RehabRobo-Query: Answering Natural Language Queries about Rehabilitation Robotics Ontology on the Cloud

Tracking #: 1786-2999

Zeynep Dogmus
Esra Erdem
Volkan Patoglu

Responsible editor: 
Guest Editors ENLI4SW 2016

Submission type: 
Full Paper
We introduce a novel method to answer natural language queries about rehabilitation robotics, over the formal ontology RehabRobo-Onto. For that, (i) we design and develop a novel controlled natural language for rehabilitation robotics, called RehabRobo-CNL; (ii) we introduce translations of queries in RehabRobo-CNL into Sparql queries, utilizing a novel concept of query description trees; (iii) we use an automated reasoner to find answers to Sparql queries. To facilitate the use of our method by experts, we develop an intelligent, interactive query answering system, called RehabRobo-Query, using Semantic Web technologies, and make it available on the cloud via Amazon web services. RehabRobo-Query guides the users to express their queries in natural language and displays the answers to queries in a readable format, possibly with links to detailed information. Easy access to information on RehabRobo-Onto through complex queries in natural language may help engineers inspire new rehabilitation robot designs, while also guiding practitioners to make more informed decisions on technology based rehabilitation.
Full PDF Version: 

Minor Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Nick Bassiliades submitted on 18/Dec/2017
Review Comment:

Almost all my concerns have been tackled by the authors.

I just have a couple of remarks that I think the authors should correct.

Concerning my comment on justifying why the ontology was built from scratch instead of (partially) reusing well-known ontologies, such as BIBO/FABIO and FOAF, the provided justification is still weak.

Concerning my comment on two-step vs. one-step translation of the query tree to SPARQL, the authors have removed the two-step process and have described better the one-step process. However, at the beginning of section 5 they still mention two-steps after the transformation of CNL to the query tree, instead of one-step they actually present. They should correct this. Furthermore, they mention in various places of section 5 the term "SPARQL concept". What is that? It is not defined. Maybe you just mean "SPARQL construct"? Please correct or define.

Review #2
By Antonis Bikakis submitted on 06/Jan/2018
Minor Revision
Review Comment:

In the revised submission the authors have addressed my and the other reviewers’ comments. The paper now includes many more examples better motivating the proposed approach. It also gives many more details about the underlying ontology, the performance evaluation and the user-based experiments.

Some remaining minor points that need to addressed (mostly typos and expression errors) are:

Section 1

- Par.3, line 1: “advancements at” -> “advancements in”
- Par.4, ASSISTON-SE: briefly explain what it is
- Par.6: “by European Network” -> “by the European Network”
- Par.8: “robotics as the oncology” -> “robotics such as the ontology”
- Par.10: Add Section 2 in the paper outline

Section 2

- Par.1: “efforts of European” -> “efforts of the European”
- Par.4, “a rehabilitation robot has Assessment with respect to some evaluation metrics”: explain briefly how these metrics are represented

Section 3

- Par.1: “we have identified”, “we have designed” -> “we identified”, “we designed”

Section 3.1

- Par.5: “on similar mechanism design” -> “on a similar mechanism design”
- Par.5: “as ability” -> “as the ability”
- Q9-Q13: “are evaluated by” -> “are used to evaluate”

Section 3.2

- Par.1: “we have identified”, “we have designed” -> “we identified”, “we designed”

Section 4

- Par.4: “user is able” -> “the user is able”, “user can choose” -> “the user can choose”
- Par.6: “is displayed to user” -> “are displayed to the user”

Section 5.1

- Par.6: “associated by” -> “associated with” (3 occurrences)

Section 5.2

- Par.8: “and then the description” -> “and then with the description”

Section 6

- “SPARQL representation” -> “The SPARQL representation”

Section 7.2

- all verbs in past perfect (e.g. “has been given”) must be replaced with their simple past forms (“was given)
- par.1: “evaluated usefulness” -> “evaluated the usefulness”

Section 8

- Par.2: “propose various approaches” -> “implement various approaches”
- Par.5: “clarification dialogues and learning mechanism” -> “the clarification dialogues and the learning mechanism”

Section 9

- Par.1: “we have introduced” -> “we introduced”
- In your response to the reviewers, you mentioned that you are planning to perform further usability studies. I would suggest you add this in the paragraph describing your plans for future work.

I would also suggest you ask a native English speaker to proofread the paper before submitting the final version.