@inproceedings{lee-2026-pragmaspan,
title = "{P}ragma{S}pan at {WMT}26: Taxonomy-Guided Few-Shot Error Span Detection and an Empirical Analysis of {MPP}",
author = "Lee, Soyoung",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.101/",
pages = "1678--1688",
ISBN = "979-8-89176-474-3",
abstract = "We present PragmaSpan, a training-free, few-shot GPT-5.5 error-span detector with a seven-axis diagnostic taxonomy for WMT26 Task 1, wrapped in a reliability-oriented harness using incomplete-response-aware retries, deterministic parsing, offset recovery, exact-span deduplication, and independent artifact validation. The taxonomy provides a domain-sensitive diagnostic representation: its interpersonal and discourse axes track domain conversationality and match gold errors at least as often as its traditional axes, with no significant detection-F difference from a standard Multidimensional Quality Metrics (MQM) category tree. We use the system to characterize the severity-weighted Match with Partial overlap and Partial credit (MPP) metric. Across prompt and model comparisons, human-agreement calibration, and post-hoc refinement, we find (i) prompt variants do not differ significantly on our sample, while GPT-4.1-to-GPT-5.5 gains exceed differences among variants; (ii) human{--}human MPP is low on our multi-annotator surrogate sample, and system{--}human agreement is not significantly different from this empirical baseline; (iii) improvements in matched-pair severity or boundary accuracy can coincide with lower MPP, demonstrating the need to interpret MPP jointly with matched-pair diagnostics and match coverage; and (iv) a calibration gain on a single-annotator MQM benchmark does not replicate on a multi-annotator Error Span Annotation benchmark. Interpreting error-span improvements therefore requires complementary metrics and annotation-regime checks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-2026-pragmaspan">
<titleInfo>
<title>PragmaSpan at WMT26: Taxonomy-Guided Few-Shot Error Span Detection and an Empirical Analysis of MPP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soyoung</namePart>
<namePart type="family">Lee</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>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</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">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>We present PragmaSpan, a training-free, few-shot GPT-5.5 error-span detector with a seven-axis diagnostic taxonomy for WMT26 Task 1, wrapped in a reliability-oriented harness using incomplete-response-aware retries, deterministic parsing, offset recovery, exact-span deduplication, and independent artifact validation. The taxonomy provides a domain-sensitive diagnostic representation: its interpersonal and discourse axes track domain conversationality and match gold errors at least as often as its traditional axes, with no significant detection-F difference from a standard Multidimensional Quality Metrics (MQM) category tree. We use the system to characterize the severity-weighted Match with Partial overlap and Partial credit (MPP) metric. Across prompt and model comparisons, human-agreement calibration, and post-hoc refinement, we find (i) prompt variants do not differ significantly on our sample, while GPT-4.1-to-GPT-5.5 gains exceed differences among variants; (ii) human–human MPP is low on our multi-annotator surrogate sample, and system–human agreement is not significantly different from this empirical baseline; (iii) improvements in matched-pair severity or boundary accuracy can coincide with lower MPP, demonstrating the need to interpret MPP jointly with matched-pair diagnostics and match coverage; and (iv) a calibration gain on a single-annotator MQM benchmark does not replicate on a multi-annotator Error Span Annotation benchmark. Interpreting error-span improvements therefore requires complementary metrics and annotation-regime checks.</abstract>
<identifier type="citekey">lee-2026-pragmaspan</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.101/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1678</start>
<end>1688</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PragmaSpan at WMT26: Taxonomy-Guided Few-Shot Error Span Detection and an Empirical Analysis of MPP
%A Lee, Soyoung
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F lee-2026-pragmaspan
%X We present PragmaSpan, a training-free, few-shot GPT-5.5 error-span detector with a seven-axis diagnostic taxonomy for WMT26 Task 1, wrapped in a reliability-oriented harness using incomplete-response-aware retries, deterministic parsing, offset recovery, exact-span deduplication, and independent artifact validation. The taxonomy provides a domain-sensitive diagnostic representation: its interpersonal and discourse axes track domain conversationality and match gold errors at least as often as its traditional axes, with no significant detection-F difference from a standard Multidimensional Quality Metrics (MQM) category tree. We use the system to characterize the severity-weighted Match with Partial overlap and Partial credit (MPP) metric. Across prompt and model comparisons, human-agreement calibration, and post-hoc refinement, we find (i) prompt variants do not differ significantly on our sample, while GPT-4.1-to-GPT-5.5 gains exceed differences among variants; (ii) human–human MPP is low on our multi-annotator surrogate sample, and system–human agreement is not significantly different from this empirical baseline; (iii) improvements in matched-pair severity or boundary accuracy can coincide with lower MPP, demonstrating the need to interpret MPP jointly with matched-pair diagnostics and match coverage; and (iv) a calibration gain on a single-annotator MQM benchmark does not replicate on a multi-annotator Error Span Annotation benchmark. Interpreting error-span improvements therefore requires complementary metrics and annotation-regime checks.
%U https://aclanthology.org/2026.wmt-main.101/
%P 1678-1688
Markdown (Informal)
[PragmaSpan at WMT26: Taxonomy-Guided Few-Shot Error Span Detection and an Empirical Analysis of MPP](https://aclanthology.org/2026.wmt-main.101/) (Lee, WMT 2026)
ACL