Insights into non-projectivity in Hindi

Mannem, Prashanth; Chaudhry, Himani; Bharati, Agehananda

doi:10.3115/1667884.1667887

Cited by 8 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simply put, an arc in a dependency tree is projective if there is a directed path from the head word x to all the words between the two endpoints of the arc (Kübler et al, 2009). The non-projective cases that we found were similar to the ones discussed in Mannem et al (2009a). A quick look at Table 1 makes few things evident straight away.…”

Section: Edge Type and Non-projective Edgesupporting

confidence: 75%

“…The rst three transformations remove non-projectivity in paired connective, relative and complement clauses. These three nonprojective cases are also the most frequent non-projective structures in Hindi (Mannem et al, 2009a). Figure 1 shows the changes in the analy-sis of paired connectives 7 .…”

Section: Experiments I: Exploring Alternative Analysis Via Structural Transformationsmentioning

confidence: 95%

See 1 more Smart Citation

Analyzing Parser Errors

Husain

Agrawal²

2012

LiLT

View full text Add to dashboard Cite

We present a detailed error analysis of a transition-based dependency parser trained on a Hindi dependency treebank. Parser error analysis has not been systematically examined from the point of view of treebanking before and this work intends to contribute in this area. We address two main questions in this paper: Can the parsing of certain structures be made easier by using alternative analyses for these structures? Are there certain linguistic cues implicit (or missing) in the current treebank that can be made explicit (or added) in order to make the parsing of complex constructions easier? These questions will guide us in examining the potential benefits of parser error analysis during treebanking. Through our experiments and analysis we were able to shed light on the causes of errors and subsequently have been able to improve the performance of the parser.

show abstract

Section: Edge Type and Non-projective Edgesupporting

confidence: 75%

Section: Experiments I: Exploring Alternative Analysis Via Structural Transformationsmentioning

confidence: 95%

Analyzing Parser Errors

Husain

Agrawal²

2012

LiLT

View full text Add to dashboard Cite

show abstract

“…The same holds for the 37 coarse-grained relations: universaldependencies.org/u/dep/index.html 8 This amount is in line withMannem et al (2009).…”

supporting

confidence: 65%

“…Whilst English and many of our training languages have an SVO word order, Hindi has an SOV word order. Hindi treebanks have a larger percentage of non-projective dependency trees (Mannem et al, 2009), where dependency arcs are allowed to cross one another.…”

Section: Training and Evaluationmentioning

confidence: 99%

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

Langedijk¹,

Dankers²,

Lippe³

et al. 2021

Preprint

View full text Add to dashboard Cite

Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of cross-lingual dependency parsing. We train our model on a diverse set of languages to learn a parameter initialization that can adapt quickly to new languages. We find that meta-learning with pre-training can significantly improve upon the performance of language transfer and standard supervised learning baselines for a variety of unseen, typologically diverse, and low-resource languages, in a few-shot learning setup.

show abstract

“…While we are able to handle some in our current conversion, there are others we still need to work on. One such type which we have addressed is the 'yah-ki' यह-क (this-that) complement constructions which follow the pattern: yah ('यह)-its property-VP-ki क clause' (Mannem et al, 2009). In cases of ellipsis, a NULL node is introduced to facilitate annotation, since the entire 'ki' (that) clause is annotated as the child of 'yaha' (this) /`NULL' node here.…”

Section: Ellipsismentioning

confidence: 99%

Conversion from Paninian Karakas to Universal Dependencies for Hindi Dependency Treebank

Tandon¹,

Chaudhry²,

Bhat³

et al. 2016

Proceedings of the 10th Linguistic Annotation Workshop Held In Conjunction With ACL 2016 (LAW-X 2016)

Self Cite

View full text Add to dashboard Cite

Universal Dependencies (UD) are gaining much attention of late for systematic evaluation of cross-lingual techniques for crosslingual dependency parsing. In this paper we present our work in line with UD. Our contribution to this is manifold. We extend UD to Indian languages through conversion of Pān ̣inian Dependencies to UD for the Hindi Dependency Treebank (HDTB). We discuss the differences in annotation in both the schemes, present parsing experiments for both the formalisms and empirically evaluate their weaknesses and strengths for Hindi. We produce an automatically converted Hindi Treebank conforming to the international standard UD scheme, making it useful as a resource for multilingual language technology.

show abstract

Insights into non-projectivity in Hindi

Cited by 8 publications

References 5 publications

Analyzing Parser Errors

Analyzing Parser Errors

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

Conversion from Paninian Karakas to Universal Dependencies for Hindi Dependency Treebank

Contact Info

Product

Resources

About