Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism

Neural auto-regressive sequence-to-sequence models have been dominant in text generation tasks, especially the question generation task. However, neural generation models suffer from the global and local semantic semantic drift problems. Hence, we propose the hierarchical encoding–decoding mechanism...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tianbo Ji, Chenyang Lyu, Zhichao Cao, Peng Cheng
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	multi-hop question generation hierarchical encoding-decoding syntactic knowledge Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/9ea3193bfe014b1ba4773bde0b5c6f0d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9ea3193bfe014b1ba4773bde0b5c6f0d
record_format	dspace
spelling	oai:doaj.org-article:9ea3193bfe014b1ba4773bde0b5c6f0d2021-11-25T17:29:45ZMulti-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism10.3390/e231114491099-4300https://doaj.org/article/9ea3193bfe014b1ba4773bde0b5c6f0d2021-10-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1449https://doaj.org/toc/1099-4300Neural auto-regressive sequence-to-sequence models have been dominant in text generation tasks, especially the question generation task. However, neural generation models suffer from the global and local semantic semantic drift problems. Hence, we propose the hierarchical encoding–decoding mechanism that aims at encoding rich structure information of the input passages and reducing the variance in the decoding phase. In the encoder, we hierarchically encode the input passages according to its structure at four granularity-levels: [word, chunk, sentence, document]-level. Second, we progressively select the context vector from the document-level representations to the word-level representations at each decoding time step. At each time-step in the decoding phase, we progressively select the context vector from the document-level representations to word-level. We also propose the context switch mechanism that enables the decoder to use the context vector from the last step when generating the current word at each time-step.It provides a means of improving the stability of the text generation process during the decoding phase when generating a set of consecutive words. Additionally, we inject syntactic parsing knowledge to enrich the word representations. Experimental results show that our proposed model substantially improves the performance and outperforms previous baselines according to both automatic and human evaluation. Besides, we implement a deep and comprehensive analysis of generated questions based on their types.Tianbo JiChenyang LyuZhichao CaoPeng ChengMDPI AGarticlemulti-hop question generationhierarchical encoding-decodingsyntactic knowledgeScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1449, p 1449 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	multi-hop question generation hierarchical encoding-decoding syntactic knowledge Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	multi-hop question generation hierarchical encoding-decoding syntactic knowledge Science Q Astrophysics QB460-466 Physics QC1-999 Tianbo Ji Chenyang Lyu Zhichao Cao Peng Cheng Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
description	Neural auto-regressive sequence-to-sequence models have been dominant in text generation tasks, especially the question generation task. However, neural generation models suffer from the global and local semantic semantic drift problems. Hence, we propose the hierarchical encoding–decoding mechanism that aims at encoding rich structure information of the input passages and reducing the variance in the decoding phase. In the encoder, we hierarchically encode the input passages according to its structure at four granularity-levels: [word, chunk, sentence, document]-level. Second, we progressively select the context vector from the document-level representations to the word-level representations at each decoding time step. At each time-step in the decoding phase, we progressively select the context vector from the document-level representations to word-level. We also propose the context switch mechanism that enables the decoder to use the context vector from the last step when generating the current word at each time-step.It provides a means of improving the stability of the text generation process during the decoding phase when generating a set of consecutive words. Additionally, we inject syntactic parsing knowledge to enrich the word representations. Experimental results show that our proposed model substantially improves the performance and outperforms previous baselines according to both automatic and human evaluation. Besides, we implement a deep and comprehensive analysis of generated questions based on their types.
format	article
author	Tianbo Ji Chenyang Lyu Zhichao Cao Peng Cheng
author_facet	Tianbo Ji Chenyang Lyu Zhichao Cao Peng Cheng
author_sort	Tianbo Ji
title	Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
title_short	Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
title_full	Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
title_fullStr	Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
title_full_unstemmed	Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
title_sort	multi-hop question generation using hierarchical encoding-decoding and context switch mechanism
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9ea3193bfe014b1ba4773bde0b5c6f0d
work_keys_str_mv	AT tianboji multihopquestiongenerationusinghierarchicalencodingdecodingandcontextswitchmechanism AT chenyanglyu multihopquestiongenerationusinghierarchicalencodingdecodingandcontextswitchmechanism AT zhichaocao multihopquestiongenerationusinghierarchicalencodingdecodingandcontextswitchmechanism AT pengcheng multihopquestiongenerationusinghierarchicalencodingdecodingandcontextswitchmechanism
_version_	1718412301670809600

Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism

Ejemplares similares