Most current question answering datasets frame the task as reading comprehension where the question is about a paragraph or document and the answer often is a span in the document. The Machine Reading group at UCL also provides an overview of reading comprehension tasks.
Neural reading comprehension models have recently achieved impressive gener- alisation results, yet still perform poorly when given adversarially selected input.
The recently proposed BERT~\citep{devlin2018bert} has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc.
READING COMPREHENSION TEXT CLASSIFICATION UNSUPERVISED MACHINE TRANSLATION
In addition, visualization experiments show that our proposed model can better mimic the human reasoning process for conversational MC compared to existing models.
Empirical results show that the state-of-the-art models have an outstanding ability to capture biases contained in the dataset with high accuracy on EASY set.
We evaluate the question generation capability of our method by comparing the BLEU score with existing methods and test our method by fine-tuning the MRC model on the downstream MRC data after training on synthetic data.
LANGUAGE MODELLING MACHINE READING COMPREHENSION QUESTION ANSWERING QUESTION GENERATION
Real-world question answering systems often retrieve potentially relevant documents to a given question through a keyword search, followed by a machine reading comprehension (MRC) step to find the exact answer from them.
The purpose of the reading module is to produce a question-aware representation of the document.
Integrating distributed representations with symbolic operations is essential for reading comprehension requiring complex reasoning, such as counting, sorting and arithmetics, but most existing approaches are hard to scale to more domains or more complex reasoning.
To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation.
Integrating visual features has been proved useful in language representation learning.