A Case Study on Meaning Representation for Vietnamese

Linh, Ha My; Nguyen, Huyen

doi:10.18653/v1/w19-3317

Cited by 9 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to compare human judgments and AMR judgments, we develop the first French-English AMR parallel corpus, which represents the first application of AMR to French. We produce gold AMR annotations for 100 sentences, which were randomly sampled, from the REFreSD dataset (Briakou and Carpuat, 2020;Linh and Nguyen, 2019 Findings from Corpus Annotation In light of our research question considering whether AMR can serve as a proxy of fine-grained semantic divergence, we consider both qualitative and quantitative evidence. While producing this small corpus of French-English parallel AMRs, our suspicions that AMR would be able to more fully capture semantic divergence than perceived sentencelevel divergence were confirmed.…”

Section: Examination Of Gold Amr Datamentioning

confidence: 99%

Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation

Wein¹,

Wang²,

Schneider³

2022

Preprint

View full text Add to dashboard Cite

Identifying semantically equivalent sentences is important for many cross-lingual and monolingual NLP tasks. Current approaches to semantic equivalence take a loose, sentencelevel approach to "equivalence," despite previous evidence that fine-grained differences and implicit content have an effect on human understanding (Roth and Anthonio, 2021) and system performance (Briakou and Carpuat, 2021). In this work, we introduce a novel, more sensitive method of characterizing semantic equivalence that leverages Abstract Meaning Representation graph structures. We develop an approach, which can be used with either gold or automatic AMR annotations, and demonstrate that our solution is in fact finer-grained than existing corpus filtering methods and more accurate at predicting strictly equivalent sentences than existing semantic similarity metrics. We suggest that our finer-grained measure of semantic equivalence could limit the workload in the task of human post-edited machine translation and in human evaluation of sentence similarity.

show abstract

Section: Examination Of Gold Amr Datamentioning

confidence: 99%

Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation

Wein¹,

Wang²,

Schneider³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Though AMR was originally designed for English (Banarescu et al, 2013), AMR's abstraction away from morphosyntactic variation lends itself to crosslingual adaptation by capturing shared semantic structure (Li et al, 2016). Cross-lingual adaptations of AMR have been developed and evaluated for Czech , Chinese (Xue et al, 2014;Li et al, 2016), Spanish (Migueles-Abraira et al, 2018), Vietnamese (Linh and Nguyen, 2019), Korean (Choe et al, 2020), Portuguese (Sobrevilla Cabezudo andPardo, 2019;Anchiêta and Pardo, 2018;Inácio et al, 2022), Turkish (Azin and Eryiğit, 2019;Oral et al, 2022), Persian (Takhshid et al, 2022), and Celtic languages (Heinecke and Shimorina, 2022).…”

Section: Cross-lingual Adaptations Of Amrmentioning

confidence: 99%

Spanish Abstract Meaning Representation: Annotation of a General Corpus

Wein

Donatelli²,

Ethan³

et al. 2022

NEJLT

View full text Add to dashboard Cite

Abstract Abstract Meaning Representation (AMR), originally designed for English, has been adapted to a number of languages to facilitate cross-lingual semantic representation and analysis. We build on previous work and present the first sizable, general annotation project for Spanish AMR. We release a detailed set of annotation guidelines and a corpus of 486 gold-annotated sentences spanning multiple genres from an existing, cross-lingual AMR corpus. Our work constitutes the second largest non-English gold AMR corpus to date. Fine-tuning an AMR to-Spanish generation model with our annotations results in a BERTScore improvement of 8.8%, demonstrating initial utility of our work.

show abstract

“…Cross-linguistically Abstract Meaning Representation is not an interlingua, but has since been studied in multiple languages and cross-linguistically (Xue et al, 2014;Li et al, 2016;Migueles-Abraira, 2017;Linh and Nguyen, 2019;Sobrevilla Cabezudo and Pardo, 2019;Choe et al, 2019). AMR annotations of The Little Prince have been presented in English, Chinese (Li et al, 2016), Spanish (Migueles-Abraira, 2017), and Vietnamese (Linh and Nguyen, 2019). Additional work has been done to adapt AMR annotation (Sobrevilla Cabezudo and Pardo, 2019) and alignment (Anchiêta and Pardo, 2020) to Portuguese, and Korean (Choe et al, 2019).…”

Section: Use Of Amr In Many Languages Andmentioning

confidence: 99%

Classifying Divergences in Cross-lingual AMR Pairs

Wein¹,

Schneider²

2021

Proceedings of the Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop

View full text Add to dashboard Cite

Translation divergences are varied and widespread, challenging approaches that rely on parallel text. To annotate translation divergences, we propose a schema grounded in the Abstract Meaning Representation (AMR), a sentence-level semantic framework instantiated for a number of languages. By comparing parallel AMR graphs, we can identify specific points of divergence. Each divergence is labeled with both a type and a cause. We release a small corpus of annotated English-Spanish data, and analyze the annotations in our corpus.

show abstract

A Case Study on Meaning Representation for Vietnamese

Cited by 9 publications

References 19 publications

Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation

Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation

Spanish Abstract Meaning Representation: Annotation of a General Corpus

Classifying Divergences in Cross-lingual AMR Pairs

Contact Info

Product

Resources

About