Science

A hierarchical, answer-aware, context-aware network for question generation

Credit: Frontiers of Laptop Science (2023). DOI: 10.1007/s11704-023-2246-2

In academic settings, lecturers usually have to formulate some studying comprehension questions for a passage as an alternative of a single sentence. Tips on how to get hold of and exploit an answer-aware and context-aware passage-level illustration is a problem.

To resolve this drawback, a research workforce led by Qi Liu revealed their new research on 15 October 2024 in Frontiers of Laptop Science.

The workforce proposed a hierarchical answer-aware and context-aware community for query technology that focuses on easy methods to assemble and exploit the passage-level illustration for producing questions. In contrast with the present analysis outcomes, the proposed methodology can successfully make the most of passages for producing questions.

Within the analysis, the community primarily comprises two modules, i.e., Hierarchical Passage Encoder (HPE) and Hierarchical Passage-aware Decoder (HPD). Particularly, HPE consists of two-level answer-aware and context-aware consideration with multi-hop reasoning, which goals to generate a greater answer-aware and context-aware passage-level illustration.

HPD consists of a passage-aware decoder and a three-way copy mechanism to find out how a lot passage-level data is required throughout decoding and duplicate uncommon phrases from the answer-specific sentence or the passage.

Intensive experimental outcomes and case studies show that the hierarchical answer-aware and content-aware community proposed on this paper can successfully make the most of passages for producing questions.

The workforce additionally plans to broaden their community to multilingual questions and to optimize for various kinds of questions throughout varied topics.

Extra data:
Ruijun Solar et al, HACAN: a hierarchical answer-aware and context-aware community for query technology, Frontiers of Laptop Science (2024). DOI: 10.1007/s11704-023-2246-2

Offered by
Frontiers Journals

Quotation:
A hierarchical, answer-aware, context-aware community for query technology (2024, October 23)
retrieved 23 October 2024
from https://techxplore.com/information/2024-10-hierarchical-aware-context-network-generation.html

This doc is topic to copyright. Other than any honest dealing for the aim of personal research or analysis, no
half could also be reproduced with out the written permission. The content material is supplied for data functions solely.



Click Here To Join Our Telegram Channel


Source link

You probably have any considerations or complaints relating to this text, please tell us and the article will probably be eliminated quickly. 

Raise A Concern

Show More

Related Articles

Back to top button