Paper Group NANR 271
SemEval-2018 Task 12: The Argument Reasoning Comprehension Task. LightRel at SemEval-2018 Task 7: Lightweight and Fast Relation Classification. Bag of Experts Architectures for Model Reuse in Conversational Language Understanding. The UWNLP system at SemEval-2018 Task 7: Neural Relation Extraction Model with Selectively Incorporated Concept Embeddi …
SemEval-2018 Task 12: The Argument Reasoning Comprehension Task
| Title | SemEval-2018 Task 12: The Argument Reasoning Comprehension Task |
| Authors | Ivan Habernal, Henning Wachsmuth, Iryna Gurevych, Benno Stein |
| Abstract | A natural language argument is composed of a claim as well as reasons given as premises for the claim. The warrant explaining the reasoning is usually left implicit, as it is clear from the context and common sense. This makes a comprehension of arguments easy for humans but hard for machines. This paper summarizes the first shared task on argument reasoning comprehension. Given a premise and a claim along with some topic information, the goal was to automatically identify the correct warrant among two candidates that are plausible and lexically close, but in fact imply opposite claims. We describe the dataset with 1970 instances that we built for the task, and we outline the 21 computational approaches that participated, most of which used neural networks. The results reveal the complexity of the task, with many approaches hardly improving over the random accuracy of about 0.5. Still, the best observed accuracy (0.712) underlines the principle feasibility of identifying warrants. Our analysis indicates that an inclusion of external knowledge is key to reasoning comprehension. |
| Tasks | Common Sense Reasoning |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1121/ |
| https://www.aclweb.org/anthology/S18-1121 | |
| PWC | https://paperswithcode.com/paper/semeval-2018-task-12-the-argument-reasoning |
| Repo | |
| Framework | |
LightRel at SemEval-2018 Task 7: Lightweight and Fast Relation Classification
| Title | LightRel at SemEval-2018 Task 7: Lightweight and Fast Relation Classification |
| Authors | Tyler Renslow, G{"u}nter Neumann |
| Abstract | We present LightRel, a lightweight and fast relation classifier. Our goal is to develop a high baseline for different relation extraction tasks. By defining only very few data-internal, word-level features and external knowledge sources in the form of word clusters and word embeddings, we train a fast and simple linear classifier |
| Tasks | Feature Engineering, Relation Classification, Relation Extraction, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1123/ |
| https://www.aclweb.org/anthology/S18-1123 | |
| PWC | https://paperswithcode.com/paper/lightrel-at-semeval-2018-task-7-lightweight |
| Repo | |
| Framework | |
Bag of Experts Architectures for Model Reuse in Conversational Language Understanding
| Title | Bag of Experts Architectures for Model Reuse in Conversational Language Understanding |
| Authors | Rahul Jha, Alex Marin, Suvamsh Shivaprasad, Imed Zitouni |
| Abstract | Slot tagging, the task of detecting entities in input user utterances, is a key component of natural language understanding systems for personal digital assistants. Since each new domain requires a different set of slots, the annotation costs for labeling data for training slot tagging models increases rapidly as the number of domains grow. To tackle this, we describe Bag of Experts (BoE) architectures for model reuse for both LSTM and CRF based models. Extensive experimentation over a dataset of 10 domains drawn from data relevant to our commercial personal digital assistant shows that our BoE models outperform the baseline models with a statistically significant average margin of 5.06{%} in absolute F1-score when training with 2000 instances per domain, and achieve an even higher improvement of 12.16{%} when only 25{%} of the training data is used. |
| Tasks | Domain Adaptation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-3019/ |
| https://www.aclweb.org/anthology/N18-3019 | |
| PWC | https://paperswithcode.com/paper/bag-of-experts-architectures-for-model-reuse |
| Repo | |
| Framework | |
The UWNLP system at SemEval-2018 Task 7: Neural Relation Extraction Model with Selectively Incorporated Concept Embeddings
| Title | The UWNLP system at SemEval-2018 Task 7: Neural Relation Extraction Model with Selectively Incorporated Concept Embeddings |
| Authors | Yi Luan, Mari Ostendorf, Hannaneh Hajishirzi |
| Abstract | This paper describes our submission for SemEval 2018 Task 7 shared task on semantic relation extraction and classification in scientific papers. Our model is based on the end-to-end relation extraction model of (Miwa and Bansal, 2016) with several enhancements such as character-level encoding attention mechanism on selecting pretrained concept candidate embeddings. Our official submission ranked the second in relation classification task (Subtask 1.1 and Subtask 2 Senerio 2), and the first in the relation extraction task (Subtask 2 Scenario 1). |
| Tasks | Relation Classification, Relation Extraction, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1125/ |
| https://www.aclweb.org/anthology/S18-1125 | |
| PWC | https://paperswithcode.com/paper/the-uwnlp-system-at-semeval-2018-task-7 |
| Repo | |
| Framework | |
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network
| Title | MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network |
| Authors | Di Jin, Franck Dernoncourt, Elena Sergeeva, Matthew McDermott, Geeticka Chauhan |
| Abstract | SemEval 2018 Task 7 tasked participants to build a system to classify two entities within a sentence into one of the 6 possible relation types. We tested 3 classes of models: Linear classifiers, Long Short-Term Memory (LSTM) models, and Convolutional Neural Network (CNN) models. Ultimately, the CNN model class proved most performant, so we specialized to this model for our final submissions. We improved performance beyond a vanilla CNN by including a variant of negative sampling, using custom word embeddings learned over a corpus of ACL articles, training over corpora of both tasks 1.1 and 1.2, using reversed feature, using part of context words beyond the entity pairs and using ensemble methods to improve our final predictions. We also tested attention based pooling, up-sampling, and data augmentation, but none improved performance. Our model achieved rank 6 out of 28 (macro-averaged F1-score: 72.7) in subtask 1.1, and rank 4 out of 20 (macro F1: 80.6) in subtask 1.2. |
| Tasks | Common Sense Reasoning, Data Augmentation, Relation Classification, Relation Extraction, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1127/ |
| https://www.aclweb.org/anthology/S18-1127 | |
| PWC | https://paperswithcode.com/paper/mit-medg-at-semeval-2018-task-7-semantic |
| Repo | |
| Framework | |
Fast and Robust Estimation for Unit-Norm Constrained Linear Fitting Problems
| Title | Fast and Robust Estimation for Unit-Norm Constrained Linear Fitting Problems |
| Authors | Daiki Ikami, Toshihiko Yamasaki, Kiyoharu Aizawa |
| Abstract | M-estimator using iteratively reweighted least squares (IRLS) is one of the best-known methods for robust estimation. However, IRLS is ineffective for robust unit-norm constrained linear fitting (UCLF) problems, such as fundamental matrix estimation because of a poor initial solution. We overcome this problem by developing a novel objective function and its optimization, named iteratively reweighted eigenvalues minimization (IREM). IREM is guaranteed to decrease the objective function and achieves fast convergence and high robustness. In robust fundamental matrix estimation, IREM performs approximately 5-500 times faster than random sampling consensus (RANSAC) while preserving comparable or superior robustness. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Ikami_Fast_and_Robust_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Ikami_Fast_and_Robust_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-robust-estimation-for-unit-norm |
| Repo | |
| Framework | |
IRCMS at SemEval-2018 Task 7 : Evaluating a basic CNN Method and Traditional Pipeline Method for Relation Classification
| Title | IRCMS at SemEval-2018 Task 7 : Evaluating a basic CNN Method and Traditional Pipeline Method for Relation Classification |
| Authors | Zhongbo Yin, Zhunchen Luo, Wei Luo, Mao Bin, Changhai Tian, Yuming Ye, Shuai Wu |
| Abstract | This paper presents our participation for sub-task1 (1.1 and 1.2) in SemEval 2018 task 7: Semantic Relation Extraction and Classification in Scientific Papers (G{'a}bor et al., 2018). We experimented on this task with two methods: CNN method and traditional pipeline method. We use the context between two entities (included) as input information for both methods, which extremely reduce the noise effect. For the CNN method, we construct a simple convolution neural network to automatically learn features from raw texts without any manual processing. Moreover, we use the softmax function to classify the entity pair into a specific relation category. For the traditional pipeline method, we use the Hackabout method as a representation which is described in section3.5. The CNN method{'}s result is much better than traditional pipeline method (49.1{%} vs. 42.3{%} and 71.1{%} vs. 54.6{%} ). |
| Tasks | Named Entity Recognition, Relation Classification, Relation Extraction, Semantic Textual Similarity |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1129/ |
| https://www.aclweb.org/anthology/S18-1129 | |
| PWC | https://paperswithcode.com/paper/ircms-at-semeval-2018-task-7-evaluating-a |
| Repo | |
| Framework | |
ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings
| Title | ClaiRE at SemEval-2018 Task 7: Classification of Relations using Embeddings |
| Authors | Lena Hettinger, Alex Dallmann, er, Albin Zehe, Thomas Niebler, Andreas Hotho |
| Abstract | In this paper we describe our system for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1.1) and noisy data (subtask 1.2). We compare two models for classification, a C-LSTM which utilizes only word embeddings and an SVM that also takes handcrafted features into account. To adapt to the domain of science we train word embeddings on scientific papers collected from arXiv.org. The hand-crafted features consist of lexical features to model the semantic relations as well as the entities between which the relation holds. Classification of Relations using Embeddings (ClaiRE) achieved an F1 score of 74.89{%} for the first subtask and 78.39{%} for the second. |
| Tasks | Question Answering, Relation Classification, Relation Extraction, Sentiment Analysis, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1134/ |
| https://www.aclweb.org/anthology/S18-1134 | |
| PWC | https://paperswithcode.com/paper/claire-at-semeval-2018-task-7-classification |
| Repo | |
| Framework | |
Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes
| Title | Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes |
| Authors | Hassan Ashtiani, Shai Ben-David, Nicholas Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan |
| Abstract | We prove that ϴ(k d^2 / ε^2) samples are necessary and sufficient for learning a mixture of k Gaussians in R^d, up to error ε in total variation distance. This improves both the known upper bounds and lower bounds for this problem. For mixtures of axis-aligned Gaussians, we show that O(k d / ε^2) samples suffice, matching a known lower bound. The upper bound is based on a novel technique for distribution learning based on a notion of sample compression. Any class of distributions that allows such a sample compression scheme can also be learned with few samples. Moreover, if a class of distributions has such a compression scheme, then so do the classes of products and mixtures of those distributions. The core of our main result is showing that the class of Gaussians in R^d has an efficient sample compression. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7601-nearly-tight-sample-complexity-bounds-for-learning-mixtures-of-gaussians-via-sample-compression-schemes |
| http://papers.nips.cc/paper/7601-nearly-tight-sample-complexity-bounds-for-learning-mixtures-of-gaussians-via-sample-compression-schemes.pdf | |
| PWC | https://paperswithcode.com/paper/nearly-tight-sample-complexity-bounds-for |
| Repo | |
| Framework | |
Automatic Annotation of Semantic Term Types in the Complete ACL Anthology Reference Corpus
| Title | Automatic Annotation of Semantic Term Types in the Complete ACL Anthology Reference Corpus |
| Authors | Anne-Kathrin Schumann, H{'e}ctor Mart{'\i}nez Alonso |
| Abstract | |
| Tasks | Knowledge Base Population, Lexical Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1586/ |
| https://www.aclweb.org/anthology/L18-1586 | |
| PWC | https://paperswithcode.com/paper/automatic-annotation-of-semantic-term-types |
| Repo | |
| Framework | |
Improving Neural Language Models with Weight Norm Initialization and Regularization
| Title | Improving Neural Language Models with Weight Norm Initialization and Regularization |
| Authors | Christian Herold, Yingbo Gao, Hermann Ney |
| Abstract | Embedding and projection matrices are commonly used in neural language models (NLM) as well as in other sequence processing networks that operate on large vocabularies. We examine such matrices in fine-tuned language models and observe that a NLM learns word vectors whose norms are related to the word frequencies. We show that by initializing the weight norms with scaled log word counts, together with other techniques, lower perplexities can be obtained in early epochs of training. We also introduce a weight norm regularization loss term, whose hyperparameters are tuned via a grid search. With this method, we are able to significantly improve perplexities on two word-level language modeling tasks (without dynamic evaluation): from 54.44 to 53.16 on Penn Treebank (PTB) and from 61.45 to 60.13 on WikiText-2 (WT2). |
| Tasks | Language Modelling, Machine Translation, Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6310/ |
| https://www.aclweb.org/anthology/W18-6310 | |
| PWC | https://paperswithcode.com/paper/improving-neural-language-models-with-weight |
| Repo | |
| Framework | |
Talla at SemEval-2018 Task 7: Hybrid Loss Optimization for Relation Classification using Convolutional Neural Networks
| Title | Talla at SemEval-2018 Task 7: Hybrid Loss Optimization for Relation Classification using Convolutional Neural Networks |
| Authors | Bhanu Pratap, Daniel Shank, Oladipo Ositelu, Byron Galbraith |
| Abstract | This paper describes our approach to SemEval-2018 Task 7 {–} given an entity-tagged text from the ACL Anthology corpus, identify and classify pairs of entities that have one of six possible semantic relationships. Our model consists of a convolutional neural network leveraging pre-trained word embeddings, unlabeled ACL-abstracts, and multiple window sizes to automatically learn useful features from entity-tagged sentences. We also experiment with a hybrid loss function, a combination of cross-entropy loss and ranking loss, to boost the separation in classification scores. Lastly, we include WordNet-based features to further improve the performance of our model. Our best model achieves an F1(macro) score of 74.2 and 84.8 on subtasks 1.1 and 1.2, respectively. |
| Tasks | Feature Engineering, Question Answering, Relation Classification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1139/ |
| https://www.aclweb.org/anthology/S18-1139 | |
| PWC | https://paperswithcode.com/paper/talla-at-semeval-2018-task-7-hybrid-loss |
| Repo | |
| Framework | |
Tw-StAR at SemEval-2018 Task 1: Preprocessing Impact on Multi-label Emotion Classification
| Title | Tw-StAR at SemEval-2018 Task 1: Preprocessing Impact on Multi-label Emotion Classification |
| Authors | Hala Mulki, Chedi Bechikh Ali, Hatem Haddad, Ismail Babao{\u{g}}lu |
| Abstract | In this paper, we describe our contribution in SemEval-2018 contest. We tackled task 1 {}Affect in Tweets{''}, subtask E-c {}Detecting Emotions (multi-label classification){''}. A multilabel classification system Tw-StAR was developed to recognize the emotions embedded in Arabic, English and Spanish tweets. To handle the multi-label classification problem via traditional classifiers, we employed the binary relevance transformation strategy while a TF-IDF scheme was used to generate the tweets{'} features. We investigated using single and combinations of several preprocessing tasks to further improve the performance. The results showed that specific combinations of preprocessing tasks could significantly improve the evaluation measures. This has been later emphasized by the official results as our system ranked 3rd for both Arabic and Spanish datasets and 14th for the English dataset. |
| Tasks | Emotion Classification, Lemmatization, Multi-Label Classification, Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1024/ |
| https://www.aclweb.org/anthology/S18-1024 | |
| PWC | https://paperswithcode.com/paper/tw-star-at-semeval-2018-task-1-preprocessing |
| Repo | |
| Framework | |
TeamDL at SemEval-2018 Task 8: Cybersecurity Text Analysis using Convolutional Neural Network and Conditional Random Fields
| Title | TeamDL at SemEval-2018 Task 8: Cybersecurity Text Analysis using Convolutional Neural Network and Conditional Random Fields |
| Authors | Manik R, an, Krishna Madgula, Snehanshu Saha |
| Abstract | In this work we present our participation to SemEval-2018 Task 8 subtasks 1 {&} 2 respectively. We developed Convolution Neural Network system for malware sentence classification (subtask 1) and Conditional Random Fields system for malware token label prediction (subtask 2). We experimented with couple of word embedding strategies, feature sets and achieved competitive performance across the two subtasks. For subtask 1 We experimented with two category of word embeddings namely native embeddings and task specific embedding using Word2vec and Glove algorithms. 1. Native Embeddings: All words including the unknown ones that are randomly initialized use embeddings from original Word2vec/Glove models. 2. Task specific : The embeddings are generated by training Word2vec/Glove algorithms on sentences from MalwareTextDB We found that glove outperforms rest of embeddings for subtask 1. For subtask 2, we used N-grams of size 6, previous, next tokens and labels, features giving disjunctions of words anywhere in the left or right, word shape features, word lemma of current, previous and next words, word-tag pair features, POS tags, prefix and suffixes. |
| Tasks | Sentence Classification, Text Classification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1140/ |
| https://www.aclweb.org/anthology/S18-1140 | |
| PWC | https://paperswithcode.com/paper/teamdl-at-semeval-2018-task-8-cybersecurity |
| Repo | |
| Framework | |
HCCL at SemEval-2018 Task 8: An End-to-End System for Sequence Labeling from Cybersecurity Reports
| Title | HCCL at SemEval-2018 Task 8: An End-to-End System for Sequence Labeling from Cybersecurity Reports |
| Authors | Mingming Fu, Xuemin Zhao, Yonghong Yan |
| Abstract | This paper describes HCCL team systems that participated in SemEval 2018 Task 8: SecureNLP (Semantic Extraction from cybersecurity reports using NLP). To solve the problem, our team applied a neural network architecture that benefits from both word and character level representaions automatically, by using combination of Bi-directional LSTM, CNN and CRF (Ma and Hovy, 2016). Our system is truly end-to-end, requiring no feature engineering or data preprocessing, and we ranked 4th in the subtask 1, 7th in the subtask2 and 3rd in the SubTask2-relaxed. |
| Tasks | Feature Engineering, Named Entity Recognition, Structured Prediction |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1141/ |
| https://www.aclweb.org/anthology/S18-1141 | |
| PWC | https://paperswithcode.com/paper/hccl-at-semeval-2018-task-8-an-end-to-end |
| Repo | |
| Framework | |
