Paper Group NANR 267
SemEval-2018 Task 5: Counting Events and Participants in the Long Tail. A High-Quality Denoising Dataset for Smartphone Cameras. Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints. Proceedings of The 12th International Workshop on Semantic Evaluation. SemEval 2018 Task 2: Multilingual Emoji P …
SemEval-2018 Task 5: Counting Events and Participants in the Long Tail
| Title | SemEval-2018 Task 5: Counting Events and Participants in the Long Tail |
| Authors | Marten Postma, Filip Ilievski, Piek Vossen |
| Abstract | This paper discusses SemEval-2018 Task 5: a referential quantification task of counting events and participants in local, long-tail news documents with high ambiguity. The complexity of this task challenges systems to establish the meaning, reference and identity across documents. The task consists of three subtasks and spans across three domains. We detail the design of this referential quantification task, describe the participating systems, and present additional analysis to gain deeper insight into their performance. |
| Tasks | Word Sense Disambiguation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1009/ |
| https://www.aclweb.org/anthology/S18-1009 | |
| PWC | https://paperswithcode.com/paper/semeval-2018-task-5-counting-events-and |
| Repo | |
| Framework | |
A High-Quality Denoising Dataset for Smartphone Cameras
| Title | A High-Quality Denoising Dataset for Smartphone Cameras |
| Authors | Abdelrahman Abdelhamed, Stephen Lin, Michael S. Brown |
| Abstract | The last decade has seen an astronomical shift from imaging with DSLR and point-and-shoot cameras to imaging with smartphone cameras. Due to the small aperture and sensor size, smartphone images have notably more noise than their DSLR counterparts. While denoising for smartphone images is an active research area, the research community currently lacks a denoising image dataset representative of real noisy images from smartphone cameras with high-quality ground truth. We address this issue in this paper with the following contributions. We propose a systematic procedure for estimating ground truth for noisy images that can be used to benchmark denoising performance for smartphone cameras. Using this procedure, we have captured a dataset, the Smartphone Image Denoising Dataset (SIDD), of ~30,000 noisy images from 10 scenes under different lighting conditions using five representative smartphone cameras and generated their ground truth images. We used this dataset to benchmark a number of denoising algorithms. We show that CNN-based methods perform better when trained on our high-quality dataset than when trained using alternative strategies, such as low-ISO images used as a proxy for ground truth data. |
| Tasks | Denoising, Image Denoising |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Abdelhamed_A_High-Quality_Denoising_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Abdelhamed_A_High-Quality_Denoising_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-high-quality-denoising-dataset-for |
| Repo | |
| Framework | |
Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints
| Title | Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints |
| Authors | Jiahuan Zhou, Bing Su, Ying Wu |
| Abstract | Multi-shot person re-identification (MsP-RID) utilizes multiple images from the same person to facilitate identification. Considering the fact that motion information may not be discriminative nor reliable enough for MsP-RID, this paper is focused on handling the large variations in the visual appearances through learning discriminative visual metrics for identification. Existing metric learning-based methods usually exploit pair-wise or triple-wise similarity constraints, that generally demands intensive optimization in metric learning, or leads to degraded performances by using sub-optimal solutions. In addition, as the training data are significantly imbalanced, the learning can be largely dominated by the negative pairs and thus produces unstable and non-discriminative results. In this paper, we propose a novel type of similarity constraint. It assigns the sample points to a set of extbf{reference points} to produce a linear number of extbf{reference constraints}. Several optimal transport-based schemes for reference constraint generation are proposed and studied. Based on those constraints, by utilizing a typical regressive metric learning model, the closed-form solution of the learned metric can be easily obtained. Extensive experiments and comparative studies on several public MsP-RID benchmarks have validated the effectiveness of our method and its significant superiority over the state-of-the-art MsP-RID methods in terms of both identification accuracy and running speed. |
| Tasks | Metric Learning, Person Re-Identification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_Easy_Identification_From_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Easy_Identification_From_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/easy-identification-from-better-constraints |
| Repo | |
| Framework | |
Proceedings of The 12th International Workshop on Semantic Evaluation
| Title | Proceedings of The 12th International Workshop on Semantic Evaluation |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1000/ |
| https://www.aclweb.org/anthology/S18-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-12th-international-1 |
| Repo | |
| Framework | |
SemEval 2018 Task 2: Multilingual Emoji Prediction
| Title | SemEval 2018 Task 2: Multilingual Emoji Prediction |
| Authors | Francesco Barbieri, Jose Camacho-Collados, Francesco Ronzano, Luis Espinosa-Anke, Miguel Ballesteros, Valerio Basile, Viviana Patti, Horacio Saggion |
| Abstract | This paper describes the results of the first Shared Task on Multilingual Emoji Prediction, organized as part of SemEval 2018. Given the text of a tweet, the task consists of predicting the most likely emoji to be used along such tweet. Two subtasks were proposed, one for English and one for Spanish, and participants were allowed to submit a system run to one or both subtasks. In total, 49 teams participated to the English subtask and 22 teams submitted a system run to the Spanish subtask. Evaluation was carried out emoji-wise, and the final ranking was based on macro F-Score. Data and further information about this task can be found at \url{https://competitions.codalab.org/competitions/17344}. |
| Tasks | Emotion Recognition, Information Retrieval, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1003/ |
| https://www.aclweb.org/anthology/S18-1003 | |
| PWC | https://paperswithcode.com/paper/semeval-2018-task-2-multilingual-emoji |
| Repo | |
| Framework | |
T"ubingen-Oslo at SemEval-2018 Task 2: SVMs perform better than RNNs in Emoji Prediction
| Title | T"ubingen-Oslo at SemEval-2018 Task 2: SVMs perform better than RNNs in Emoji Prediction |
| Authors | {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin, Taraka Rama |
| Abstract | This paper describes our participation in the SemEval-2018 task Multilingual Emoji Prediction. We participated in both English and Spanish subtasks, experimenting with support vector machines (SVMs) and recurrent neural networks. Our SVM classifier obtained the top rank in both subtasks with macro-averaged F1-measures of 35.99{%} for English and 22.36{%} for Spanish data sets. Similar to a few earlier attempts, the results with neural networks were not on par with linear SVMs. |
| Tasks | Document Classification, Hyperparameter Optimization, Language Identification, Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1004/ |
| https://www.aclweb.org/anthology/S18-1004 | |
| PWC | https://paperswithcode.com/paper/ta14bingen-oslo-at-semeval-2018-task-2-svms |
| Repo | |
| Framework | |
FrameIt: Ontology Discovery for Noisy User-Generated Text
| Title | FrameIt: Ontology Discovery for Noisy User-Generated Text |
| Authors | Dan Iter, Alon Halevy, Wang-Chiew Tan |
| Abstract | A common need of NLP applications is to extract structured data from text corpora in order to perform analytics or trigger an appropriate action. The ontology defining the structure is typically application dependent and in many cases it is not known a priori. We describe the FrameIt System that provides a workflow for (1) quickly discovering an ontology to model a text corpus and (2) learning an SRL model that extracts the instances of the ontology from sentences in the corpus. FrameIt exploits data that is obtained in the ontology discovery phase as weak supervision data to bootstrap the SRL model and then enables the user to refine the model with active learning. We present empirical results and qualitative analysis of the performance of FrameIt on three corpora of noisy user-generated text. |
| Tasks | Active Learning, Semantic Role Labeling |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6123/ |
| https://www.aclweb.org/anthology/W18-6123 | |
| PWC | https://paperswithcode.com/paper/frameit-ontology-discovery-for-noisy-user |
| Repo | |
| Framework | |
A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents
| Title | A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents |
| Authors | Yan Zheng, Zhaopeng Meng, Jianye Hao, Zongzhang Zhang, Tianpei Yang, Changjie Fan |
| Abstract | In multiagent domains, coping with non-stationary agents that change behaviors from time to time is a challenging problem, where an agent is usually required to be able to quickly detect the other agent’s policy during online interaction, and then adapt its own policy accordingly. This paper studies efficient policy detecting and reusing techniques when playing against non-stationary agents in Markov games. We propose a new deep BPR+ algorithm by extending the recent BPR+ algorithm with a neural network as the value-function approximator. To detect policy accurately, we propose the \textit{rectified belief model} taking advantage of the \textit{opponent model} to infer the other agent’s policy from reward signals and its behaviors. Instead of directly storing individual policies as BPR+, we introduce \textit{distilled policy network} that serves as the policy library in BPR+, using policy distillation to achieve efficient online policy learning and reuse. Deep BPR+ inherits all the advantages of BPR+ and empirically shows better performance in terms of detection accuracy, cumulative rewards and speed of convergence compared to existing algorithms in complex Markov games with raw visual inputs. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7374-a-deep-bayesian-policy-reuse-approach-against-non-stationary-agents |
| http://papers.nips.cc/paper/7374-a-deep-bayesian-policy-reuse-approach-against-non-stationary-agents.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-bayesian-policy-reuse-approach-against |
| Repo | |
| Framework | |
An End-to-End Multi-task Learning Model for Fact Checking
| Title | An End-to-End Multi-task Learning Model for Fact Checking |
| Authors | Sizhen Li, Shuai Zhao, Bo Cheng, Hao Yang |
| Abstract | With huge amount of information generated every day on the web, fact checking is an important and challenging task which can help people identify the authenticity of most claims as well as providing evidences selected from knowledge source like Wikipedia. Here we decompose this problem into two parts: an entity linking task (retrieving relative Wikipedia pages) and recognizing textual entailment between the claim and selected pages. In this paper, we present an end-to-end multi-task learning with bi-direction attention (EMBA) model to classify the claim as {}supports{''}, {}refutes{''} or {``}not enough info{''} with respect to the pages retrieved and detect sentences as evidence at the same time. We conduct experiments on the FEVER (Fact Extraction and VERification) paper test dataset and shared task test dataset, a new public dataset for verification against textual sources. Experimental results show that our method achieves comparable performance compared with the baseline system. | |
| Tasks | Common Sense Reasoning, Entity Linking, Fake News Detection, Multi-Task Learning, Natural Language Inference |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5523/ |
| https://www.aclweb.org/anthology/W18-5523 | |
| PWC | https://paperswithcode.com/paper/an-end-to-end-multi-task-learning-model-for |
| Repo | |
| Framework | |
Entity Resolution and Location Disambiguation in the Ancient Hindu Temples Domain using Web Data
| Title | Entity Resolution and Location Disambiguation in the Ancient Hindu Temples Domain using Web Data |
| Authors | Ayush Maheshwari, Vishwajeet Kumar, Ganesh Ramakrishnan, J. Saketha Nath |
| Abstract | We present a system for resolving entities and disambiguating locations based on publicly available web data in the domain of ancient Hindu Temples. Scarce, unstructured information poses a challenge to Entity Resolution(ER) and snippet ranking. Additionally, because the same set of entities may be associated with multiple locations, Location Disambiguation(LD) is a problem. The mentions and descriptions of temples exist in the order of hundreds of thousands, with such data generated by various users in various forms such as text (Wikipedia pages), videos (YouTube videos), blogs, etc. We demonstrate an integrated approach using a combination of grammar rules for parsing and unsupervised (clustering) algorithms to resolve entity and locations with high confidence. A demo of our system is accessible at \url{tinyurl.com/templedemos}. Our system is open source and available on GitHub. |
| Tasks | Entity Resolution |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-5010/ |
| https://www.aclweb.org/anthology/N18-5010 | |
| PWC | https://paperswithcode.com/paper/entity-resolution-and-location-disambiguation |
| Repo | |
| Framework | |
SemEval 2018 Task 6: Parsing Time Normalizations
| Title | SemEval 2018 Task 6: Parsing Time Normalizations |
| Authors | Egoitz Laparra, Dongfang Xu, Ahmed Elsayed, Steven Bethard, Martha Palmer |
| Abstract | This paper presents the outcomes of the Parsing Time Normalization shared task held within SemEval-2018. The aim of the task is to parse time expressions into the compositional semantic graphs of the Semantically Compositional Annotation of Time Expressions (SCATE) schema, which allows the representation of a wider variety of time expressions than previous approaches. Two tracks were included, one to evaluate the parsing of individual components of the produced graphs, in a classic information extraction way, and another one to evaluate the quality of the time intervals resulting from the interpretation of those graphs. Though 40 participants registered for the task, only one team submitted output, achieving 0.55 F1 in Track 1 (parsing) and 0.70 F1 in Track 2 (intervals). |
| Tasks | Semantic Parsing |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1011/ |
| https://www.aclweb.org/anthology/S18-1011 | |
| PWC | https://paperswithcode.com/paper/semeval-2018-task-6-parsing-time |
| Repo | |
| Framework | |
Translation of Biomedical Documents with Focus on Spanish-English
| Title | Translation of Biomedical Documents with Focus on Spanish-English |
| Authors | Mirela-Stefania Duma, Wolfgang Menzel |
| Abstract | For the WMT 2018 shared task of translating documents pertaining to the Biomedical domain, we developed a scoring formula that uses an unsophisticated and effective method of weighting term frequencies and was integrated in a data selection pipeline. The method was applied on five language pairs and it performed best on Portuguese-English, where a BLEU score of 41.84 placed it third out of seven runs submitted by three institutions. In this paper, we describe our method and results with a special focus on Spanish-English where we compare it against a state-of-the-art method. Our contribution to the task lies in introducing a fast, unsupervised method for selecting domain-specific data for training models which obtain good results using only 10{%} of the general domain data. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6444/ |
| https://www.aclweb.org/anthology/W18-6444 | |
| PWC | https://paperswithcode.com/paper/translation-of-biomedical-documents-with |
| Repo | |
| Framework | |
LT3 at SemEval-2018 Task 1: A classifier chain to detect emotions in tweets
| Title | LT3 at SemEval-2018 Task 1: A classifier chain to detect emotions in tweets |
| Authors | Luna De Bruyne, Orph{'e}e De Clercq, V{'e}ronique Hoste |
| Abstract | This paper presents an emotion classification system for English tweets, submitted for the SemEval shared task on Affect in Tweets, subtask 5: Detecting Emotions. The system combines lexicon, n-gram, style, syntactic and semantic features. For this multi-class multi-label problem, we created a classifier chain. This is an ensemble of eleven binary classifiers, one for each possible emotion category, where each model gets the predictions of the preceding models as additional features. The predicted labels are combined to get a multi-label representation of the predictions. Our system was ranked eleventh among thirty five participating teams, with a Jaccard accuracy of 52.0{%} and macro- and micro-average F1-scores of 49.3{%} and 64.0{%}, respectively. |
| Tasks | Emotion Classification, Emotion Recognition, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1016/ |
| https://www.aclweb.org/anthology/S18-1016 | |
| PWC | https://paperswithcode.com/paper/lt3-at-semeval-2018-task-1-a-classifier-chain |
| Repo | |
| Framework | |
Generation and Consolidation of Recollections for Efficient Deep Lifelong Learning
| Title | Generation and Consolidation of Recollections for Efficient Deep Lifelong Learning |
| Authors | Matt Riemer, Michele Franceschini, and Tim Klinger |
| Abstract | Deep lifelong learning systems need to efficiently manage resources to scale to large numbers of experiences and non-stationary goals. In this paper, we explore the relationship between lossy compression and the resource constrained lifelong learning problem of function transferability. We demonstrate that lossy episodic experience storage can enable efficient function transferability between different architectures and algorithms at a fraction of the storage cost of lossless storage. This is achieved by introducing a generative knowledge distillation strategy that does not store any full training examples. As an important extension of this idea, we show that lossy recollections stabilize deep networks much better than lossless sampling in resource constrained settings of lifelong learning while avoiding catastrophic forgetting. For this setting, we propose a novel dual purpose recollection buffer used to both stabilize the recollection generator itself and an accompanying reasoning model. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1ISxGZRb |
| https://openreview.net/pdf?id=r1ISxGZRb | |
| PWC | https://paperswithcode.com/paper/generation-and-consolidation-of-recollections |
| Repo | |
| Framework | |
Epita at SemEval-2018 Task 1: Sentiment Analysis Using Transfer Learning Approach
| Title | Epita at SemEval-2018 Task 1: Sentiment Analysis Using Transfer Learning Approach |
| Authors | Guillaume Daval-Frerot, Abdesselam Bouchekif, Anatole Moreau |
| Abstract | In this paper we present our system for detecting valence task. The major issue was to apply a state-of-the-art system despite the small dataset provided: the system would quickly overfit. The main idea of our proposal is to use transfer learning, which allows to avoid learning from scratch. Indeed, we start to train a first model to predict if a tweet is positive, negative or neutral. For this we use an external dataset which is larger and similar to the target dataset. Then, the pre-trained model is re-used as the starting point to train a new model that classifies a tweet into one of the seven various levels of sentiment intensity. Our system, trained using transfer learning, achieves 0.776 and 0.763 respectively for Pearson correlation coefficient and weighted quadratic kappa metrics on the subtask evaluation dataset. |
| Tasks | Sentiment Analysis, Transfer Learning |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1021/ |
| https://www.aclweb.org/anthology/S18-1021 | |
| PWC | https://paperswithcode.com/paper/epita-at-semeval-2018-task-1-sentiment |
| Repo | |
| Framework | |
