A Neural Graph-based Approach to Verbal MWE Identification

Waszczuk, Jakub; Ehren, Rafael; Stodden, Regina; Kallmeyer, Laura

doi:10.18653/v1/w19-5113

Cited by 5 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the distinction between these categories is not always clear, and few precise tests exist for the annotators to tell them apart (Gross, 1982). 1 Most state-of-the-art MWE identification models are based on neural architectures (Ramisch et al, 2018;Taslimipoor and Rohanian, 2018) with some employing graph-based methods to make use of structured information such as dependency parse trees (Waszczuk et al, 2019;Rohanian et al, 2019). Top-performing metaphor detection models also use neural methods (Rei et al, 2017;Gao et al, 2018), with some utilising additional data such as sentiment and linguistic information to further improve performance (Mao et al, 2019;Dankers et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Verbal Multiword Expressions for Identification of Metaphor

Rohanian¹,

Rei²,

Taslimipoor³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Metaphor is a linguistic device in which a concept is expressed by mentioning another. Identifying metaphorical expressions, therefore, requires a non-compositional understanding of semantics. Multiword Expressions (MWEs), on the other hand, are linguistic phenomena with varying degrees of semantic opacity and their identification poses a challenge to computational models. This work is the first attempt at analysing the interplay of metaphor and MWEs processing through the design of a neural architecture whereby classification of metaphors is enhanced by informing the model of the presence of MWEs. To the best of our knowledge, this is the first "MWE-aware" metaphor identification system paving the way for further experiments on the complex interactions of these phenomena. The results and analyses show that this proposed architecture reach state-of-the-art on two different established metaphor datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Verbal Multiword Expressions for Identification of Metaphor

Rohanian¹,

Rei²,

Taslimipoor³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…This parse-then-extract strategy is widely adopted (Vincze et al, 2013;Nasr et al, 2015;Simkó et al, 2017). Waszczuk et al (2019) introduce additional parameterized scoring functions for the arc labelers and use global decoding to produce consistent structures during arc-labeling steps once unlabeled dependency parse trees are predicted. Our work additionally proposes a joint decoder that combines the scores from both parsers and taggers.…”

Section: Related Workmentioning

confidence: 99%

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches

Shi

Lee

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

An interesting and frequent type of multiword expression (MWE) is the headless MWE, for which there are no true internal syntactic dominance relations; examples include many named entities ("Wells Fargo") and dates ("July 5, 2020") as well as certain productive constructions ("blow for blow", "day after day"). Despite their special status and prevalence, current dependency-annotation schemes require treating such flat structures as if they had internal syntactic heads, and most current parsers handle them in the same fashion as headed constructions. Meanwhile, outside the context of parsing, taggers are typically used for identifying MWEs, but taggers might benefit from structural information. We empirically compare these two common strategies-parsing and tagging-for predicting flat MWEs. Additionally, we propose an efficient joint decoding algorithm that combines scores from both strategies. Experimental results on the MWE-Aware English Dependency Corpus and on six non-English dependency treebanks with frequent flat structures show that: (1) tagging is more accurate than parsing for identifying flat-structure MWEs, (2) our joint decoder reconciles the two different views and, for non-BERT features, leads to higher accuracies, and (3) most of the gains result from feature sharing between the parsers and taggers.

show abstract

“…In this dataset, multi-word expressions are classified into three categories: general, quasi-general and other; these categories are not based on communicative functions. Therefore, state-of-the-art models for identification of multi-word expressions trained on the dataset (Waszczuk et al, 2019;Saied et al, 2019) cannot be directly applied to the extraction of formulaic expressions.…”

Section: Multi-word Expressions and Formulaic Expressionsmentioning

confidence: 99%

Extraction and Evaluation of Formulaic Expressions Used in Scholarly Papers

Iwatsuki¹,

Boudin²,

Aizawa³

2020

Preprint

View full text Add to dashboard Cite

Formulaic expressions, such as 'in this paper we propose', are helpful for authors of scholarly papers because they convey communicative functions; in the above, it is 'showing the aim of this paper '. Thus, resources of formulaic expressions, such as a dictionary, that could be looked up easily would be useful. However, forms of formulaic expressions can often vary to a great extent. For example, 'in this paper we propose', 'in this study we propose' and 'in this paper we propose a new method to' are all regarded as formulaic expressions. Such a diversity of spans and forms causes problems in both extraction and evaluation of formulaic expressions. In this paper, we propose a new approach that is robust to variation of spans and forms of formulaic expressions. Our approach regards a sentence as consisting of a formulaic part and non-formulaic part. Then, instead of trying to extract formulaic expressions from a whole corpus, by extracting them from each sentence, different forms can be dealt with at once. Based on this formulation, to avoid the diversity problem, we propose evaluating extraction methods by how much they convey specific communicative functions rather than by comparing extracted expressions to an existing lexicon. We also propose a new extraction method that utilises named entities and dependency structures to remove the non-formulaic part from a sentence. Experimental results show that the proposed extraction method achieved the best performance compared to other existing methods.

show abstract

A Neural Graph-based Approach to Verbal MWE Identification

Cited by 5 publications

References 12 publications

Verbal Multiword Expressions for Identification of Metaphor

Verbal Multiword Expressions for Identification of Metaphor

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches

Extraction and Evaluation of Formulaic Expressions Used in Scholarly Papers

Contact Info

Product

Resources

About