@inproceedings{dong-etal-2024-mc,
title = "{MC}-indexing: Effective Long Document Retrieval via Multi-view Content-aware Indexing",
author = "Dong, Kuicai and
Goh Xin Deik, Derrick and
Lee, Yi Quan and
Zhang, Hao and
Li, Xiangyang and
Zhang, Cong and
Liu, Yong",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.150/",
doi = "10.18653/v1/2024.findings-emnlp.150",
pages = "2673--2691",
abstract = "Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and paragraph demarcations. However, the indexing methods of long documents remain under-explored, while existing systems generally employ fixed-length chunking. As they do not consider content structures, the resultant chunks can exclude vital information or include irrelevant content. Motivated by this, we propose the **M**ulti-view **C**ontent-aware indexing (**MC-indexing**) for more effective long DocQA via (i) segment structured document into content chunks, and (ii) represent each content chunk in raw-text, keywords, and summary views. We highlight that MC-indexing requires neither training nor fine-tuning. Having plug-and-play capability, it can be seamlessly integrated with any retrievers to boost their performance. Besides, we propose a long DocQA dataset that includes not only question-answer pair, but also document structure and answer scope. When compared to state-of-art chunking schemes, MC-indexing has significantly increased the recall by **42.8{\%}**, **30.0{\%}**, **23.9{\%}**, and **16.3{\%}** via top k = 1.5, 3, 5, and 10 respectively. These improved scores are the average of 8 widely used retrievers (2 sparse and 6 dense) via extensive experiments."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2024-mc">
<titleInfo>
<title>MC-indexing: Effective Long Document Retrieval via Multi-view Content-aware Indexing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kuicai</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derrick</namePart>
<namePart type="family">Goh Xin Deik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">Quan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and paragraph demarcations. However, the indexing methods of long documents remain under-explored, while existing systems generally employ fixed-length chunking. As they do not consider content structures, the resultant chunks can exclude vital information or include irrelevant content. Motivated by this, we propose the **M**ulti-view **C**ontent-aware indexing (**MC-indexing**) for more effective long DocQA via (i) segment structured document into content chunks, and (ii) represent each content chunk in raw-text, keywords, and summary views. We highlight that MC-indexing requires neither training nor fine-tuning. Having plug-and-play capability, it can be seamlessly integrated with any retrievers to boost their performance. Besides, we propose a long DocQA dataset that includes not only question-answer pair, but also document structure and answer scope. When compared to state-of-art chunking schemes, MC-indexing has significantly increased the recall by **42.8%**, **30.0%**, **23.9%**, and **16.3%** via top k = 1.5, 3, 5, and 10 respectively. These improved scores are the average of 8 widely used retrievers (2 sparse and 6 dense) via extensive experiments.</abstract>
<identifier type="citekey">dong-etal-2024-mc</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.150</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.150/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>2673</start>
<end>2691</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MC-indexing: Effective Long Document Retrieval via Multi-view Content-aware Indexing
%A Dong, Kuicai
%A Goh Xin Deik, Derrick
%A Lee, Yi Quan
%A Zhang, Hao
%A Li, Xiangyang
%A Zhang, Cong
%A Liu, Yong
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F dong-etal-2024-mc
%X Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and paragraph demarcations. However, the indexing methods of long documents remain under-explored, while existing systems generally employ fixed-length chunking. As they do not consider content structures, the resultant chunks can exclude vital information or include irrelevant content. Motivated by this, we propose the **M**ulti-view **C**ontent-aware indexing (**MC-indexing**) for more effective long DocQA via (i) segment structured document into content chunks, and (ii) represent each content chunk in raw-text, keywords, and summary views. We highlight that MC-indexing requires neither training nor fine-tuning. Having plug-and-play capability, it can be seamlessly integrated with any retrievers to boost their performance. Besides, we propose a long DocQA dataset that includes not only question-answer pair, but also document structure and answer scope. When compared to state-of-art chunking schemes, MC-indexing has significantly increased the recall by **42.8%**, **30.0%**, **23.9%**, and **16.3%** via top k = 1.5, 3, 5, and 10 respectively. These improved scores are the average of 8 widely used retrievers (2 sparse and 6 dense) via extensive experiments.
%R 10.18653/v1/2024.findings-emnlp.150
%U https://aclanthology.org/2024.findings-emnlp.150/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.150
%P 2673-2691
Markdown (Informal)
[MC-indexing: Effective Long Document Retrieval via Multi-view Content-aware Indexing](https://aclanthology.org/2024.findings-emnlp.150/) (Dong et al., Findings 2024)
ACL
- Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee, Hao Zhang, Xiangyang Li, Cong Zhang, and Yong Liu. 2024. MC-indexing: Effective Long Document Retrieval via Multi-view Content-aware Indexing. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2673–2691, Miami, Florida, USA. Association for Computational Linguistics.