Paper Group NANR 207
Emoji Usage Across Platforms: A Case Study for the Charlottesville Event. Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing. Recognizing UMLS Semantic Types with Deep Learning. MAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction. Relation Extraction among Multip …
Emoji Usage Across Platforms: A Case Study for the Charlottesville Event
| Title | Emoji Usage Across Platforms: A Case Study for the Charlottesville Event |
| Authors | Khyati Mahajan, Samira Shaikh |
| Abstract | We study emoji usage patterns across two social media platforms, one of them considered a fringe community called Gab, and the other Twitter. We find that Gab tends to comparatively use more emotionally charged emoji, but also seems more apathetic towards the violence during the event, while Twitter takes a more empathetic approach to the event. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3651/ |
| https://www.aclweb.org/anthology/W19-3651 | |
| PWC | https://paperswithcode.com/paper/emoji-usage-across-platforms-a-case-study-for |
| Repo | |
| Framework | |
Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing
| Title | Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing |
| Authors | Anastasia Shimorina, Elena Khasanova, Claire Gardent |
| Abstract | In this paper, we propose an approach for semi-automatically creating a data-to-text (D2T) corpus for Russian that can be used to learn a D2T natural language generation model. An error analysis of the output of an English-to-Russian neural machine translation system shows that 80{%} of the automatically translated sentences contain an error and that 53{%} of all translation errors bear on named entities (NE). We therefore focus on named entities and introduce two post-editing techniques for correcting wrongly translated NEs. |
| Tasks | Data-to-Text Generation, Machine Translation, Text Generation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3706/ |
| https://www.aclweb.org/anthology/W19-3706 | |
| PWC | https://paperswithcode.com/paper/creating-a-corpus-for-russian-data-to-text |
| Repo | |
| Framework | |
Recognizing UMLS Semantic Types with Deep Learning
| Title | Recognizing UMLS Semantic Types with Deep Learning |
| Authors | Isar Nejadgholi, Kathleen C. Fraser, Berry De Bruijn, Muqun Li, Astha LaPlante, Khaldoun Zine El Abidine |
| Abstract | Entity recognition is a critical first step to a number of clinical NLP applications, such as entity linking and relation extraction. We present the first attempt to apply state-of-the-art entity recognition approaches on a newly released dataset, MedMentions. This dataset contains over 4000 biomedical abstracts, annotated for UMLS semantic types. In comparison to existing datasets, MedMentions contains a far greater number of entity types, and thus represents a more challenging but realistic scenario in a real-world setting. We explore a number of relevant dimensions, including the use of contextual versus non-contextual word embeddings, general versus domain-specific unsupervised pre-training, and different deep learning architectures. We contrast our results against the well-known i2b2 2010 entity recognition dataset, and propose a new method to combine general and domain-specific information. While producing a state-of-the-art result for the i2b2 2010 task (F1 = 0.90), our results on MedMentions are significantly lower (F1 = 0.63), suggesting there is still plenty of opportunity for improvement on this new data. |
| Tasks | Entity Linking, Relation Extraction, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6219/ |
| https://www.aclweb.org/anthology/D19-6219 | |
| PWC | https://paperswithcode.com/paper/recognizing-umls-semantic-types-with-deep |
| Repo | |
| Framework | |
MAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction
| Title | MAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction |
| Authors | Pengcheng Yang, Fuli Luo, Peng Chen, Tianyu Liu, Xu Sun |
| Abstract | The task of unsupervised bilingual lexicon induction (UBLI) aims to induce word translations from monolingual corpora in two languages. Previous work has shown that morphological variation is an intractable challenge for the UBLI task, where the induced translation in failure case is usually morphologically related to the correct translation. To tackle this challenge, we propose a morphology-aware alignment model for the UBLI task. The proposed model aims to alleviate the adverse effect of morphological variation by introducing grammatical information learned by the pre-trained denoising language model. Results show that our approach can substantially outperform several state-of-the-art unsupervised systems, and even achieves competitive performance compared to supervised methods. |
| Tasks | Denoising, Language Modelling |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1308/ |
| https://www.aclweb.org/anthology/P19-1308 | |
| PWC | https://paperswithcode.com/paper/maam-a-morphology-aware-alignment-model-for |
| Repo | |
| Framework | |
Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism
| Title | Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism |
| Authors | Seong Sik Park, Harksoo Kim |
| Abstract | Many previous studies on relation extrac-tion have been focused on finding only one relation between two entities in a single sentence. However, we can easily find the fact that multiple entities exist in a single sentence and the entities form multiple relations. To resolve this prob-lem, we propose a relation extraction model based on a dual pointer network with a multi-head attention mechanism. The proposed model finds n-to-1 subject-object relations by using a forward de-coder called an object decoder. Then, it finds 1-to-n subject-object relations by using a backward decoder called a sub-ject decoder. In the experiments with the ACE-05 dataset and the NYT dataset, the proposed model achieved the state-of-the-art performances (F1-score of 80.5{%} in the ACE-05 dataset, F1-score of 78.3{%} in the NYT dataset) |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6608/ |
| https://www.aclweb.org/anthology/D19-6608 | |
| PWC | https://paperswithcode.com/paper/relation-extraction-among-multiple-entities |
| Repo | |
| Framework | |
Hamiltonian descent for composite objectives
| Title | Hamiltonian descent for composite objectives |
| Authors | Brendan O’Donoghue, Chris J. Maddison |
| Abstract | In optimization the duality gap between the primal and the dual problems is a measure of the suboptimality of any primal-dual point. In classical mechanics the equations of motion of a system can be derived from the Hamiltonian function, which is a quantity that describes the total energy of the system. In this paper we consider a convex optimization problem consisting of the sum of two convex functions, sometimes referred to as a composite objective, and we identify the duality gap to be the `energy’ of the system. In the Hamiltonian formalism the energy is conserved, so we add a contractive term to the standard equations of motion so that this energy decreases linearly (ie, geometrically) with time. This yields a continuous-time ordinary differential equation (ODE) in the primal and dual variables which converges to zero duality gap, ie, optimality. This ODE has several useful properties: it induces a natural operator splitting; at convergence it yields both the primal and dual solutions; and it is invariant to affine transformation despite only using first order information. We provide several discretizations of this ODE, some of which are new algorithms and others correspond to known techniques, such as the alternating direction method of multipliers (ADMM). We conclude with some numerical examples that show the promise of our approach. We give an example where our technique can solve a convex quadratic minimization problem orders of magnitude faster than several commonly-used gradient methods, including conjugate gradient, when the conditioning of the problem is poor. Our framework provides new insights into previously known algorithms in the literature as well as providing a technique to generate new primal-dual algorithms. | |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9590-hamiltonian-descent-for-composite-objectives |
| http://papers.nips.cc/paper/9590-hamiltonian-descent-for-composite-objectives.pdf | |
| PWC | https://paperswithcode.com/paper/hamiltonian-descent-for-composite-objectives |
| Repo | |
| Framework | |
Knowledge Aware Semantic Concept Expansion for Image-Text Matching
| Title | Knowledge Aware Semantic Concept Expansion for Image-Text Matching |
| Authors | Botian Shi, Lei Ji, Pan Lu, Zhendong Niu, Nan Duan |
| Abstract | Image-text matching is a vital cross-modality task in artificial intelligence and has attracted increasing attention in recent years. Existing works have shown that learning semantic concepts is useful to enhance image representation and can significantly improve the performance of both image-to-text and text-to-image retrieval. However, existing models simply detect semantic concepts from a given image, which are less likely to deal with long-tail and occlusion concepts. Frequently co-occurred concepts in the same scene, e.g. bedroom and bed, can provide common-sense knowledge to discover other semantic-related concepts. In this paper, we develop a Scene Concept Graph (SCG) by aggregating image scene graphs and extracting frequently co-occurred concept pairs as scene common-sense knowledge. Moreover, we propose a novel model to incorporate this knowledge to improve image-text matching. Specifically, semantic concepts are detected from images and then expanded by the SCG. After learning to select relevant contextual concepts, we fuse their representations with the image embedding feature to feed into the matching module. Extensive experiments are conducted on Flickr30K and MSCOCO datasets, and prove that our model achieves state-of-the-art results due to the effectiveness of incorporating the external SCG. |
| Tasks | Common Sense Reasoning, Content-Based Image Retrieval, Image Retrieval, Text Matching |
| Published | 2019-08-10 |
| URL | https://www.ijcai.org/Proceedings/2019/720 |
| https://www.ijcai.org/proceedings/2019/0720.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-aware-semantic-concept-expansion |
| Repo | |
| Framework | |
Learning Diverse Generations using Determinantal Point Processes
| Title | Learning Diverse Generations using Determinantal Point Processes |
| Authors | Mohamed Elfeki, Camille Couprie, Mohamed Elhoseiny |
| Abstract | Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic looking images. A fundamental characteristic of generative models is their ability to produce multi-modal outputs. However, while training, they are often susceptible to mode collapse, which means that the model is limited in mapping the input noise to only a few modes of the true data distribution. In this paper, we draw inspiration from Determinantal Point Process (DPP) to devise a generative model that alleviates mode collapse while producing higher quality samples. DPP is an elegant probabilistic measure used to model negative correlations within a subset and hence quantify its diversity. We use DPP kernel to model the diversity in real data as well as in synthetic data. Then, we devise a generation penalty term that encourages the generator to synthesize data with a similar diversity to real data. In contrast to previous state-of-the-art generative models that tend to use additional trainable parameters or complex training paradigms, our method does not change the original training scheme. Embedded in an adversarial training and variational autoencoder, our Generative DPP approach shows a consistent resistance to mode-collapse on a wide-variety of synthetic data and natural image datasets including MNIST, CIFAR10, and CelebA, while outperforming state-of-the-art methods for data-efficiency, convergence-time, and generation quality. Our code will be made publicly available. |
| Tasks | Point Processes |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1x8WnA5Ym |
| https://openreview.net/pdf?id=S1x8WnA5Ym | |
| PWC | https://paperswithcode.com/paper/learning-diverse-generations-using |
| Repo | |
| Framework | |
Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data
| Title | Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data |
| Authors | Ruidong Wu, Yuan Yao, Xu Han, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun |
| Abstract | Open relation extraction (OpenRE) aims to extract relational facts from the open-domain corpus. To this end, it discovers relation patterns between named entities and then clusters those semantically equivalent patterns into a united relation cluster. Most OpenRE methods typically confine themselves to unsupervised paradigms, without taking advantage of existing relational facts in knowledge bases (KBs) and their high-quality labeled instances. To address this issue, we propose Relational Siamese Networks (RSNs) to learn similarity metrics of relations from labeled data of pre-defined relations, and then transfer the relational knowledge to identify novel relations in unlabeled data. Experiment results on two real-world datasets show that our framework can achieve significant improvements as compared with other state-of-the-art methods. Our code is available at https://github.com/thunlp/RSN. |
| Tasks | Relation Extraction, Transfer Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1021/ |
| https://www.aclweb.org/anthology/D19-1021 | |
| PWC | https://paperswithcode.com/paper/open-relation-extraction-relational-knowledge |
| Repo | |
| Framework | |
Distance-Based Authorship Verification Across Modern Standard Arabic Genres
| Title | Distance-Based Authorship Verification Across Modern Standard Arabic Genres |
| Authors | Hossam Ahmed |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5611/ |
| https://www.aclweb.org/anthology/W19-5611 | |
| PWC | https://paperswithcode.com/paper/distance-based-authorship-verification-across |
| Repo | |
| Framework | |
Proceedings of the 16th Meeting on the Mathematics of Language
| Title | Proceedings of the 16th Meeting on the Mathematics of Language |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5700/ |
| https://www.aclweb.org/anthology/W19-5700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-16th-meeting-on-the |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)
| Title | Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6300/ |
| https://www.aclweb.org/anthology/D19-6300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-3 |
| Repo | |
| Framework | |
JUSTDeep at NLP4IF 2019 Task 1: Propaganda Detection using Ensemble Deep Learning Models
| Title | JUSTDeep at NLP4IF 2019 Task 1: Propaganda Detection using Ensemble Deep Learning Models |
| Authors | Hani Al-Omari, Malak Abdullah, Ola AlTiti, Samira Shaikh |
| Abstract | The internet and the high use of social media have enabled the modern-day journalism to publish, share and spread news that is difficult to distinguish if it is true or fake. Defining {``}fake news{''} is not well established yet, however, it can be categorized under several labels: false, biased, or framed to mislead the readers that are characterized as propaganda. Digital content production technologies with logical fallacies and emotional language can be used as propaganda techniques to gain more readers or mislead the audience. Recently, several researchers have proposed deep learning (DL) models to address this issue. This research paper provides an ensemble deep learning model using BiLSTM, XGBoost, and BERT to detect propaganda. The proposed model has been applied on the dataset provided by the challenge NLP4IF 2019, Task 1 Sentence Level Classification (SLC) and it shows a significant performance over the baseline model. | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5016/ |
| https://www.aclweb.org/anthology/D19-5016 | |
| PWC | https://paperswithcode.com/paper/justdeep-at-nlp4if-2019-task-1-propaganda |
| Repo | |
| Framework | |
PLMP - Point-Line Minimal Problems in Complete Multi-View Visibility
| Title | PLMP - Point-Line Minimal Problems in Complete Multi-View Visibility |
| Authors | Timothy Duff, Kathlen Kohn, Anton Leykin, Tomas Pajdla |
| Abstract | We present a complete classification of all minimal problems for generic arrangements of points and lines completely observed by calibrated perspective cameras. We show that there are only 30 minimal problems in total, no problems exist for more than 6 cameras, for more than 5 points, and for more than 6 lines. We present a sequence of tests for detecting minimality starting with counting degrees of freedom and ending with full symbolic and numeric verification of representative examples. For all minimal problems discovered, we present their algebraic degrees, i.e. the number of solutions, which measure their intrinsic difficulty. It shows how exactly the difficulty of problems grows with the number of views. Importantly, several new mini- mal problems have small degrees that might be practical in image matching and 3D reconstruction. |
| Tasks | 3D Reconstruction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Duff_PLMP_-_Point-Line_Minimal_Problems_in_Complete_Multi-View_Visibility_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Duff_PLMP_-_Point-Line_Minimal_Problems_in_Complete_Multi-View_Visibility_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/plmp-point-line-minimal-problems-in-complete-1 |
| Repo | |
| Framework | |
(Almost) Unsupervised Grammatical Error Correction using Synthetic Comparable Corpus
| Title | (Almost) Unsupervised Grammatical Error Correction using Synthetic Comparable Corpus |
| Authors | Satoru Katsumata, Mamoru Komachi |
| Abstract | We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through experiments on a low resource track of the shared task at BEA2019. As a result, we achieved an F0.5 score of 28.31 points with the test data. |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4413/ |
| https://www.aclweb.org/anthology/W19-4413 | |
| PWC | https://paperswithcode.com/paper/almost-unsupervised-grammatical-error |
| Repo | |
| Framework | |
