Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing
Different linearizations have been proposed to cast dependency parsing as sequence labeling and solve the task as: (i) a head selection problem, (ii) finding a representation of the token arcs as bracket strings, or (iii) associating partial transition sequences of a transition-based parser to words. Yet, there is little understanding about how these linearizations behave in low-resource setups. Here, we first study their data efficiency, simulating data-restricted setups from a diverse set of rich-resource treebanks. Second, we test whether such differences manifest in truly low-resource setups. The results show that head selection encodings are more data-efficient and perform better in an ideal (gold) framework, but that such advantage greatly vanishes in favour of bracketing formats when the running setup resembles a real-world low-resource configuration.
Code (0)
등록된 구현이 없습니다.
Tasks
AllDependency ParsingSimilar Papers 제목 키워드 기반
Dependency Graph Parsing as Sequence Labeling
Various linearizations have been proposed to cast syntactic dependency parsing as sequence labeling. However, these approaches do not support more complex graph-based representations, such as semantic dependencies or enh…
Dependency ParsingNested Named Entity Recognition as Single-Pass Sequence Labeling
We cast nested named entity recognition (NNER) as a sequence labeling task by leveraging prior work that linearizes constituency structures, effectively reducing the complexity of this structured prediction problem to st…
named-entity-recognitionNamed Entity RecognitionNested Named Entity RecognitionStructured Prediction+2Parsing linearizations appreciate PoS tags - but some are fussy about errors
PoS tags, once taken for granted as a useful resource for syntactic parsing, have become more situational with the popularization of deep learning. Recent work on the impact of PoS tags on graph- and transition-based par…
POSBracketing Encodings for 2-Planar Dependency Parsing
We present a bracketing-based encoding that can be used to represent any 2-planar dependency tree over a sentence of length n as a sequence of n labels, hence providing almost total coverage of crossing arcs in sequence …
Dependency ParsingPOSSentenceNeural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection
Recurrent neural network architectures combining with attention mechanism, or neural attention model, have shown promising performance recently for the tasks including speech recognition, image caption generation, visual…
Caption GenerationClassificationGeneral ClassificationMachine Translation+7