@inproceedings{suryanarayanan-etal-2025-pralekha,
title = "{PRALEKHA}: Cross-Lingual Document Alignment for {I}ndic Languages",
author = "Suryanarayanan, Sanjay and
Song, Haiyue and
Khan, Mohammed Safi Ur Rahman and
Kunchukuttan, Anoop and
Dabre, Raj",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.37/",
pages = "662--676",
ISBN = "979-8-89176-298-5",
abstract = "Mining parallel document pairs for document-level machine translation (MT) remains challenging due to the limitations of existing Cross-Lingual Document Alignment (CLDA) techniques. Existing methods often rely on metadata such as URLs, which are scarce, or on pooled document representations that fail to capture fine-grained alignment cues. Moreover, the limited context window of sentence embedding models hinders their ability to represent document-level context, while sentence-based alignment introduces a combinatorially large search space, leading to high computational cost. To address these challenges for Indic languages, we introduce Pralekha, a benchmark containing over 3 million aligned document pairs across 11 Indic languages and English, which includes 1.5 million English{--}Indic pairs. Furthermore, we propose Document Alignment Coefficient (DAC), a novel metric for fine-grained document alignment. Unlike pooling-based methods, DAC aligns documents by matching smaller chunks and computes similarity as the ratio of aligned chunks to the average number of chunks in a pair. Intrinsic evaluation shows that our chunk-based method is 2{--}3{\texttimes} faster while maintaining competitive performance, and that DAC achieves substantial gains over pooling-based baselines. Extrinsic evaluation further demonstrates that document-level MT models trained on DAC-aligned pairs consistently outperform those using baseline alignment methods. These results highlight DAC{'}s effectiveness for parallel document mining. The dataset and evaluation framework are publicly available to support further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suryanarayanan-etal-2025-pralekha">
<titleInfo>
<title>PRALEKHA: Cross-Lingual Document Alignment for Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjay</namePart>
<namePart type="family">Suryanarayanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyue</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Safi</namePart>
<namePart type="given">Ur</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Mining parallel document pairs for document-level machine translation (MT) remains challenging due to the limitations of existing Cross-Lingual Document Alignment (CLDA) techniques. Existing methods often rely on metadata such as URLs, which are scarce, or on pooled document representations that fail to capture fine-grained alignment cues. Moreover, the limited context window of sentence embedding models hinders their ability to represent document-level context, while sentence-based alignment introduces a combinatorially large search space, leading to high computational cost. To address these challenges for Indic languages, we introduce Pralekha, a benchmark containing over 3 million aligned document pairs across 11 Indic languages and English, which includes 1.5 million English–Indic pairs. Furthermore, we propose Document Alignment Coefficient (DAC), a novel metric for fine-grained document alignment. Unlike pooling-based methods, DAC aligns documents by matching smaller chunks and computes similarity as the ratio of aligned chunks to the average number of chunks in a pair. Intrinsic evaluation shows that our chunk-based method is 2–3× faster while maintaining competitive performance, and that DAC achieves substantial gains over pooling-based baselines. Extrinsic evaluation further demonstrates that document-level MT models trained on DAC-aligned pairs consistently outperform those using baseline alignment methods. These results highlight DAC’s effectiveness for parallel document mining. The dataset and evaluation framework are publicly available to support further research.</abstract>
<identifier type="citekey">suryanarayanan-etal-2025-pralekha</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.37/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>662</start>
<end>676</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PRALEKHA: Cross-Lingual Document Alignment for Indic Languages
%A Suryanarayanan, Sanjay
%A Song, Haiyue
%A Khan, Mohammed Safi Ur Rahman
%A Kunchukuttan, Anoop
%A Dabre, Raj
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F suryanarayanan-etal-2025-pralekha
%X Mining parallel document pairs for document-level machine translation (MT) remains challenging due to the limitations of existing Cross-Lingual Document Alignment (CLDA) techniques. Existing methods often rely on metadata such as URLs, which are scarce, or on pooled document representations that fail to capture fine-grained alignment cues. Moreover, the limited context window of sentence embedding models hinders their ability to represent document-level context, while sentence-based alignment introduces a combinatorially large search space, leading to high computational cost. To address these challenges for Indic languages, we introduce Pralekha, a benchmark containing over 3 million aligned document pairs across 11 Indic languages and English, which includes 1.5 million English–Indic pairs. Furthermore, we propose Document Alignment Coefficient (DAC), a novel metric for fine-grained document alignment. Unlike pooling-based methods, DAC aligns documents by matching smaller chunks and computes similarity as the ratio of aligned chunks to the average number of chunks in a pair. Intrinsic evaluation shows that our chunk-based method is 2–3× faster while maintaining competitive performance, and that DAC achieves substantial gains over pooling-based baselines. Extrinsic evaluation further demonstrates that document-level MT models trained on DAC-aligned pairs consistently outperform those using baseline alignment methods. These results highlight DAC’s effectiveness for parallel document mining. The dataset and evaluation framework are publicly available to support further research.
%U https://aclanthology.org/2025.ijcnlp-long.37/
%P 662-676
Markdown (Informal)
[PRALEKHA: Cross-Lingual Document Alignment for Indic Languages](https://aclanthology.org/2025.ijcnlp-long.37/) (Suryanarayanan et al., IJCNLP-AACL 2025)
ACL
- Sanjay Suryanarayanan, Haiyue Song, Mohammed Safi Ur Rahman Khan, Anoop Kunchukuttan, and Raj Dabre. 2025. PRALEKHA: Cross-Lingual Document Alignment for Indic Languages. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 662–676, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.