@inproceedings{guha-majumdar-2026-extractive,
title = "Extractive Corroboration Pipeline for Crisis Situation Report Generation from Social Media",
author = "Guha Majumdar, Sreeja",
editor = "Ticona, Belu and
Xia, Fei and
Lewis, William D. and
Anastasopoulos, Antonios",
booktitle = "Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.lt4cpr-1.14/",
pages = "156--165",
ISBN = "979-8-89176-450-7",
abstract = "Automatic generation of crisis situation reports from social media requires transforming noisy, short-form text into structured, evidence-grounded prose, without access to information outside a single bounded time window. This paper describes an extractive pipeline submitted to a shared task on this problem: a supervised section classifier trained on tweet-to-bullet citation links, corroboration-based confidence estimation, safety-netted extractive bullet-text synthesis, and rule-based temporal filtering. The submitted system passes the task{'}s structural validator on all official test cells, spanning crisis types absent from training, and receives an official evaluation score of 0.480. Decomposing the two metrics composing this score shows that the system obtains a BERTScore F1 of 0.508 and a BLEURT score of 0.451, exposing a substantial difference between semantic similarity and learned fluency/adequacy evaluation. Development-time diagnostics, including a coreference-recall experiment and a per-section quality breakdown, provide independent evidence that extractive text generation is a major remaining limitation. Three architectural alternatives tested during development are reported with their measurements rather than omitted, and a scoped, safety-netted rewrite step is identified as a direct next architectural extension."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guha-majumdar-2026-extractive">
<titleInfo>
<title>Extractive Corroboration Pipeline for Crisis Situation Report Generation from Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sreeja</namePart>
<namePart type="family">Guha Majumdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response</title>
</titleInfo>
<name type="personal">
<namePart type="given">Belu</namePart>
<namePart type="family">Ticona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-450-7</identifier>
</relatedItem>
<abstract>Automatic generation of crisis situation reports from social media requires transforming noisy, short-form text into structured, evidence-grounded prose, without access to information outside a single bounded time window. This paper describes an extractive pipeline submitted to a shared task on this problem: a supervised section classifier trained on tweet-to-bullet citation links, corroboration-based confidence estimation, safety-netted extractive bullet-text synthesis, and rule-based temporal filtering. The submitted system passes the task’s structural validator on all official test cells, spanning crisis types absent from training, and receives an official evaluation score of 0.480. Decomposing the two metrics composing this score shows that the system obtains a BERTScore F1 of 0.508 and a BLEURT score of 0.451, exposing a substantial difference between semantic similarity and learned fluency/adequacy evaluation. Development-time diagnostics, including a coreference-recall experiment and a per-section quality breakdown, provide independent evidence that extractive text generation is a major remaining limitation. Three architectural alternatives tested during development are reported with their measurements rather than omitted, and a scoped, safety-netted rewrite step is identified as a direct next architectural extension.</abstract>
<identifier type="citekey">guha-majumdar-2026-extractive</identifier>
<location>
<url>https://aclanthology.org/2026.lt4cpr-1.14/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>156</start>
<end>165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extractive Corroboration Pipeline for Crisis Situation Report Generation from Social Media
%A Guha Majumdar, Sreeja
%Y Ticona, Belu
%Y Xia, Fei
%Y Lewis, William D.
%Y Anastasopoulos, Antonios
%S Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-450-7
%F guha-majumdar-2026-extractive
%X Automatic generation of crisis situation reports from social media requires transforming noisy, short-form text into structured, evidence-grounded prose, without access to information outside a single bounded time window. This paper describes an extractive pipeline submitted to a shared task on this problem: a supervised section classifier trained on tweet-to-bullet citation links, corroboration-based confidence estimation, safety-netted extractive bullet-text synthesis, and rule-based temporal filtering. The submitted system passes the task’s structural validator on all official test cells, spanning crisis types absent from training, and receives an official evaluation score of 0.480. Decomposing the two metrics composing this score shows that the system obtains a BERTScore F1 of 0.508 and a BLEURT score of 0.451, exposing a substantial difference between semantic similarity and learned fluency/adequacy evaluation. Development-time diagnostics, including a coreference-recall experiment and a per-section quality breakdown, provide independent evidence that extractive text generation is a major remaining limitation. Three architectural alternatives tested during development are reported with their measurements rather than omitted, and a scoped, safety-netted rewrite step is identified as a direct next architectural extension.
%U https://aclanthology.org/2026.lt4cpr-1.14/
%P 156-165
Markdown (Informal)
[Extractive Corroboration Pipeline for Crisis Situation Report Generation from Social Media](https://aclanthology.org/2026.lt4cpr-1.14/) (Guha Majumdar, LT4CPR 2026)
ACL