The ATILF-LLF System for Parseme Shared Task: a Transition-based
            Verbal Multiword Expression Tagger

Saied, Hazem Al; Constant, Matthieu; Candito, Marie

doi:10.18653/v1/w17-1717

Cited by 9 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Departing from prior work, we distinguish these operations using computational methods and a naturalistic stimulus. Multiword expressions identified in The Little Prince using the methods of Al Saied et al (2017) and Constant and Sigogne (2011) serve as a hypothesis about points in the narrative where extra memory retrievals would occur.…”

Section: Discussionmentioning

confidence: 99%

“…Crucially, this way of identifying MWEs is blind to hierarchical syntactic structure. The second approach uses a transition based system (Al Saied, Candito, & Constant, 2017). This system is a variant of the well-known Nivre parser (Constant & Nivre, 2016), in which abstract "actions" update an abstract computational state that moves through the text, emitting MWE marks as a side-effect.…”

Section: Stimulus and Mwe Identificationmentioning

confidence: 99%

“…The SVM decision rule is more complicated. For details, see Al Saied et al (2017). , (B) gives the bottom-up parser action count with respect to this tree, represented in orange and annotated at the offset of each word in the story, (C) is the categorical multiword expression predictor, represented in blue, where 0 or 1 is tagged at the offset of a word if it is the final word of a MWE, (D) is the gradient multiword expression predictor, represented in dark blue, and similar to the previous predictor the offset of the final word in a MWE is tagged with the corresponding PMI score, quantifying its lexical cohesion.…”

Section: Remove Add Markmentioning

confidence: 99%

See 2 more Smart Citations

Localising memory retrieval and syntactic composition: an fMRI study of naturalistic language comprehension

Bhattasali

Fabre

Luh

et al. 2018

Language, Cognition and Neuroscience

Self Cite

View full text Add to dashboard Cite

This study examines memory retrieval and syntactic composition using fMRI while participants listen to a book, The Little Prince. These two processes are quantified drawing on methods from computational linguistics. Memory retrieval is quantified via multi-word expressions that are likely to be stored as a unit, rather than built-up compositionally. Syntactic composition is quantified via bottom-up parsing that tracks tree-building work needed in composed syntactic phrases. Regression analyses localise these to spatially-distinct brain regions. Composition mainly correlates with bilateral activity in anterior temporal lobe and inferior frontal gyrus. Retrieval of stored expressions drives right-lateralised activation in the precuneus. Less cohesive expressions activate well-known nodes of the language network implicated in composition. These results help to detail the neuroanatomical bases of two widely-assumed cognitive operations in language processing.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Stimulus and Mwe Identificationmentioning

confidence: 99%

Section: Remove Add Markmentioning

confidence: 99%

See 1 more Smart Citation

Localising memory retrieval and syntactic composition: an fMRI study of naturalistic language comprehension

Bhattasali

Fabre

Luh

et al. 2018

Language, Cognition and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the PARSEME Shared Tasks, several machine learning-based methods competed on the four languages under investigation, among others. Some of them relied on parsing (Al Saied, Constant, and Candito 2017;Nerima, Foufi, and Wehrli 2017;Simkó, Kovács, and Vincze 2017;Waszczuk 2018), whereas others exploited sequence labeling using CRFs (Boroş et al 2017;Maldonado et al 2017;Moreau et al 2018) and neural networks (Klyueva, Doucet, and Straka 2017;Berk et al 2018;Boroş and Burtica 2018;Ehren, Lichte, and Samih 2018;Stodden, QasemiZadeh, and Kallmeyer 2018;Zampieri et al 2018).…”

Section: Methods For Identifying Lvcsmentioning

confidence: 99%

Detecting light verb constructions across languages

Nagy¹,

Rácz

Vincze

2019

Nat. Lang. Eng.

View full text Add to dashboard Cite

Light verb constructions (LVCs) are verb and noun combinations in which the verb has lost its meaning to some degree and the noun is used in one of its original senses, typically denoting an event or an action. They exhibit special linguistic features, especially when regarded in a multilingual context. In this paper, we focus on the automatic detection of LVCs in raw text in four different languages, namely, English, German, Spanish, and Hungarian. First, we analyze the characteristics of LVCs from a linguistic point of view based on parallel corpus data. Then, we provide a standardized (i.e., language-independent) representation of LVCs that can be used in machine learning experiments. After, we experiment on identifying LVCs in different languages: we exploit language adaptation techniques which demonstrate that data from an additional language can be successfully employed in improving the performance of supervised LVC detection for a given language. As there are several annotated corpora from several domains in the case of English and Hungarian, we also investigate the effect of simple domain adaptation techniques to reduce the gap between domains. Furthermore, we combine domain adaptation techniques with language adaptation techniques for these two languages. Our results show that both out-domain and additional language data can improve performance. We believe that our language adaptation method may have practical implications in several fields of natural language processing, especially in machine translation.

show abstract

“…Previous edition of VMWE shared task (Savary et al, 2017) features successful systems such as the transition-based (Al Saied et al, 2017) and the CRF-based systems (Maldonado et al, 2017). In the transition-based system, sequence labelling is done using a greedy transition-based parser.…”

Section: Introductionmentioning

confidence: 99%

SHOMA at Parseme Shared Task on Automatic Identification of VMWEs: Neural Multiword Expression Tagging with High Generalisation

Taslimipoor,

Rohanian

2018

Preprint

View full text Add to dashboard Cite

This paper presents a language-independent deep learning architecture adapted to the task of multiword expression (MWE) identification. We employ a neural architecture comprising of convolutional and recurrent layers with the addition of an optional CRF layer at the top. This system participated in the open track of the Parseme shared task on automatic identification of verbal MWEs due to the use of pre-trained wikipedia word embeddings. It outperformed all participating systems in both open and closed tracks with the overall macro-average MWE-based F1 score of 58.09 averaged among all languages. A particular strength of the system is its superior performance on unseen data entries.

show abstract

The ATILF-LLF System for Parseme Shared Task: a Transition-based Verbal Multiword Expression Tagger

Cited by 9 publications

References 10 publications

Localising memory retrieval and syntactic composition: an fMRI study of naturalistic language comprehension

Localising memory retrieval and syntactic composition: an fMRI study of naturalistic language comprehension

Detecting light verb constructions across languages

SHOMA at Parseme Shared Task on Automatic Identification of VMWEs: Neural Multiword Expression Tagging with High Generalisation

Contact Info

Product

Resources

About