TeCoFeS: Text Column Featurization using Semantic Analysis

Ananya Singha; Mukul Singh; Ashish Tiwari; Sumit Gulwani; Vu Le; Chris Parnin

doi:10.18653/v1/2025.findings-naacl.392

TeCoFeS: Text Column Featurization using Semantic Analysis

Ananya Singha, Mukul Singh, Ashish Tiwari, Sumit Gulwani, Vu Le, Chris Parnin

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Extracting insights from text columns can bechallenging and time-intensive. Existing methods for topic modeling and feature extractionare based on syntactic features and often overlook the semantics. We introduce the semantictext column featurization problem, and presenta scalable approach for automatically solvingit. We extract a small sample smartly, use alarge language model (LLM) to label only thesample, and then lift the labeling to the wholecolumn using text embeddings. We evaluateour approach by turning existing text classification benchmarks into semantic categorization benchmarks. Our approach performs better than baselines and naive use of LLMs.

Anthology ID:: 2025.findings-naacl.392
Volume:: Findings of the Association for Computational Linguistics: NAACL 2025
Month:: April
Year:: 2025
Address:: Albuquerque, New Mexico
Editors:: Luis Chiruzzo, Alan Ritter, Lu Wang
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 7055–7061
Language:
URL:: https://aclanthology.org/2025.findings-naacl.392/
DOI:: 10.18653/v1/2025.findings-naacl.392
Bibkey:
Cite (ACL):: Ananya Singha, Mukul Singh, Ashish Tiwari, Sumit Gulwani, Vu Le, and Chris Parnin. 2025. TeCoFeS: Text Column Featurization using Semantic Analysis. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 7055–7061, Albuquerque, New Mexico. Association for Computational Linguistics.
Cite (Informal):: TeCoFeS: Text Column Featurization using Semantic Analysis (Singha et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-naacl.392.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{singha-etal-2025-tecofes,
    title = "{T}e{C}o{F}e{S}: Text Column Featurization using Semantic Analysis",
    author = "Singha, Ananya  and
      Singh, Mukul  and
      Tiwari, Ashish  and
      Gulwani, Sumit  and
      Le, Vu  and
      Parnin, Chris",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-naacl.392/",
    doi = "10.18653/v1/2025.findings-naacl.392",
    pages = "7055--7061",
    ISBN = "979-8-89176-195-7",
    abstract = "Extracting insights from text columns can bechallenging and time-intensive. Existing methods for topic modeling and feature extractionare based on syntactic features and often overlook the semantics. We introduce the semantictext column featurization problem, and presenta scalable approach for automatically solvingit. We extract a small sample smartly, use alarge language model (LLM) to label only thesample, and then lift the labeling to the wholecolumn using text embeddings. We evaluateour approach by turning existing text classification benchmarks into semantic categorization benchmarks. Our approach performs better than baselines and naive use of LLMs."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singha-etal-2025-tecofes">
    <titleInfo>
        <title>TeCoFeS: Text Column Featurization using Semantic Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ananya</namePart>
        <namePart type="family">Singha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mukul</namePart>
        <namePart type="family">Singh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ashish</namePart>
        <namePart type="family">Tiwari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sumit</namePart>
        <namePart type="family">Gulwani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vu</namePart>
        <namePart type="family">Le</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chris</namePart>
        <namePart type="family">Parnin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-195-7</identifier>
    </relatedItem>
    <abstract>Extracting insights from text columns can bechallenging and time-intensive. Existing methods for topic modeling and feature extractionare based on syntactic features and often overlook the semantics. We introduce the semantictext column featurization problem, and presenta scalable approach for automatically solvingit. We extract a small sample smartly, use alarge language model (LLM) to label only thesample, and then lift the labeling to the wholecolumn using text embeddings. We evaluateour approach by turning existing text classification benchmarks into semantic categorization benchmarks. Our approach performs better than baselines and naive use of LLMs.</abstract>
    <identifier type="citekey">singha-etal-2025-tecofes</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-naacl.392</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-naacl.392/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>7055</start>
            <end>7061</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T TeCoFeS: Text Column Featurization using Semantic Analysis
%A Singha, Ananya
%A Singh, Mukul
%A Tiwari, Ashish
%A Gulwani, Sumit
%A Le, Vu
%A Parnin, Chris
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F singha-etal-2025-tecofes
%X Extracting insights from text columns can bechallenging and time-intensive. Existing methods for topic modeling and feature extractionare based on syntactic features and often overlook the semantics. We introduce the semantictext column featurization problem, and presenta scalable approach for automatically solvingit. We extract a small sample smartly, use alarge language model (LLM) to label only thesample, and then lift the labeling to the wholecolumn using text embeddings. We evaluateour approach by turning existing text classification benchmarks into semantic categorization benchmarks. Our approach performs better than baselines and naive use of LLMs.
%R 10.18653/v1/2025.findings-naacl.392
%U https://aclanthology.org/2025.findings-naacl.392/
%U https://doi.org/10.18653/v1/2025.findings-naacl.392
%P 7055-7061

Download as File

Markdown (Informal)

[TeCoFeS: Text Column Featurization using Semantic Analysis](https://aclanthology.org/2025.findings-naacl.392/) (Singha et al., Findings 2025)

TeCoFeS: Text Column Featurization using Semantic Analysis (Singha et al., Findings 2025)

ACL

Ananya Singha, Mukul Singh, Ashish Tiwari, Sumit Gulwani, Vu Le, and Chris Parnin. 2025. TeCoFeS: Text Column Featurization using Semantic Analysis. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 7055–7061, Albuquerque, New Mexico. Association for Computational Linguistics.