Paper Group NANR 270
Egocentric Activity Prediction via Event Modulated Attention. Element-wise Bilinear Interaction for Sentence Matching. IronyMagnet at SemEval-2018 Task 3: A Siamese network for Irony detection in Social media. Teanga: A Linked Data based platform for Natural Language Processing. A Danish FrameNet Lexicon and an Annotated Corpus Used for Training an …
Egocentric Activity Prediction via Event Modulated Attention
| Title | Egocentric Activity Prediction via Event Modulated Attention |
| Authors | Yang Shen, Bingbing Ni, Zefan Li, Ning Zhuang |
| Abstract | Predicting future activities from an egocentric viewpoint is of particular interest in assisted living. However, state-of-the-art egocentric activity understanding techniques are mostly NOT capable of predictive tasks, as their synchronous processing architecture performs poorly in either modeling event dependency or pruning temporal redundant features. This work explicitly addresses these issues by proposing an asynchronous gaze-event driven attentive activity prediction network. This network is built on a gaze-event extraction module inspired by the fact that gaze moving in/out a certain object most probably indicates the occurrence/ending of a certain activity. The extracted gaze events are input to: 1) an asynchronous module which reasons about the temporal dependency between events and 2) a synchronous module which softly attends to informative temporal durations for more compact and discriminative feature extraction. Both modules are seamlessly integrated for collaborative prediction. Extensive experimental results on egocentric activity prediction as well as recognition well demonstrate the effectiveness of the proposed method. |
| Tasks | Activity Prediction |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yang_Shen_Egocentric_Activity_Prediction_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yang_Shen_Egocentric_Activity_Prediction_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/egocentric-activity-prediction-via-event |
| Repo | |
| Framework | |
Element-wise Bilinear Interaction for Sentence Matching
| Title | Element-wise Bilinear Interaction for Sentence Matching |
| Authors | Jihun Choi, Taeuk Kim, Sang-goo Lee |
| Abstract | When we build a neural network model predicting the relationship between two sentences, the most general and intuitive approach is to use a Siamese architecture, where the sentence vectors obtained from a shared encoder is given as input to a classifier. For the classifier to work effectively, it is important to extract appropriate features from the two vectors and feed them as input. There exist several previous works that suggest heuristic-based function for matching sentence vectors, however it cannot be said that the heuristics tailored for a specific task generalize to other tasks. In this work, we propose a new matching function, ElBiS, that learns to model element-wise interaction between two vectors. From experiments, we empirically demonstrate that the proposed ElBiS matching function outperforms the concatenation-based or heuristic-based matching functions on natural language inference and paraphrase identification, while maintaining the fused representation compact. |
| Tasks | Natural Language Inference, Paraphrase Identification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2012/ |
| https://www.aclweb.org/anthology/S18-2012 | |
| PWC | https://paperswithcode.com/paper/element-wise-bilinear-interaction-for |
| Repo | |
| Framework | |
IronyMagnet at SemEval-2018 Task 3: A Siamese network for Irony detection in Social media
| Title | IronyMagnet at SemEval-2018 Task 3: A Siamese network for Irony detection in Social media |
| Authors | Aniruddha Ghosh, Tony Veale |
| Abstract | This paper describes our system, entitled IronyMagnet, for the 3rd Task of the SemEval 2018 workshop, {}Irony Detection in English Tweets{''}. In Task 1, irony classification task has been considered as a binary classification task. Now for the first time, finer categories of irony are considered as part of a shared task. In task 2, three types of irony are considered; {}Irony by contrast{''} - ironic instances where evaluative expression portrays inverse polarity (positive, negative) of the literal proposition; {}Situational irony{''} - ironic instances where output of a situation do not comply with its expectation; {}Other verbal irony{''} - instances where ironic intent does not rely on polarity contrast or unexpected outcome. We proposed a Siamese neural network for irony detection, which is consisted of two subnetworks, each containing a long short term memory layer(LSTM) and an embedding layer initialized with vectors from Glove word embedding 1 . The system achieved a f-score of 0.72, and 0.50 in task 1, and task 2 respectively. |
| Tasks | Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1093/ |
| https://www.aclweb.org/anthology/S18-1093 | |
| PWC | https://paperswithcode.com/paper/ironymagnet-at-semeval-2018-task-3-a-siamese |
| Repo | |
| Framework | |
Teanga: A Linked Data based platform for Natural Language Processing
| Title | Teanga: A Linked Data based platform for Natural Language Processing |
| Authors | Housam Ziad, John P. McCrae, Paul Buitelaar |
| Abstract | |
| Tasks | Machine Translation, Part-Of-Speech Tagging, Sentiment Analysis, Text Classification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1383/ |
| https://www.aclweb.org/anthology/L18-1383 | |
| PWC | https://paperswithcode.com/paper/teanga-a-linked-data-based-platform-for |
| Repo | |
| Framework | |
A Danish FrameNet Lexicon and an Annotated Corpus Used for Training and Evaluating a Semantic Frame Classifier
| Title | A Danish FrameNet Lexicon and an Annotated Corpus Used for Training and Evaluating a Semantic Frame Classifier |
| Authors | Bolette Pedersen, Sanni Nimb, Anders S{\o}gaard, Mareike Hartmann, Sussi Olsen |
| Abstract | |
| Tasks | Common Sense Reasoning |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1378/ |
| https://www.aclweb.org/anthology/L18-1378 | |
| PWC | https://paperswithcode.com/paper/a-danish-framenet-lexicon-and-an-annotated |
| Repo | |
| Framework | |
Feature Optimization for Predicting Readability of Arabic L1 and L2
| Title | Feature Optimization for Predicting Readability of Arabic L1 and L2 |
| Authors | Hind Saddiki, Nizar Habash, Violetta Cavalli-Sforza, Muhamed Al Khalil |
| Abstract | Advances in automatic readability assessment can impact the way people consume information in a number of domains. Arabic, being a low-resource and morphologically complex language, presents numerous challenges to the task of automatic readability assessment. In this paper, we present the largest and most in-depth computational readability study for Arabic to date. We study a large set of features with varying depths, from shallow words to syntactic trees, for both L1 and L2 readability tasks. Our best L1 readability accuracy result is 94.8{%} (75{%} error reduction from a commonly used baseline). The comparable results for L2 are 72.4{%} (45{%} error reduction). We also demonstrate the added value of leveraging L1 features for L2 readability prediction. |
| Tasks | Language Modelling |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3703/ |
| https://www.aclweb.org/anthology/W18-3703 | |
| PWC | https://paperswithcode.com/paper/feature-optimization-for-predicting |
| Repo | |
| Framework | |
INAOE-UPV at SemEval-2018 Task 3: An Ensemble Approach for Irony Detection in Twitter
| Title | INAOE-UPV at SemEval-2018 Task 3: An Ensemble Approach for Irony Detection in Twitter |
| Authors | Delia Iraz{'u} Hern{'a}ndez Far{'\i}as, Fern S{'a}nchez-Vega, o, Manuel Montes-y-G{'o}mez, Paolo Rosso |
| Abstract | This paper describes an ensemble approach to the SemEval-2018 Task 3. The proposed method is composed of two renowned methods in text classification together with a novel approach for capturing ironic content by exploiting a tailored lexicon for irony detection. We experimented with different ensemble settings. The obtained results show that our method has a good performance for detecting the presence of ironic content in Twitter. |
| Tasks | Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1097/ |
| https://www.aclweb.org/anthology/S18-1097 | |
| PWC | https://paperswithcode.com/paper/inaoe-upv-at-semeval-2018-task-3-an-ensemble |
| Repo | |
| Framework | |
Robust Optical Flow in Rainy Scenes
| Title | Robust Optical Flow in Rainy Scenes |
| Authors | Ruoteng Li, Robby T. Tan, Loong-Fah Cheong |
| Abstract | Optical flow estimation in rainy scenes is challenging due to degradation caused by rain streaks and rain accumulation, where the latter refers to the poor visibility of remote scenes due to intense rainfall. To resolve the problem, we introduce a residue channel, a single channel (gray) image that is free from rain, and its colored version, a colored-residue image. We propose to utilize these two rain-free images in computing optical flow. To deal with the loss of contrast and the attendant sensitivity to noise, we decompose each of the input images into a piecewise-smooth structure layer and a high-frequency fine-detail texture layer. We combine the colored-residue images and structure layers in a unified objective function, so that the estimation of optical flow can be more robust. Results on both synthetic and real images show that our algorithm outperforms existing methods on different types of rain sequences. To our knowledge, this is the first optical flow method specifically dealing with rain. We also provide an optical flow dataset consisting of both synthetic and real rain images. |
| Tasks | Optical Flow Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ruoteng_Li_Robust_Optical_Flow_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ruoteng_Li_Robust_Optical_Flow_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-optical-flow-in-rainy-scenes |
| Repo | |
| Framework | |
#NonDicevoSulSerio at SemEval-2018 Task 3: Exploiting Emojis and Affective Content for Irony Detection in English Tweets
| Title | #NonDicevoSulSerio at SemEval-2018 Task 3: Exploiting Emojis and Affective Content for Irony Detection in English Tweets |
| Authors | Endang Wahyu Pamungkas, Viviana Patti |
| Abstract | This paper describes the participation of the {#}NonDicevoSulSerio team at SemEval2018-Task3, which focused on Irony Detection in English Tweets and was articulated in two tasks addressing the identification of irony at different levels of granularity. We participated in both tasks proposed: Task A is a classical binary classification task to determine whether a tweet is ironic or not, while Task B is a multiclass classification task devoted to distinguish different types of irony, where systems have to predict one out of four labels describing verbal irony by clash, other verbal irony, situational irony, and non-irony. We addressed both tasks by proposing a model built upon a well-engineered features set involving both syntactic and lexical features, and a wide range of affective-based features, covering different facets of sentiment and emotions. The use of new features for taking advantage of the affective information conveyed by emojis has been analyzed. On this line, we also tried to exploit the possible incongruity between sentiment expressed in the text and in the emojis included in a tweet. We used a Support Vector Machine classifier, and obtained promising results. We also carried on experiments in an unconstrained setting. |
| Tasks | Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1106/ |
| https://www.aclweb.org/anthology/S18-1106 | |
| PWC | https://paperswithcode.com/paper/nondicevosulserio-at-semeval-2018-task-3 |
| Repo | |
| Framework | |
NewsReader at SemEval-2018 Task 5: Counting events by reasoning over event-centric-knowledge-graphs
| Title | NewsReader at SemEval-2018 Task 5: Counting events by reasoning over event-centric-knowledge-graphs |
| Authors | Piek Vossen |
| Abstract | In this paper, we describe the participation of the NewsReader system in the SemEval-2018 Task 5 on Counting Events and Participants in the Long Tail. NewsReader is a generic unsupervised text processing system that detects events with participants, time and place to generate Event Centric Knowledge Graphs (ECKGs). We minimally adapted these ECKGs to establish a baseline performance for the task. We first use the ECKGs to establish which documents report on the same incident and what event mentions are coreferential. Next, we aggregate ECKGs across coreferential mentions and use the aggregated knowledge to answer the questions of the task. Our participation tests the quality of NewsReader to create ECKGs, as well as the potential of ECKGs to establish event identity and reason over the result to answer the task queries. |
| Tasks | Knowledge Graphs |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1108/ |
| https://www.aclweb.org/anthology/S18-1108 | |
| PWC | https://paperswithcode.com/paper/newsreader-at-semeval-2018-task-5-counting |
| Repo | |
| Framework | |
NAI-SEA at SemEval-2018 Task 5: An Event Search System
| Title | NAI-SEA at SemEval-2018 Task 5: An Event Search System |
| Authors | Yingchi Liu, Quanzhi Li, Luo Si |
| Abstract | In this paper, we describe Alibaba{'}s participating system in the semEval-2018 Task5: Counting Events and Participants in the Long Tail. We designed and implemented a pipeline system that consists of components to extract question properties and document features, document event category classifications, document retrieval and document clustering. To retrieve the majority of the relevant documents, we carefully designed our system to extract key information from each question and document pair. After retrieval, we perform further document clustering to count the number of events. The task contains 3 subtasks, on which we achieved F1 score of 78.33, 50.52, 63.59 , respectively, for document level retrieval. Our system ranks first in all the three subtasks on document level retrieval, and it also ranks first in incident-level evaluation by RSME measure in subtask 3. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1110/ |
| https://www.aclweb.org/anthology/S18-1110 | |
| PWC | https://paperswithcode.com/paper/nai-sea-at-semeval-2018-task-5-an-event |
| Repo | |
| Framework | |
SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using Natural Language Processing (SecureNLP)
| Title | SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using Natural Language Processing (SecureNLP) |
| Authors | Ph, Peter i, Amila Silva, Wei Lu |
| Abstract | This paper describes the SemEval 2018 shared task on semantic extraction from cybersecurity reports, which is introduced for the first time as a shared task on SemEval. This task comprises four SubTasks done incrementally to predict the characteristics of a specific malware using cybersecurity reports. To the best of our knowledge, we introduce the world{'}s largest publicly available dataset of annotated malware reports in this task. This task received in total 18 submissions from 9 participating teams. |
| Tasks | Malware Detection |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1113/ |
| https://www.aclweb.org/anthology/S18-1113 | |
| PWC | https://paperswithcode.com/paper/semeval-2018-task-8-semantic-extraction-from |
| Repo | |
| Framework | |
Using PPM for Health Related Text Detection
| Title | Using PPM for Health Related Text Detection |
| Authors | Victoria Bobicev, Victoria Lazu, Daniela Istrati |
| Abstract | This paper describes the participation of the LILU team in SMM4H challenge on social media mining for health related events description such as drug intakes or vaccinations. |
| Tasks | Language Modelling |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5918/ |
| https://www.aclweb.org/anthology/W18-5918 | |
| PWC | https://paperswithcode.com/paper/using-ppm-for-health-related-text-detection |
| Repo | |
| Framework | |
Computationally Constructed Concepts: A Machine Learning Approach to Metaphor Interpretation Using Usage-Based Construction Grammatical Cues
| Title | Computationally Constructed Concepts: A Machine Learning Approach to Metaphor Interpretation Using Usage-Based Construction Grammatical Cues |
| Authors | Zachary Rosen |
| Abstract | The current study seeks to implement a deep learning classification algorithm using argument-structure level representation of metaphoric constructions, for the identification of source domain mappings in metaphoric utterances. It thus builds on previous work in computational metaphor interpretation (Mohler et al. 2014; Shutova 2010; Bollegala {&} Shutova 2013; Hong 2016; Su et al. 2017) while implementing a theoretical framework based off of work in the interface of metaphor and construction grammar (Sullivan 2006, 2007, 2013). The results indicate that it is possible to achieve an accuracy of approximately 80.4{%} using the proposed method, combining construction grammatical features with a simple deep learning NN. I attribute this increase in accuracy to the use of constructional cues, extracted from the raw text of metaphoric instances. |
| Tasks | Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0912/ |
| https://www.aclweb.org/anthology/W18-0912 | |
| PWC | https://paperswithcode.com/paper/computationally-constructed-concepts-a |
| Repo | |
| Framework | |
SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge
| Title | SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge |
| Authors | Simon Ostermann, Michael Roth, Ashutosh Modi, Stefan Thater, Manfred Pinkal |
| Abstract | This report summarizes the results of the SemEval 2018 task on machine comprehension using commonsense knowledge. For this machine comprehension task, we created a new corpus, MCScript. It contains a high number of questions that require commonsense knowledge for finding the correct answer. 11 teams from 4 different countries participated in this shared task, most of them used neural approaches. The best performing system achieves an accuracy of 83.95{%}, outperforming the baselines by a large margin, but still far from the human upper bound, which was found to be at 98{%}. |
| Tasks | Reading Comprehension, Story Completion |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1119/ |
| https://www.aclweb.org/anthology/S18-1119 | |
| PWC | https://paperswithcode.com/paper/semeval-2018-task-11-machine-comprehension |
| Repo | |
| Framework | |
