Open Challenges in NLP for NFRs: A Focus on Semantics, Generalization, and Interpretability. Krasniqi, R. In Proceedings of the 8th Workshop on Natural Language Processing for Requirements Engineering (NLP4RE), co-located with REFSQ, volume 3959, pages 1–11, Barcelona, Spain, 2025. ACM. ![Open Challenges in NLP for NFRs: A Focus on Semantics, Generalization, and Interpretability [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex 1 download Leveraging natural language processing (NLP) models within the non-functional requirements (NFR) domain has proven highly effective in addressing various issues, including automated traceability, classification of NFR compliance documents, NFR prioritization, among others. Despite these significant advancements, there remain open challenges associated with the full integration of NLP models in the NFR domain. For example, using NLP models to capture the semantics of complex phrases present in safety-critical NFRs must ensure that they do not lead to misinterpretations and potential safety risks. Therefore, this paper focuses on three key challenges related to semantic soundness, ontology generalizability, and the interpretability of model outcomes. These challenges have been chosen for several reasons. First, the absence of semantic precision can result in the misinterpretation of NFRs. Second, given that NFRs cover diverse domains, NLP models must generalize across these domains. Lastly, many problems within the NFR domain rely on decision-making based on predictions from NLP models. However, frequently adapted traditional NLP models such as ensemble models or kernel models are often regarded as ‘black-boxes,’ with output predictions that are challenging to interpret. Guided by these insights, we present a roadmap agenda through 10 implicit system-based scenarios drawn from the NFR perspective. These scenarios illustrate gaps where these NLP challenges become evident within the NFR domain. Additionally, we suggest solutions, strategies, and alternative approaches to better address these NLP challenges.
@inproceedings{krasniqi_open_2025,
address = {Barcelona, Spain},
title = {Open {Challenges} in {NLP} for {NFRs}: {A} {Focus} on {Semantics}, {Generalization}, and {Interpretability}},
volume = {3959},
url = {https://ceur-ws.org/Vol-3959/NLP4RE-paper1.pdf},
abstract = {Leveraging natural language processing (NLP) models within the non-functional requirements (NFR) domain
has proven highly effective in addressing various issues, including automated traceability, classification of NFR compliance documents, NFR prioritization, among others. Despite these significant advancements, there remain open challenges associated with the full integration of NLP models in the NFR domain. For example, using NLP models to capture the semantics of complex phrases present in safety-critical NFRs must ensure that they do not
lead to misinterpretations and potential safety risks. Therefore, this paper focuses on three key challenges related to semantic soundness, ontology generalizability, and the interpretability of model outcomes. These challenges have been chosen for several reasons. First, the absence of semantic precision can result in the misinterpretation
of NFRs. Second, given that NFRs cover diverse domains, NLP models must generalize across these domains. Lastly, many problems within the NFR domain rely on decision-making based on predictions from NLP models. However, frequently adapted traditional NLP models such as ensemble models or kernel models are often regarded as ‘black-boxes,’ with output predictions that are challenging to interpret. Guided by these insights, we present a
roadmap agenda through 10 implicit system-based scenarios drawn from the NFR perspective. These scenarios illustrate gaps where these NLP challenges become evident within the NFR domain. Additionally, we suggest solutions, strategies, and alternative approaches to better address these NLP challenges.},
language = {en},
booktitle = {Proceedings of the 8th {Workshop} on {Natural} {Language} {Processing} for {Requirements} {Engineering}
({NLP4RE}), co-located with {REFSQ}},
publisher = {ACM},
author = {Krasniqi, Rrezarta},
year = {2025},
keywords = {Conference Workshop Papers},
pages = {1--11},
}
Downloads: 1
{"_id":"73CkddAjMNnrx5pJs","bibbaseid":"krasniqi-openchallengesinnlpfornfrsafocusonsemanticsgeneralizationandinterpretability-2025","author_short":["Krasniqi, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Barcelona, Spain","title":"Open Challenges in NLP for NFRs: A Focus on Semantics, Generalization, and Interpretability","volume":"3959","url":"https://ceur-ws.org/Vol-3959/NLP4RE-paper1.pdf","abstract":"Leveraging natural language processing (NLP) models within the non-functional requirements (NFR) domain has proven highly effective in addressing various issues, including automated traceability, classification of NFR compliance documents, NFR prioritization, among others. Despite these significant advancements, there remain open challenges associated with the full integration of NLP models in the NFR domain. For example, using NLP models to capture the semantics of complex phrases present in safety-critical NFRs must ensure that they do not lead to misinterpretations and potential safety risks. Therefore, this paper focuses on three key challenges related to semantic soundness, ontology generalizability, and the interpretability of model outcomes. These challenges have been chosen for several reasons. First, the absence of semantic precision can result in the misinterpretation of NFRs. Second, given that NFRs cover diverse domains, NLP models must generalize across these domains. Lastly, many problems within the NFR domain rely on decision-making based on predictions from NLP models. However, frequently adapted traditional NLP models such as ensemble models or kernel models are often regarded as ‘black-boxes,’ with output predictions that are challenging to interpret. Guided by these insights, we present a roadmap agenda through 10 implicit system-based scenarios drawn from the NFR perspective. These scenarios illustrate gaps where these NLP challenges become evident within the NFR domain. Additionally, we suggest solutions, strategies, and alternative approaches to better address these NLP challenges.","language":"en","booktitle":"Proceedings of the 8th Workshop on Natural Language Processing for Requirements Engineering (NLP4RE), co-located with REFSQ","publisher":"ACM","author":[{"propositions":[],"lastnames":["Krasniqi"],"firstnames":["Rrezarta"],"suffixes":[]}],"year":"2025","keywords":"Conference Workshop Papers","pages":"1–11","bibtex":"@inproceedings{krasniqi_open_2025,\n\taddress = {Barcelona, Spain},\n\ttitle = {Open {Challenges} in {NLP} for {NFRs}: {A} {Focus} on {Semantics}, {Generalization}, and {Interpretability}},\n\tvolume = {3959},\n\turl = {https://ceur-ws.org/Vol-3959/NLP4RE-paper1.pdf},\n\tabstract = {Leveraging natural language processing (NLP) models within the non-functional requirements (NFR) domain\nhas proven highly effective in addressing various issues, including automated traceability, classification of NFR compliance documents, NFR prioritization, among others. Despite these significant advancements, there remain open challenges associated with the full integration of NLP models in the NFR domain. For example, using NLP models to capture the semantics of complex phrases present in safety-critical NFRs must ensure that they do not\nlead to misinterpretations and potential safety risks. Therefore, this paper focuses on three key challenges related to semantic soundness, ontology generalizability, and the interpretability of model outcomes. These challenges have been chosen for several reasons. First, the absence of semantic precision can result in the misinterpretation\nof NFRs. Second, given that NFRs cover diverse domains, NLP models must generalize across these domains. Lastly, many problems within the NFR domain rely on decision-making based on predictions from NLP models. However, frequently adapted traditional NLP models such as ensemble models or kernel models are often regarded as ‘black-boxes,’ with output predictions that are challenging to interpret. Guided by these insights, we present a\nroadmap agenda through 10 implicit system-based scenarios drawn from the NFR perspective. These scenarios illustrate gaps where these NLP challenges become evident within the NFR domain. Additionally, we suggest solutions, strategies, and alternative approaches to better address these NLP challenges.},\n\tlanguage = {en},\n\tbooktitle = {Proceedings of the 8th {Workshop} on {Natural} {Language} {Processing} for {Requirements} {Engineering}\n({NLP4RE}), co-located with {REFSQ}},\n\tpublisher = {ACM},\n\tauthor = {Krasniqi, Rrezarta},\n\tyear = {2025},\n\tkeywords = {Conference Workshop Papers},\n\tpages = {1--11},\n}\n\n","author_short":["Krasniqi, R."],"key":"krasniqi_open_2025","id":"krasniqi_open_2025","bibbaseid":"krasniqi-openchallengesinnlpfornfrsafocusonsemanticsgeneralizationandinterpretability-2025","role":"author","urls":{"Paper":"https://ceur-ws.org/Vol-3959/NLP4RE-paper1.pdf"},"keyword":["Conference Workshop Papers"],"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/10198036/collections/2RHJXKSI/items?key=X0RoN8iO9RtTbrWfSkRasb7b&format=bibtex&limit=100","dataSources":["37aX9ioouEvzbunGp","JHDShjsHrs6ZHE4bz"],"keywords":["conference workshop papers"],"search_terms":["open","challenges","nlp","nfrs","focus","semantics","generalization","interpretability","krasniqi"],"title":"Open Challenges in NLP for NFRs: A Focus on Semantics, Generalization, and Interpretability","year":2025,"downloads":1}