Discontinuous Constituent Parsing as Sequence Labeling
This paper reduces discontinuous parsing to sequence labeling. It first shows that existing reductions for constituent parsing as labeling do not support discontinuities. Second, it fills this gap and proposes to encode tree discontinuities as nearly ordered permutations of the input sequence. Third, it studies whether such discontinuous representations are learnable. The experiments show that despite the architectural simplicity, under the right representation, the models are fast and accurate.
Code (1)
Similar Papers 제목 키워드 기반
Discontinuous Grammar as a Foreign Language
In order to achieve deep natural language understanding, syntactic constituent parsing is a vital step, highly demanded by many artificial intelligence systems to process both text and speech. One of the most recent prop…
Machine TranslationNatural Language UnderstandingTranslationDiscontinuous Constituent Parsing with Pointer Networks
One of the most complex syntactic representations used in computational linguistics and NLP are discontinuous constituent trees, crucial for representing all grammatical phenomena of languages such as German. Recent adva…
Dependency ParsingPart-Of-Speech TaggingSentenceIntegrating Supertag Features into Neural Discontinuous Constituent Parsing
Syntactic parsing is essential in natural-language processing, with constituent structure being one widely used description of syntax. Traditional views of constituency demand that constituents consist of adjacent words,…
ChunkingDependency ParsingSentenceExploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing
To achieve deep natural language understanding, syntactic constituent parsing plays a crucial role and is widely required by many artificial intelligence systems for processing both text and speech. A recent approach inv…
Natural Language UnderstandingConstituency ParsingMachine TranslationIncremental Discontinuous Phrase Structure Parsing with the GAP Transition
This article introduces a novel transition system for discontinuous lexicalized constituent parsing called SR-GAP. It is an extension of the shift-reduce algorithm with an additional gap transition. Evaluation on two Ger…