paper-with-me

Papers

SIGMORPHON–UniMorph 2022 Shared Task 0: Modeling Inflection in Language Acquisition

2022-07-01 · NAACL (SIGMORPHON) 2022 7 · Jordan Kodner, Salam Khalifa

This year’s iteration of the SIGMORPHONUniMorph shared task on “human-like” morphological inflection generation focuses on generalization and errors in language acquisition. Systems are trained on data sets extracted from corpora of child-directed speech in order to simulate a natural learning setting, and their predictions are evaluated against what is known about children’s developmental trajectories for three well-studied patterns: English past tense, German noun plurals, and Arabic noun plurals. Three submitted neural systems were evaluated together with two baselines. Performance was generally good, and all systems were prone to human-like over-regularization. However, all systems were also prone to non-human-like over-irregularization and nonsense productions to varying degrees. We situate this behavior in a discussion of the Past Tense Debate.

📄 PDF Abstract BibTeX

Code (1)

sigmorphon/2022inflectionst 공식 구현

Tasks

Language AcquisitionMorphological Inflection

Similar Papers 제목 키워드 기반

Were We There Already? Applying Minimal Generalization to the SIGMORPHON-UniMorph Shared Task on Cognitively Plausible Morphological Inflection

2021-08-01 · ACL (SIGMORPHON) 2021 8 · Colin Wilson, Jane S.Y. Li

Morphological rules with various levels of specificity can be learned from example lexemes by recursive application of minimal generalization (Albright and Hayes, 2002, 2003). A model that learns rules solely through min…

Morphological InflectionSpecificity

SIGMORPHON–UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection

2022-07-01 · NAACL (SIGMORPHON) 2022 7 · Jordan Kodner, Salam Khalifa, Khuyagbaatar Batsuren, Hossep Dolatian 외

The 2022 SIGMORPHON–UniMorph shared task on large scale morphological inflection generation included a wide range of typologically diverse languages: 33 languages from 11 top-level language families: Arabic (Modern Stand…

Morphological Inflection

Generalizing Morphological Inflection Systems to Unseen Lemmas

2022-07-01 · NAACL (SIGMORPHON) 2022 7 · Changbing Yang, Ruixin (Ray) Yang, Garrett Nicolai, Miikka Silfverberg

This paper presents experiments on morphological inflection using data from the SIGMORPHON-UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection. We present a transformer inflecti…

HallucinationLEMMAMorphological Inflection

SIGMORPHON 2022 Task 0 Submission Description: Modelling Morphological Inflection with Data-Driven and Rule-Based Approaches

2022-07-01 · NAACL (SIGMORPHON) 2022 7 · Tatiana Merzhevich, Nkonye Gbadegoye, Leander Girrbach, Jingwen Li 외

This paper describes our participation in the 2022 SIGMORPHON-UniMorph Shared Task on Typologically Diverse and AcquisitionInspired Morphological Inflection Generation. We present two approaches: one being a modification…

DecoderMorphological Inflection

SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages

2021-08-01 · ACL (SIGMORPHON) 2021 8 · Tiago Pimentel, Maria Ryskina, Sabrina J. Mielke, Shijie Wu 외

This year's iteration of the SIGMORPHON Shared Task on morphological reinflection focuses on typological diversity and cross-lingual variation of morphosyntactic features. In terms of the task, we enrich UniMorph with ne…

Diversity