Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2401.01512 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913238300491776 |
|---|---|
| author | Velasco, Alejandro Palacio, David N. Rodriguez-Cardenas, Daniel Poshyvanyk, Denys |
| author_facet | Velasco, Alejandro Palacio, David N. Rodriguez-Cardenas, Daniel Poshyvanyk, Denys |
| contents | This paper discusses the limitations of evaluating Masked Language Models (MLMs) in code completion tasks. We highlight that relying on accuracy-based measurements may lead to an overestimation of models' capabilities by neglecting the syntax rules of programming languages. To address these issues, we introduce a technique called SyntaxEval in which Syntactic Capabilities are used to enhance the evaluation of MLMs. SyntaxEval automates the process of masking elements in the model input based on their Abstract Syntax Trees (ASTs). We conducted a case study on two popular MLMs using data from GitHub repositories. Our results showed negative causal effects between the node types and MLMs' accuracy. We conclude that MLMs under study fail to predict some syntactic capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01512 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code? Velasco, Alejandro Palacio, David N. Rodriguez-Cardenas, Daniel Poshyvanyk, Denys Software Engineering This paper discusses the limitations of evaluating Masked Language Models (MLMs) in code completion tasks. We highlight that relying on accuracy-based measurements may lead to an overestimation of models' capabilities by neglecting the syntax rules of programming languages. To address these issues, we introduce a technique called SyntaxEval in which Syntactic Capabilities are used to enhance the evaluation of MLMs. SyntaxEval automates the process of masking elements in the model input based on their Abstract Syntax Trees (ASTs). We conducted a case study on two popular MLMs using data from GitHub repositories. Our results showed negative causal effects between the node types and MLMs' accuracy. We conclude that MLMs under study fail to predict some syntactic capabilities. |
| title | Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code? |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2401.01512 |