Home /

Research

Showing 859 - 864 / 897

The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks


Authors:  BrihiJoshi, NeilShah, FrancescoBarbieri....
Published date-11/02/2020
Tasks:  QuestionAnswering, SentimentAnalysis

Abstract: Contextual embeddings derived from transformer-based neural language models have shown state-of-the-art performance for various tasks such as question answering, sentiment analysis, and textual similarity in recent years. Extensive work shows …

Coresets for Regressions with Panel Data


Authors:  LingxiaoHuang, K.Sudhir, NisheethK.Vishnoi....
Published date-11/02/2020

Abstract: This paper introduces the problem of coresets for regression problems to panel data settings. We first define coresets for several variants of regression problems with panel data and then present …

Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation


Authors:  ZhongfenDeng, HaoPeng, CongyingXia....
Published date-11/02/2020
Tasks:  DecisionMaking

Abstract: Review rating prediction of text reviews is a rapidly growing technology with a wide range of applications in natural language processing. However, most existing methods either use hand-crafted features or …

Multi-Task Learning for Calorie Prediction on a Novel Large-Scale Recipe Dataset Enriched with Nutritional Information


Authors:  RobinRuede, VerenaHeusser, LukasFrank....
Published date-11/02/2020
Tasks:  Multi-TaskLearning

Abstract: A rapidly growing amount of content posted online, such as food recipes, opens doors to new exciting applications at the intersection of vision and language. In this work, we aim …

Exploring Question-Specific Rewards for Generating Deep Questions


Authors:  YuxiXie, LiangmingPan, DongzheWang....
Published date-11/02/2020
Tasks:  QuestionGeneration

Abstract: Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with actual question …

Emergent Communication Pretraining for Few-Shot Machine Translation


Authors:  YaoyiranLi, EdoardoM.Ponti, IvanVulić....
Published date-11/02/2020
Tasks:  MachineTranslation, TransferLearning

Abstract: While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's languages …

Filter by

Categories

Tags