<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hassani-etal-2026-temps">
    <titleInfo>
        <title>TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mourad</namePart>
        <namePart type="family">Hassani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julien</namePart>
        <namePart type="family">Romero</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amel</namePart>
        <namePart type="family">Bouzeghoub</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name>
        <namePart>Jacquelinet</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Modern information retrieval (IR) systems rarely represent time, yet many information needs depend on it: in clinical, journalistic, and legal search, when an event occurred can decide whether a document is relevant. Dense retrievers and Retrieval-Augmented Generation (RAG) pipelines match queries to documents well on topic but poorly on time, so they surface content that is on-topic yet temporally wrong. We introduce Temporal Textual Similarity (TTS), a task that measures how well two anchored texts align in time, independent of their topical similarity. We then present TEMPS (Temporal Embedding Model for Precise Search), a modular temporal branch that attaches to a frozen semantic retriever and trains on that signal. It resolves anchored temporal expressions to intervals and moment-matches each one to a Gaussian; the resulting ordering supervises an anchor-date-conditioned encoder, whose score we fuse with the semantic score at inference. Grounding supplies the supervision, so training uses no hand-labeled temporal data. The temporal score itself is the Gaussian-KL inclusion measure from distributional embeddings; what TEMPS adds is the grounding and the moment-matched supervision. On three temporal benchmarks, TEMPS improves MRR for every semantic backbone tested and, on TS-Retriever, lifts R@1 from 19.92 to 25.39 over the prior temporal state of the art.</abstract>
    <identifier type="citekey">hassani-etal-2026-temps</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2657/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>60482</start>
            <end>60505</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval
%A Hassani, Mourad
%A Romero, Julien
%A Bouzeghoub, Amel
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%A Jacquelinet
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F hassani-etal-2026-temps
%X Modern information retrieval (IR) systems rarely represent time, yet many information needs depend on it: in clinical, journalistic, and legal search, when an event occurred can decide whether a document is relevant. Dense retrievers and Retrieval-Augmented Generation (RAG) pipelines match queries to documents well on topic but poorly on time, so they surface content that is on-topic yet temporally wrong. We introduce Temporal Textual Similarity (TTS), a task that measures how well two anchored texts align in time, independent of their topical similarity. We then present TEMPS (Temporal Embedding Model for Precise Search), a modular temporal branch that attaches to a frozen semantic retriever and trains on that signal. It resolves anchored temporal expressions to intervals and moment-matches each one to a Gaussian; the resulting ordering supervises an anchor-date-conditioned encoder, whose score we fuse with the semantic score at inference. Grounding supplies the supervision, so training uses no hand-labeled temporal data. The temporal score itself is the Gaussian-KL inclusion measure from distributional embeddings; what TEMPS adds is the grounding and the moment-matched supervision. On three temporal benchmarks, TEMPS improves MRR for every semantic backbone tested and, on TS-Retriever, lifts R@1 from 19.92 to 25.39 over the prior temporal state of the art.
%U https://aclanthology.org/2026.emnlp-main.2657/
%P 60482-60505

Markdown (Informal)

[TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval](https://aclanthology.org/2026.emnlp-main.2657/) (Hassani et al., EMNLP 2026)

• TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval (Hassani et al., EMNLP 2026)

ACL

• Mourad Hassani, Julien Romero, Amel Bouzeghoub, and Jacquelinet. 2026. TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 60482–60505, Budapest, Hungary. Association for Computational Linguistics.