@inproceedings{makinae-etal-2026-inside,
title = "Inside Sentence Embeddings: Leveraging Token Representations for Machine Translation Evaluation and Word Alignment",
author = "Makinae, Mana and
Goto, Takumi and
Sakai, Yusuke and
Kamigaito, Hidetaka and
Watanabe, Taro",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2214/",
pages = "47431--47438",
ISBN = "979-8-89176-462-0",
abstract = "Contextualized token-level embeddings from encoders, e.g., mBERT, are used for several cross-lingual tasks, e.g., machine translation (MT) evaluation and alignment tasks, but fine-tuning is required for the specific task settings. In contrast, multilingual sentence embeddings are trained under sentence-level objectives on parallel data, but their token-level representations remain unclear whether they carry cross-lingual semantics, although not explicitly trained with token-level objectives. In this paper, we investigate token representations extracted from multilingual sentence embedding models for MT evaluation and word alignment. Experimental results and analysis show that sentence embedding models can provide useful token-level representations for direct similarity-based tasks. Although the observed advantage is not consistent across all settings, the results indicate that multilingual sentence-level training may support token-level semantic similarity without explicit token-level training."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="makinae-etal-2026-inside">
<titleInfo>
<title>Inside Sentence Embeddings: Leveraging Token Representations for Machine Translation Evaluation and Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mana</namePart>
<namePart type="family">Makinae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takumi</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Contextualized token-level embeddings from encoders, e.g., mBERT, are used for several cross-lingual tasks, e.g., machine translation (MT) evaluation and alignment tasks, but fine-tuning is required for the specific task settings. In contrast, multilingual sentence embeddings are trained under sentence-level objectives on parallel data, but their token-level representations remain unclear whether they carry cross-lingual semantics, although not explicitly trained with token-level objectives. In this paper, we investigate token representations extracted from multilingual sentence embedding models for MT evaluation and word alignment. Experimental results and analysis show that sentence embedding models can provide useful token-level representations for direct similarity-based tasks. Although the observed advantage is not consistent across all settings, the results indicate that multilingual sentence-level training may support token-level semantic similarity without explicit token-level training.</abstract>
<identifier type="citekey">makinae-etal-2026-inside</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2214/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>47431</start>
<end>47438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inside Sentence Embeddings: Leveraging Token Representations for Machine Translation Evaluation and Word Alignment
%A Makinae, Mana
%A Goto, Takumi
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F makinae-etal-2026-inside
%X Contextualized token-level embeddings from encoders, e.g., mBERT, are used for several cross-lingual tasks, e.g., machine translation (MT) evaluation and alignment tasks, but fine-tuning is required for the specific task settings. In contrast, multilingual sentence embeddings are trained under sentence-level objectives on parallel data, but their token-level representations remain unclear whether they carry cross-lingual semantics, although not explicitly trained with token-level objectives. In this paper, we investigate token representations extracted from multilingual sentence embedding models for MT evaluation and word alignment. Experimental results and analysis show that sentence embedding models can provide useful token-level representations for direct similarity-based tasks. Although the observed advantage is not consistent across all settings, the results indicate that multilingual sentence-level training may support token-level semantic similarity without explicit token-level training.
%U https://aclanthology.org/2026.findings-emnlp.2214/
%P 47431-47438
Markdown (Informal)
[Inside Sentence Embeddings: Leveraging Token Representations for Machine Translation Evaluation and Word Alignment](https://aclanthology.org/2026.findings-emnlp.2214/) (Makinae et al., Findings 2026)
ACL