Paper Group NANR 10
Cross-lingual NIL Entity Clustering for Low-resource Languages. Computational Analysis of the Historical Changes in Poetry and Prose. Amortized Bayesian Meta-Learning. Weakly Supervised Cross-lingual Semantic Relation Classification via Knowledge Distillation. Towards Extracting Medical Family History from Natural Language Interactions: A New Datas …
Cross-lingual NIL Entity Clustering for Low-resource Languages
| Title | Cross-lingual NIL Entity Clustering for Low-resource Languages |
| Authors | Kevin Blissett, Heng Ji |
| Abstract | Clustering unlinkable entity mentions across documents in multiple languages (cross-lingual NIL Clustering) is an important task as part of Entity Discovery and Linking (EDL). This task has been largely neglected by the EDL community because it is challenging to outperform simple edit distance or other heuristics based baselines. We propose a novel approach based on encoding the orthographic similarity of the mentions using a Recurrent Neural Network (RNN) architecture. Our model adapts a training procedure from the one-shot facial recognition literature in order to achieve this. We also perform several exploratory probing tasks on our name encodings in order to determine what specific types of information are likely to be encoded by our model. Experiments show our approach provides up to a 6.6{%} absolute CEAFm F-Score improvement over state-of-the-art methods and successfully captures phonological relations across languages. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2804/ |
| https://www.aclweb.org/anthology/W19-2804 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-nil-entity-clustering-for-low |
| Repo | |
| Framework | |
Computational Analysis of the Historical Changes in Poetry and Prose
| Title | Computational Analysis of the Historical Changes in Poetry and Prose |
| Authors | Amitha Gopidi, Aniket Alam |
| Abstract | The esoteric definitions of poetry are insufficient in enveloping the changes in poetry that the age of mechanical reproduction has witnessed with the widespread proliferation of the use of digital media and artificial intelligence. They are also insufficient in distinguishing between prose and poetry, as the content of both prose and poetry can be poetic. Using quotes as prose considering their poetic, context-free and celebrated nature, stylistic differences between poetry and prose are delved into. Novel features in grammar and meter are justified as distinguishing features. Datasets of popular prose and poetry spanning across 1870-1920 and 1970-2019 have been created, and multiple experiments have been conducted to prove that prose and poetry in the latter period are more alike than they were in the former. The accuracy of classification of poetry and prose of 1970-2019 is significantly lesser than that of 1870-1920, thereby proving the convergence of poetry and prose in 1970-2019. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4702/ |
| https://www.aclweb.org/anthology/W19-4702 | |
| PWC | https://paperswithcode.com/paper/computational-analysis-of-the-historical |
| Repo | |
| Framework | |
Amortized Bayesian Meta-Learning
| Title | Amortized Bayesian Meta-Learning |
| Authors | Sachin Ravi, Alex Beatson |
| Abstract | Meta-learning, or learning-to-learn, has proven to be a successful strategy in attacking problems in supervised learning and reinforcement learning that involve small amounts of data. State-of-the-art solutions involve learning an initialization and/or learning algorithm using a set of training episodes so that the meta learner can generalize to an evaluation episode quickly. These methods perform well but often lack good quantification of uncertainty, which can be vital to real-world applications when data is lacking. We propose a meta-learning method which efficiently amortizes hierarchical variational inference across tasks, learning a prior distribution over neural network weights so that a few steps of Bayes by Backprop will produce a good task-specific approximate posterior. We show that our method produces good uncertainty estimates on contextual bandit and few-shot learning benchmarks. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkgpy3C5tX |
| https://openreview.net/pdf?id=rkgpy3C5tX | |
| PWC | https://paperswithcode.com/paper/amortized-bayesian-meta-learning |
| Repo | |
| Framework | |
Weakly Supervised Cross-lingual Semantic Relation Classification via Knowledge Distillation
| Title | Weakly Supervised Cross-lingual Semantic Relation Classification via Knowledge Distillation |
| Authors | Yogarshi Vyas, Marine Carpuat |
| Abstract | Words in different languages rarely cover the exact same semantic space. This work characterizes differences in meaning between words across languages using semantic relations that have been used to relate the meaning of English words. However, because of translation ambiguity, semantic relations are not always preserved by translation. We introduce a cross-lingual relation classifier trained only with English examples and a bilingual dictionary. Our classifier relies on a novel attention-based distillation approach to account for translation ambiguity when transferring knowledge from English to cross-lingual settings. On new English-Chinese and English-Hindi test sets, the resulting models largely outperform baselines that more naively rely on bilingual embeddings or dictionaries for cross-lingual transfer, and approach the performance of fully supervised systems on English tasks. |
| Tasks | Cross-Lingual Transfer, Relation Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1532/ |
| https://www.aclweb.org/anthology/D19-1532 | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-cross-lingual-semantic |
| Repo | |
| Framework | |
Towards Extracting Medical Family History from Natural Language Interactions: A New Dataset and Baselines
| Title | Towards Extracting Medical Family History from Natural Language Interactions: A New Dataset and Baselines |
| Authors | Mahmoud Azab, Stephane Dadian, Vivi Nastase, Larry An, Rada Mihalcea |
| Abstract | We introduce a new dataset consisting of natural language interactions annotated with medical family histories, obtained during interactions with a genetic counselor and through crowdsourcing, following a questionnaire created by experts in the domain. We describe the data collection process and the annotations performed by medical professionals, including illness and personal attributes (name, age, gender, family relationships) for the patient and their family members. An initial system that performs argument identification and relation extraction shows promising results {–} average F-score of 0.87 on complex sentences on the targeted relations. |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1122/ |
| https://www.aclweb.org/anthology/D19-1122 | |
| PWC | https://paperswithcode.com/paper/towards-extracting-medical-family-history |
| Repo | |
| Framework | |
Building a treebank for Occitan: what use for Romance UD corpora?
| Title | Building a treebank for Occitan: what use for Romance UD corpora? |
| Authors | Aleks Miletic, ra, Myriam Bras, Louise Esher, Jean Sibille, Marianne Vergez-Couret |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-8002/ |
| https://www.aclweb.org/anthology/W19-8002 | |
| PWC | https://paperswithcode.com/paper/building-a-treebank-for-occitan-what-use-for |
| Repo | |
| Framework | |
Applying Rhetorical Structure Theory to Student Essays for Providing Automated Writing Feedback
| Title | Applying Rhetorical Structure Theory to Student Essays for Providing Automated Writing Feedback |
| Authors | Shiyan Jiang, Kexin Yang, Ch Suvarna, rakumari, Pooja Casula, Mingtong Zhang, Carolyn Ros{'e} |
| Abstract | We present a package of annotation resources, including annotation guideline, flowchart, and an Intelligent Tutoring System for training human annotators. These resources can be used to apply Rhetorical Structure Theory (RST) to essays written by students in K-12 schools. Furthermore, we highlight the great potential of using RST to provide automated feedback for improving writing quality across genres. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2720/ |
| https://www.aclweb.org/anthology/W19-2720 | |
| PWC | https://paperswithcode.com/paper/applying-rhetorical-structure-theory-to |
| Repo | |
| Framework | |
Text Segmentation Using N-grams to Annotate Hadith Corpus
| Title | Text Segmentation Using N-grams to Annotate Hadith Corpus |
| Authors | Shatha Altammami, Eric Atwell, Ammar Alsalka |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5605/ |
| https://www.aclweb.org/anthology/W19-5605 | |
| PWC | https://paperswithcode.com/paper/text-segmentation-using-n-grams-to-annotate |
| Repo | |
| Framework | |
Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition
| Title | Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition |
| Authors | Bingyu Liu, Weihong Deng, Yaoyao Zhong, Mei Wang, Jiani Hu, Xunqiang Tao, Yaohai Huang |
| Abstract | Recently, large-margin softmax loss methods, such as angular softmax loss (SphereFace), large margin cosine loss (CosFace), and additive angular margin loss (ArcFace), have demonstrated impressive performance on deep face recognition. These methods incorporate a fixed additive margin to all the classes, ignoring the class imbalance problem. However, imbalanced problem widely exists in various real-world face datasets, in which samples from some classes are in a higher number than others. We argue that the number of a class would influence its demand for the additive margin. In this paper, we introduce a new margin-aware reinforcement learning based loss function, namely fair loss, in which each class will learn an appropriate adaptive margin by Deep Q-learning. Specifically, we train an agent to learn a margin adaptive strategy for each class, and make the additive margins for different classes more reasonable. Our method has better performance than present large-margin loss functions on three benchmarks, Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace, which demonstrates that our method could learn better face representation on imbalanced face datasets. |
| Tasks | Face Recognition, Q-Learning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Fair_Loss_Margin-Aware_Reinforcement_Learning_for_Deep_Face_Recognition_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Fair_Loss_Margin-Aware_Reinforcement_Learning_for_Deep_Face_Recognition_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fair-loss-margin-aware-reinforcement-learning |
| Repo | |
| Framework | |
Discriminatively Learned Convex Models for Set Based Face Recognition
| Title | Discriminatively Learned Convex Models for Set Based Face Recognition |
| Authors | Hakan Cevikalp, Golara Ghorban Dordinejad |
| Abstract | Majority of the image set based face recognition methods use a generatively learned model for each person that is learned independently by ignoring the other persons in the gallery set. In contrast to these methods, this paper introduces a novel method that searches for discriminative convex models that best fit to an individual’s face images but at the same time are as far as possible from the images of other persons in the gallery. We learn discriminative convex models for both affine and convex hulls of image sets. During testing, distances from the query set images to these models are computed efficiently by using simple matrix multiplications, and the query set is assigned to the person in the gallery whose image set is closest to the query images. The proposed method significantly outperforms other methods using generative convex models in terms of both accuracy and testing time, and achieves the state-of-the-art results on four of the five tested datasets. Especially, the accuracy improvement is significant on the challenging PaSC, COX and ESOGU video datasets. |
| Tasks | Face Recognition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Cevikalp_Discriminatively_Learned_Convex_Models_for_Set_Based_Face_Recognition_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Cevikalp_Discriminatively_Learned_Convex_Models_for_Set_Based_Face_Recognition_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/discriminatively-learned-convex-models-for |
| Repo | |
| Framework | |
Generation of Hip-Hop Lyrics with Hierarchical Modeling and Conditional Templates
| Title | Generation of Hip-Hop Lyrics with Hierarchical Modeling and Conditional Templates |
| Authors | Enrique Manjavacas, Mike Kestemont, Folgert Karsdorp |
| Abstract | This paper addresses Hip-Hop lyric generation with conditional Neural Language Models. We develop a simple yet effective mechanism to extract and apply conditional templates from text snippets, and show{—}on the basis of a large-scale crowd-sourced manual evaluation{—}that these templates significantly improve the quality and realism of the generated snippets. Importantly, the proposed approach enables end-to-end training, targeting formal properties of text such as rhythm and rhyme, which are central characteristics of rap texts. Additionally, we explore how generating text at different scales (e.g.{\textasciitilde}character-level or word-level) affects the quality of the output. We find that a hybrid form{—}a hierarchical model that aims to integrate Language Modeling at both word and character-level scales{—}yields significant improvements in text quality, yet surprisingly, cannot exploit conditional templates to their fullest extent. Our findings highlight that text generation models based on Recurrent Neural Networks (RNN) are sensitive to the modeling scale and call for further research on the observed differences in effectiveness of the conditioning mechanism at different scales. |
| Tasks | Language Modelling, Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8638/ |
| https://www.aclweb.org/anthology/W19-8638 | |
| PWC | https://paperswithcode.com/paper/generation-of-hip-hop-lyrics-with |
| Repo | |
| Framework | |
Context-aware Interactive Attention for Multi-modal Sentiment and Emotion Analysis
| Title | Context-aware Interactive Attention for Multi-modal Sentiment and Emotion Analysis |
| Authors | Dushyant Singh Chauhan, Md Shad Akhtar, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | In recent times, multi-modal analysis has been an emerging and highly sought-after field at the intersection of natural language processing, computer vision, and speech processing. The prime objective of such studies is to leverage the diversified information, (e.g., textual, acoustic and visual), for learning a model. The effective interaction among these modalities often leads to a better system in terms of performance. In this paper, we introduce a recurrent neural network based approach for the multi-modal sentiment and emotion analysis. The proposed model learns the inter-modal interaction among the participating modalities through an auto-encoder mechanism. We employ a context-aware attention module to exploit the correspondence among the neighboring utterances. We evaluate our proposed approach for five standard multi-modal affect analysis datasets. Experimental results suggest the efficacy of the proposed model for both sentiment and emotion analysis over various existing state-of-the-art systems. |
| Tasks | Emotion Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1566/ |
| https://www.aclweb.org/anthology/D19-1566 | |
| PWC | https://paperswithcode.com/paper/context-aware-interactive-attention-for-multi |
| Repo | |
| Framework | |
Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions
| Title | Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions |
| Authors | Jierui Li, Lei Wang, Jipeng Zhang, Yan Wang, Bing Tian Dai, Dongxiang Zhang |
| Abstract | Several deep learning models have been proposed for solving math word problems (MWPs) automatically. Although these models have the ability to capture features without manual efforts, their approaches to capturing features are not specifically designed for MWPs. To utilize the merits of deep learning models with simultaneous consideration of MWPs{'} specific features, we propose a group attention mechanism to extract global features, quantity-related features, quantity-pair features and question-related features in MWPs respectively. The experimental results show that the proposed approach performs significantly better than previous state-of-the-art methods, and boost performance from 66.9{%} to 69.5{%} on Math23K with training-test split, from 65.8{%} to 66.9{%} on Math23K with 5-fold cross-validation and from 69.2{%} to 76.1{%} on MAWPS. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1619/ |
| https://www.aclweb.org/anthology/P19-1619 | |
| PWC | https://paperswithcode.com/paper/modeling-intra-relation-in-math-word-problems |
| Repo | |
| Framework | |
Figure Eight at SemEval-2019 Task 3: Ensemble of Transfer Learning Methods for Contextual Emotion Detection
| Title | Figure Eight at SemEval-2019 Task 3: Ensemble of Transfer Learning Methods for Contextual Emotion Detection |
| Authors | Joan Xiao |
| Abstract | This paper describes our transfer learning-based approach to contextual emotion detection as part of SemEval-2019 Task 3. We experiment with transfer learning using pre-trained language models (ULMFiT, OpenAI GPT, and BERT) and fine-tune them on this task. We also train a deep learning model from scratch using pre-trained word embeddings and BiLSTM architecture with attention mechanism. The ensembled model achieves competitive result, ranking ninth out of 165 teams. The result reveals that ULMFiT performs best due to its superior fine-tuning techniques. We propose improvements for future work. |
| Tasks | Transfer Learning, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2036/ |
| https://www.aclweb.org/anthology/S19-2036 | |
| PWC | https://paperswithcode.com/paper/figure-eight-at-semeval-2019-task-3-ensemble |
| Repo | |
| Framework | |
Tell Me More: A Dataset of Visual Scene Description Sequences
| Title | Tell Me More: A Dataset of Visual Scene Description Sequences |
| Authors | Nikolai Ilinykh, Sina Zarrie{\ss}, David Schlangen |
| Abstract | We present a dataset consisting of what we call image description sequences, which are multi-sentence descriptions of the contents of an image. These descriptions were collected in a pseudo-interactive setting, where the describer was told to describe the given image to a listener who needs to identify the image within a set of images, and who successively asks for more information. As we show, this setup produced nicely structured data that, we think, will be useful for learning models capable of planning and realising such description discourses. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8621/ |
| https://www.aclweb.org/anthology/W19-8621 | |
| PWC | https://paperswithcode.com/paper/tell-me-more-a-dataset-of-visual-scene |
| Repo | |
| Framework | |
