Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
We propose a multi-task learning framework to learn a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains. Inspired by recent ideas of data selection in machine translation, we develop a novel sample re-weighting scheme to assign sample-specific weights to the loss. Empirical study shows that our approach can be applied to many existing MRC models. Combined with contextual representations from pre-trained language models (such as ELMo), we achieve new state-of-the-art results on a set of MRC benchmark datasets. We release our code at https://github.com/xycforgithub/MultiTask-MRC.
Code (5)
Tasks
Machine Reading ComprehensionMachine TranslationMulti-Task LearningQuestion AnsweringReading ComprehensionTranslationSimilar Papers 제목 키워드 기반
Words or Characters? Fine-grained Gating for Reading Comprehension
Previous work combines word-level and character-level representations using concatenation or scalar weighting, which is suboptimal for high-level tasks like reading comprehension. We present a fine-grained gating mechani…
Question AnsweringReading ComprehensionTAGMultiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification
Whole body magnetic resonance imaging (WB-MRI) is the recommended modality for diagnosis of multiple myeloma (MM). WB-MRI is used to detect sites of disease across the entire skeletal system, but it requires significant …
Multiple Instance LearningMulti-Task LearningAdversarial Regression with Doubly Non-negative Weighting Matrices
Many machine learning tasks that involve predicting an output response can be solved by training a weighted regression model. Unfortunately, the predictive power of this type of models may severely deteriorate under low …
regressionMRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark
Machine Reading Comprehension (MRC) is an essential task in evaluating natural language understanding. Existing MRC datasets primarily assess specific aspects of reading comprehension (RC), lacking a comprehensive MRC be…
Machine Reading ComprehensionNatural Language UnderstandingReading ComprehensionTF-IDFC-RF: A Novel Supervised Term Weighting Scheme
Sentiment Analysis is a branch of Affective Computing usually considered a binary classification task. In this line of reasoning, Sentiment Analysis can be applied in several contexts to classify the attitude expressed i…
Binary ClassificationSentiment Analysis