material ID: mctest

Related Papers

A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data

Authors: nan

Publication: TIPSTER (2016)

DOI: nan

Understanding unstructured text is a ma- jor goal within natural language process- ing. Comprehension tests pose questions based on short text passages to evaluate such understanding. In this work, we …...

40540

Attention-Based Convolutional Neural Network for Machine Comprehension

Authors: nan

Publication: TIPSTER (2016)

DOI: nan

Understanding open-domain text is one of the primary challenges in NLP. Machine com- prehension benchmarks evaluate a system’s ability to understand text based on the text content only. In this …...

27326

Evaluation Metrics for Machine Reading Comprehension: Prerequisite Skills and Readability

Authors: nan

Publication: TIPSTER (2017)

DOI: nan

AbstractKnowing the quality of reading comprehension (RC) datasets is important for the development of natural-language understanding systems. In this study, two classes of metrics were adopted for evaluating RC datasets: …...

40039

Reading Comprehension with Graph-based Temporal-Casual Reasoning

Authors: nan

Publication: TIPSTER (2018)

DOI: nan

AbstractComplex questions in reading comprehension tasks require integrating information from multiple sentences. In this work, to answer such questions involving temporal and causal relations, we generate event graphs from text …...

5448

Supervised and Unsupervised Transfer Learning for Question Answering

Authors: nan

Publication: TIPSTER (2018)

DOI: nan

AbstractAlthough transfer learning has been shown to be successful for tasks like object and speech recognition, its applicability to question answering (QA) has yet to be well-studied. In this paper, …...

20892

Improving Machine Reading Comprehension with General Reading Strategies

Authors: nan

Publication: TIPSTER (2019)

DOI: nan

AbstractReading strategies have been shown to improve comprehension levels, especially for readers lacking adequate prior knowledge. Just as the process of knowledge accumulation is time-consuming for human readers, it is …...

22014

Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain from Text

Authors: nan

Publication: TIPSTER (2019)

DOI: nan

AbstractThis paper focuses on the topic of inferential machine comprehension, which aims to fully understand the meanings of given text to answer generic questions, especially the ones needed reasoning skills. …...

39743