Deep Lexical Segmentation and Syntactic Parsing in the Easy-First Dependency Framework

Constant, Matthieu; Roux, Joseph Le; Tomeh, Nadi

doi:10.18653/v1/n16-1127

Cited by 6 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies on statistical MWE-aware parsing tend to work on very simple representations of MWEs. The benefit of adopting more complex, deeper representations capable of representing, for example, embedded MWEs (Finkel and Manning 2009;Constant, Le Roux, and Tomeh 2016;Constant and Nivre 2016), is as yet unclear. There is a case to be made for such approaches to be investigated more deeply on data sets with comprehensive MWE annotations in many different languages.…”

Section: Open Issues In Mwe-aware Parsingmentioning

confidence: 99%

Multiword Expression Processing: A Survey

Constant

Eryiğit

Monti

et al. 2017

Computational Linguistics

162

126

View full text Add to dashboard Cite

Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs. The issue of MWE handling is crucial for NLP applications, where it raises a number of challenges. The emergence of solutions in the absence of guiding principles motivates this survey, whose aim is not only to provide a focused review of MWE processing, but also to clarify the nature of interactions between MWE processing and downstream applications. We propose a conceptual framework within which challenges and research contributions can be positioned. It offers a shared understanding of what is meant by “MWE processing,” distinguishing the subtasks of MWE discovery and identification. It also elucidates the interactions between MWE processing and two use cases: Parsing and machine translation. Many of the approaches in the literature can be differentiated according to how MWE processing is timed with respect to underlying use cases. We discuss how such orchestration choices affect the scope of MWE-aware systems. For each of the two MWE processing subtasks and for each of the two use cases, we conclude on open issues and research perspectives.

show abstract

Section: Open Issues In Mwe-aware Parsingmentioning

confidence: 99%

Multiword Expression Processing: A Survey

Constant

Eryiğit

Monti

et al. 2017

Computational Linguistics

162

126

View full text Add to dashboard Cite

show abstract

“…Practically, we used the LTH converter (Johansson and Nugues, 2007) to obtain the dependency version of the EWT constituent version. We also used the predicted linguistic attributes used in Constant and Le Roux (2015) and in Constant et al (2016). Both datasets include predicted POS tags, lemmas and morphology, as well as features computed from compound dictionary lookup.…”

Section: Methodsmentioning

confidence: 99%

“…Constant et al (2016) also proposed a two-dimensional representation in the form of dependency trees anchored by the same words. The annotation of fixed MWEs is redundant on both dimensions, while they are shared in our representation.…”

Section: Related Workmentioning

confidence: 99%

“…Our system includes a special treatment of MWEs using specific transitions in a classical transition-based system, in line with the proposal of Nivre (2014). Constant et al (2016) also proposed a two-dimensional representation in the form of dependency trees anchored by the same words. The annotation of fixed MWEs is redundant on both dimensions, while they are shared in our representation.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Transition-Based System for Joint Lexical and Syntactic Analysis

Constant¹,

Nivre²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Self Cite

View full text Add to dashboard Cite

We present a transition-based system that jointly predicts the syntactic structure and lexical units of a sentence by building two structures over the input words: a syntactic dependency tree and a forest of lexical units including multiword expressions (MWEs). This combined representation allows us to capture both the syntactic and semantic structure of MWEs, which in turn enables deeper downstream semantic analysis, especially for semicompositional MWEs. The proposed system extends the arc-standard transition system for dependency parsing with transitions for building complex lexical units. Experiments on two different data sets show that the approach significantly improves MWE identification accuracy (and sometimes syntactic accuracy) compared to existing joint approaches.

show abstract

“…We briefly describe the single task Easy-First (EF) parsing algorithm Kiperwasser and Goldberg (2016) and its components, then we discuss the multitask extension (MEF) inspired by (Constant et al, 2016) adapted to the tree-structured LSTM in terms of the updated parsing algorithm and its components.…”

Section: Modelmentioning

confidence: 99%

Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations

Kankanampati¹,

Roux²,

Tomeh³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

Self Cite

View full text Add to dashboard Cite

We present a parsing model for projective dependency trees which takes advantage of the existence of complementary dependency annotations for a language. This is the case for Arabic with the availability of CATiB and UD treebanks. Our system performs syntactic parsing according to both annotation types jointly as a sequence of arc-creating operations following the Easy-First approach, and partially created trees for one annotation type are also available to the other as features for the score function. This method gives error reduction of 9.9% on CATiB and 6.1% on UD compared to a single-task baseline, and ablation tests show that the main contribution of this reduction is given by sharing tree representation between tasks, and not simply sharing BiLSTM layers as is usually performed in NLP multitask systems.

show abstract

Deep Lexical Segmentation and Syntactic Parsing in the Easy-First Dependency Framework

Cited by 6 publications

References 10 publications

Multiword Expression Processing: A Survey

Multiword Expression Processing: A Survey

A Transition-Based System for Joint Lexical and Syntactic Analysis

Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations

Contact Info

Product

Resources

About