Multi-Hop Reading Comprehension

8 papers with code • 0 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Cognitive Graph for Multi-Hop Reading Comprehension at Scale


We propose a new CogQA framework for multi-hop question answering in web-scale documents.

Multi-hop Reading Comprehension through Question Decomposition and Rescoring

shmsw25/DecompRC ACL 2019

Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs.

Exploiting Explicit Paths for Multi-hop Reading Comprehension

allenai/PathNet ACL 2019

To capture additional context, PathNet also composes the passage representations along each path to compute a passage-based representation.

Compositional Questions Do Not Necessitate Multi-hop Reasoning

shmsw25/single-hop-rc ACL 2019

Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs.

Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

jiangycTarheel/EPAr ACL 2019

Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context.

Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents

jd-ai-research-silicon-valley/sae 1 Nov 2019

Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences.

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension

stonybrooknlp/suqa EMNLP 2021

Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system.

How Well Do Multi-hop Reading Comprehension Models Understand Date Information?

alab-nii/hieradate 11 Oct 2022

Other results reveal that our probing questions can help to improve the performance of the models (e. g., by +10. 3 F1) on the main QA task and our dataset can be used for data augmentation to improve the robustness of the models.