SlotGAN: Detecting Mentions in Text via Adversarial Distant Learning

Daniel Daza, Michael Cochez, Paul Groth

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present SlotGAN, a framework for training a mention detection model that only requires unlabeled text and a gazetteer. It consists of a generator trained to extract spans from an input sentence, and a discriminator trained to determine whether a span comes from the generator, or from the gazetteer.We evaluate the method on English newswire data and compare it against supervised, weakly-supervised, and unsupervised methods. We find that the performance of the method is lower than these baselines, because it tends to generate more and longer spans, and in some cases it relies only on capitalization. In other cases, it generates spans that are valid but differ from the benchmark. When evaluated with metrics based on overlap, we find that SlotGAN performs within 95 and 84 but an additional filtering mechanism is required.
Original languageEnglish
Title of host publicationProceedings of the Sixth Workshop on Structured Prediction for NLP
Place of PublicationDublin, Ireland
PublisherAssociation for Computational Linguistics (ACL)
Pages32-39
Number of pages8
DOIs
StatePublished - May 1 2022
Externally publishedYes

Fingerprint

Dive into the research topics of 'SlotGAN: Detecting Mentions in Text via Adversarial Distant Learning'. Together they form a unique fingerprint.
  • DL: ICAI Discovery Lab

    van Harmelen, F., De Rijke, M., Siebert, M., Hoekstra, R., Tsatsaronis, G., Groth, P., Cochez, M., Pernisch, R., Alivanistos, D., Mansoury, M., van Hoof, H., Pal, V., Pijnenburg, T., Mitra, P., Bey, T. & de Waard, A.

    10/1/1903/31/25

    Project: Research

Cite this