Identifying Terms in Open Source Software License Texts

Kapitsaki, Georgia M.; Paschalides, Demetris

doi:10.1109/apsec.2017.62

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relation extraction in license understanding aims to extract structured knowledge about relations between entities from unstructured license text. Unlike previous studies [28,45] which regarded a right/obligation as a whole entity, in this paper, we decompose each regulation into four types of entities, and propose a relation extraction model to reconstruct the relations between these entities for a fine-grained and structured understanding of licenses. Since there exists no tagged dataset for entity relations in licenses and labelling is time-consuming, inspired by the promising results of prompt-tuning for few-shot tasks, we employ a prompt-based relation extraction model based on KnowPrompt [7].…”

Section: Relation Extractionmentioning

confidence: 99%

“…Specifically, for each attidue entity (e.g., "are not allowed"), we follow previous works [29,45] to assign it a label (i.e., CAN, CANNOT, or MUST) for further analysis. We also classify the entities of actions into 23 categories as previous studies [25,28,45]. Each group represents a type of actions that licensees may do.…”

Section: Incompatibility Issue Localizationmentioning

confidence: 99%

“…To evaluate the performance of LiResolver for entity extraction, we compare it with two state-of-the-art tools (i.e., FOSS-LTE [28] and LiDetector [45]) and two natural language processing techniques (i.e., regular matching [4] and semantic similarity [17]). Specifically, FOSS-LTE [28] employed a topic model named Latent Dirichlet Allocation (LDA) [24] to identify license terms. LiDetector [45] utilized sequence labelling and sentiment analysis to identify license term entities (similar to the actions in this paper) and attitudes.…”

Section: Entity Extractionmentioning

confidence: 99%

“…Figure 5 shows the performance of two approaches on relation extraction. Since FOSS-LTE [28] and LiDetector [45] do not extract relations between entities, we did not compare LiResolver with them. Instead, we implemented a heuristic approach based on the positions and types of entities (denoted by PTE).…”

Section: Entity Extractionmentioning

confidence: 99%

“…For example, Alspaugh et al [2] [3] extracted tuples from licenses to model 10 licenses. Unlike the ontology-based approaches that required much prior knowledge, Kapitsaki et al [28] proposed FOSS-LTE to identify license terms with a topic model. Despite the progress, the topic model might induce much noise and cause low accuracy [45].…”

Section: Related Work 51 License Detection and Semantic Extractionmentioning

confidence: 99%

See 4 more Smart Citations

LiResolver: License Incompatibility Resolution for Open Source Software

Gao

Fan

et al. 2023

Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis

View full text Add to dashboard Cite

Open source software (OSS) licenses regulate the conditions under which OSS can be legally reused, distributed, and modified. However, a common issue arises when incorporating third-party OSS accompanied with licenses, i.e., license incompatibility, which occurs when multiple licenses exist in one project and there are conflicts between them. Despite being problematic, fixing license incompatibility issues requires substantial efforts due to the lack of license understanding and complex package dependency. In this paper, we propose LiResolver, a fine-grained, scalable, and flexible tool to resolve license incompatibility issues for open source software. Specifically, it first understands the semantics of licenses through fine-grained entity extraction and relation extraction. Then, it detects and resolves license incompatibility issues by recommending official licenses in priority. When no official licenses can satisfy the constraints, it generates a custom license as an alternative solution.Comprehensive experiments demonstrate the effectiveness of LiResolver, with 4.09% false positive (FP) rate and 0.02% false negative (FN) rate for incompatibility issue localization, and 62.61% of 230 real-world incompatible projects resolved by LiResolver. We discuss the feedback from OSS developers and the lessons learned from this work. All the datasets and the replication package of LiResolver have been made publicly available to facilitate follow-up research.

show abstract

Section: Relation Extractionmentioning

confidence: 99%

Section: Incompatibility Issue Localizationmentioning

confidence: 99%

Section: Entity Extractionmentioning

confidence: 99%

Section: Entity Extractionmentioning

confidence: 99%

Section: Related Work 51 License Detection and Semantic Extractionmentioning

confidence: 99%

See 3 more Smart Citations

LiResolver: License Incompatibility Resolution for Open Source Software

Gao

Fan

et al. 2023

Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis

View full text Add to dashboard Cite

show abstract

Legal Natural Language Processing From 2015 to 2022: A Comprehensive Systematic Mapping Study of Advances and Applications

Quevedo,

Cerny,

Rodriguez

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The surge in legal text production has amplified the workload for legal professionals, making many tasks repetitive and time-consuming. Furthermore, the complexity and specialized language of legal documents pose challenges not just for those in the legal domain but also for the general public. This emphasizes the potential role and impact of Legal Natural Language Processing (Legal NLP). Although advancements have been made in this domain, particularly after 2015 with the advent of Deep Learning and Large Language Models (LLMs), a systematic exploration of this progress until 2022 is nonexistent. In this research, we perform a Systematic Mapping Study (SMS) to bridge this gap. We aim to provide a descriptive statistical analysis of the Legal NLP research between 2015 and 2022. Categorize and sub-categorize primary publications based on their research problems. Identify limitations and areas of improvement in current research. Using a robust search methodology across four reputable indexers, we filtered 536 papers down to 75 pivotal articles. Our findings reveal the diverse methods employed for tasks such as Multiclass Classification, Summarization, and Question Answering in the Legal NLP field. We also highlight resources, challenges, and gaps in current methodologies and emphasize the need for curated datasets, ontologies, and a focus on inherent difficulties like data accessibility. As the legal sector gradually embraces Natural Language Processing (NLP), understanding the capabilities and limitations of Legal NLP becomes vital for ensuring efficient and ethical application. The research offers insights for both Legal NLP researchers and the broader legal community, advocating for continued advancements in automation while also addressing ethical concerns.

show abstract