paper-with-me

Papers

Training a Swedish Constituency Parser on Six Incompatible Treebanks

2020-05-01 · LREC 2020 5 · Richard Johansson, Yvonne Adesam

We investigate a transition-based parser that uses Eukalyptus, a function-tagged constituent treebank for Swedish which includes discontinuous constituents. In addition, we show that the accuracy of this parser can be improved by using a multitask learning architecture that makes it possible to train the parser on additional treebanks that use other annotation models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cross-Domain Generalization of Neural Constituency Parsers

2019-07-09 · ACL 2019 7 · Daniel Fried, Nikita Kitaev, Dan Klein

Neural parsers obtain state-of-the-art results on benchmark treebanks for constituency parsing -- but to what degree do they generalize to other domains? We present three results about the generalization of neural parser…

Constituency ParsingDomain Generalization

Training Parsers on Incompatible Treebanks

2013-06-01 · NAACL 2013 6 · Richard Johansson

Span-based discontinuous constituency parsing: a family of exact chart-based algorithms with time complexities from O(n\^6) down to O(n\^3)

2020-11-01 · EMNLP 2020 11 · Caio Corro

We introduce a novel chart-based algorithm for span-based parsing of discontinuous constituency trees of block degree two, including ill-nested structures. In particular, we show that we can build variants of our parser …

Constituency ParsingWord Embeddings

Span-based discontinuous constituency parsing: a family of exact chart-based algorithms with time complexities from O(n^6) down to O(n^3)

2020-03-30 · Caio Corro

We introduce a novel chart-based algorithm for span-based parsing of discontinuous constituency trees of block degree two, including ill-nested structures. In particular, we show that we can build variants of our parser …

Constituency ParsingWord Embeddings

Projecting Multiword Expression Resources on a Polish Treebank

2017-04-01 · WS 2017 4 · Agata Savary, Jakub Waszczuk

Multiword expressions (MWEs) are linguistic objects containing two or more words and showing idiosyncratic behavior at different levels. Treebanks with annotated MWEs enable studies of such properties, as well as trainin…