Semantic search as extractive paraphrase span detection: Semantic search as extractive...: J. Kanerva et al.

In this paper, we approach the problem of semantic search by introducing a task of paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given document, the same modelling setup as typically used in extractive question answering. While...

Descripción completa

Detalles Bibliográficos
Publicado en:Language Resources & Evaluation Vol. 59; no. 1; pp. 257 - 277
Autores principales: Kanerva, Jenna, Kitti, Hanna, Chang, Li-Hsin, Vahtola, Teemu, Creutz, Mathias, Ginter, Filip
Formato: Artículo
Publicado: Springer Nature Mar2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=183750667&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 183750667
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Mar2025
      vid: 59
      iid: 1
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        183750667
        10.1007/s10579-023-09715-7
      ppf: 257
      ppct: 20
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 1.5MB
      tig:
        atl: Semantic search as extractive paraphrase span detection: Semantic search as extractive...: J. Kanerva et al.
      aug:
        au:
          Kanerva, Jenna
          Kitti, Hanna
          Chang, Li-Hsin
          Vahtola, Teemu
          Creutz, Mathias
          Ginter, Filip
        affil:
          https://ror.org/05vghhr25 TurkuNLP, Department of Computing, University of Turku, Turku, Finland
          https://ror.org/040af2s02 Department of Digital Humanities, Faculty of Arts, University of Helsinki, Helsinki, Finland
      su:
        Heather
        Paraphrase
        Corpora
        Terms & phrases
        Possibility
      sug:
        subj:
          Heather
          Paraphrase
          Corpora
          Terms & phrases
          Possibility
      keyword:
        Finnish
        Paraphrase retrieval
        Paraphrasing
        Semantic search
      ab: In this paper, we approach the problem of semantic search by introducing a task of paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given document, the same modelling setup as typically used in extractive question answering. While current work in paraphrasing has almost uniquely focused on sentence-level approaches, the novel span detection approach gives a possibility to retrieve a segment of arbitrary length. On the Turku Paraphrase Corpus of 100,000 manually extracted Finnish paraphrase pairs including their original document context, we find that by achieving an exact match of 88.73 our paraphrase span detection approach outperforms widely adopted sentence-level retrieval baselines (lexical similarity as well as BERT and SBERT sentence embeddings) by more than 20pp in terms of exact match, and 11pp in terms of token-level F-score. This demonstrates a strong advantage of modelling the paraphrase retrieval in terms of span extraction rather than commonly used sentence similarity, the sentence-level approaches being clearly suboptimal for applications where the retrieval targets are not guaranteed to be full sentences. Even when limiting the evaluation to sentence-level retrieval targets only, the span detection model still outperforms the sentence-level baselines by more than 4 pp in terms of exact match, and almost 6pp F-score. Additionally, we introduce a method for creating artificial paraphrase data through back-translation, suitable for languages where manually annotated paraphrase resources for training the span detection model are not available.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2025. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N