Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations

Zhao, Xingyuan; Ozaki, Satoru; Anastasopoulos, Antonios; Neubig, Graham; Levin, Lori

doi:10.18653/v1/2020.coling-main.471

Cited by 8 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There also have been studies on extracting grammatical information from text by using dependency parsers (Chaudhary et al, 2020;Pratapa et al, 2021) and automatically glossing text (Zhao et al, 2020;Samardžić et al, 2015) as well as compiling full morphological paradigms from it (Moeller et al, 2020). By contrast, our method is independent of such annotation schemata, and it is also simpler as it does not aim at generating full grammatical or morphological descriptions of the languages examined.…”

Section: Related Workmentioning

confidence: 99%

CaMEL: Case Marker Extraction without Labels

Leonie¹,

Hofmann²,

Sabet³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

We introduce CaMEL (Case Marker Extraction without Labels), a novel and challenging task in computational morphology that is especially relevant for low-resource languages. We propose a first model for CaMEL that uses a massively multilingual corpus to extract case markers in 83 languages based only on a noun phrase chunker and an alignment system. To evaluate CaMEL, we automatically construct a silver standard from UniMorph. The case markers extracted by our model can be used to detect and visualise similarities and differences between the case systems of different languages as well as to annotate fine-grained deep cases in languages in which they are not overtly marked.

show abstract

Section: Related Workmentioning

confidence: 99%

CaMEL: Case Marker Extraction without Labels

Leonie¹,

Hofmann²,

Sabet³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…The first approaches simply memorized earlier glossing decisions and enabled the annotator to re-use these later (Baines, 2009). Later approaches have relied on structured models like CRFs (McMillan-Major, 2020), RNN encoderdecoders (Moeller and Hulden, 2018) and transformers (Zhao et al, 2020) to generate glosses for unseen tokens. NLP techniques can also be used to generate inflection tables from IGT (Moeller et al, 2020).…”

Section: Nlp For Underdocumented Languagesmentioning

confidence: 99%

“…dards is important: Zhao et al (2020) note that this can have an impact on the performance of glossing systems. McMillan-Major (2020) notes a further challenge: IGT often includes not only morphological information, but also syntactic, semantic, and pragmatic annotations, which can be much harder to learn in low-resource settings.…”

Section: Nlp For Underdocumented Languagesmentioning

confidence: 99%

“…CVC~algal-t=gat=hl), glosses for component-morphemes (e.g. PL~watch-3.II=REPORT=CN), word alignment information (Zhao et al, 2020), and free translations. IGTs remain a major annotated datatype produced in the course of linguistic fieldwork: examples are continuously digitized in large databases for hundreds of languages (Lewis and Xia, 2010), and entire corpora of IGT are periodically published in volume series such as Texts in Indigenous Languages of the Americas.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages

Forbes¹,

Samir²,

Oliver³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent progress in NLP is driven by pretrained models leveraging massive datasets and has predominantly benefited the world's political and economic superpowers. Technologically underserved languages are left behind because they lack such resources. Hundreds of underserved languages, nevertheless, have available data sources in the form of interlinear glossed text (IGT) from language documentation efforts. IGT remains underutilized in NLP work, perhaps because its annotations are only semistructured and often language-specific. With this paper, we make the case that IGT data can be leveraged successfully provided that target language expertise is available. We specifically advocate for collaboration with documentary linguists. Our paper provides a roadmap for successful projects utilizing IGT data: (1) It is essential to define which NLP tasks can be accomplished with the given IGT data and how these will benefit the speech community.(2) Great care and target language expertise is required when converting the data into structured formats commonly employed in NLP. (3) Task-specific and user-specific evaluation can help to ascertain that the tools which are created benefit the target language speech community. We illustrate each step through a case study on developing a morphological reinflection system for the Tsimchianic language Gitksan.

show abstract

“…Biblical texts are usually well-studied and thus both references to the Strong's numbers as well as morphological information are available for Hebrew and Greek texts. Automated glossing is also a widely studied field, see [18] or [19]. These approaches have never been used to create interlinear glossed Biblical texts.…”

Section: Related Workmentioning

confidence: 99%

Automated creation of parallel Bible corpora with cross-lingual semantic concordance

Dörpinghaus¹,

Düing²

2021

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Here we present a novel approach for automated creation of parallel New Testament corpora with cross-lingual semantic concordance based on Strong's numbers. As scientific editions and translations of Bible texts are often not free to use for scientific purposes and are rarely free to use, and due to the fact that the annotation, curation and quality control of alignments between these texts are quite expensive, there is a lack of available Biblical resources for scholars. We present two approaches to tackle the problem, a dictionary-based approach and a Conditional Random Field (CRF) model and a detailed evaluation on annotated and non-annotated translations. We discuss a proof-of-concept based on English and German New Testament translations. The results presented in this paper are novel and according to our knowledge unique. They present promising performance, although further research is necessary.

show abstract

Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations

Cited by 8 publications

References 25 publications

CaMEL: Case Marker Extraction without Labels

CaMEL: Case Marker Extraction without Labels

Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages

Automated creation of parallel Bible corpora with cross-lingual semantic concordance

Contact Info

Product

Resources

About