%} in terms of Macro accuracy and a macro-averaged F1-score of 67.31{%} |
| Tasks | Language Modelling |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4633/ |
| https://www.aclweb.org/anthology/W19-4633 | |
| PWC | https://paperswithcode.com/paper/the-smart-classifier-for-arabic-fine-grained |
| Repo | |
| Framework | |
