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

Tracking #: 1478-2690

Authors: 
Zeynep Dogmus
Esra Erdem
Volkan Patoglu

Responsible editor: 
Guest Editors ENLI4SW 2016

Submission type: 
Full Paper
Abstract: 
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 and description logics concepts; (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: 
Tags: 
Reviewed

Decision/Status: 
Major Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Nick Bassiliades submitted on 11/Dec/2016
Suggestion:
Major Revision
Review Comment:

This paper describes an ontology for rehabilitation robotics and a (controlled) natural language query answering system for answering questions on the same domain, based on the ontology. The paper is an extended version of a paper presented at KEOD 2014 and contains more details about the QA system implementation and also gives more details on the ontology, taken from previous papers of the same authors.

In general, the paper is well presented and clear. Some parts need improvement, both in content and in technical depth. A general comment for the methodology and the system presented is that although the system is presented as a completely domain-dependent system, most (if not all) parts of the methodology and the algorithms do not seem to be tied the specific ontology. This means that a more generic description of the methodology could be given so that the system could be re-used for other domains by changing the ontology and the controlled natural language grammar, accordingly.
For example, types correspond to classes, verbs to object properties, nouns to data type properties, values to ranges. Such a homomorphism should be exploited to create a generic language that is constrained by ontological terms, independently of a specific ontology.
The authors should think about this and provide either arguments against the validity of this claim or a generic methodology whose one of the use cases could be the rehabilitation robotics domain.

Detailed comments are given below:

- A paragraph for introducing the rehabilitation robotics domain should be given in section 1.

- Concerning the ontology, I believe that the classes "References" and "Owners" could be modelled by re-using concepts from well-known ontologies, such as BIBO or FaBio (for references) and FOAF for owners. The authors should justify their choice for introducing completely new classes for such common concepts.

- The URL of the ontology should be included in the manuscript.

- An algorithm for section 5.3 is needed, as well. Instead the translation from DL concepts to SPARQL concepts is described informally through examples.

- I believe that you should explain/motivate why you provide a 2-step translation from NLP-to-DLConcepts and then from DLConcepts-to-SPARQL. What would be the problem if you tried to translate from NLP-to-SPARQL in one step? Furthermore, since you are using DL concepts as a medium representation for the query, wouldn't be more appropriate/convenient for you to use a query language such as SPARQL-DL? Please explain/motivate on this.

- Table 8: I believe that the treatment of the universal restriction in SPARQL is wrong. Specifically, the double NOT EXISTS filters in the SPARQL expression should be nested differently than the transformation suggested by the paper.
Currently the paper includes the following:
FILTER NOT EXISTS {
FILTER NOT EXISTS {
?x rr:reference ?y2.
}
?y2 rdf:type rr:RehabRobots.
}
and the text inside explains:
"... The first FILTER NOT EXISTS expression contains another FILTER NOT EXISTS expression, which contains a triple that represents the robots y2 referenced by the previously described publication x. There is a triple in the first expression as well, that states y2 is a robot. Since both expressions contain the same variable, the mappings should agree on the robot y2. ..."
This is a wrong interpretation of the NOT EXISTS construct. Variables that are bound within a NOT EXISTS construct DO NOT "transmit" their value outside the scope of the NOT EXISTS construct in which they appear. NOT EXISTS means that there is no ?y2 value that satisfies the graph pattern inside the NOT EXISTS construct. Take a look at the W3C recommendation for SPARQL:
https://www.w3.org/TR/sparql11-query/#neg-notexists
It is explicitly stated that: "The NOT EXISTS filter expression tests whether a graph pattern does not match the dataset, given the values of variables in the group graph pattern in which the filter occurs. It does not generate any additional bindings." So, variable ?y2 cannot be bound to a value outside the scope of the inner NOT EXISTS construct.
Instead, the query should be rewritten as:
FILTER NOT EXISTS {
?y2 rdf:type rr:RehabRobots.
FILTER NOT EXISTS {
?x rr:reference ?y2.
}
}
Here, variable ?y2 is bound (within the scope of the outer NOT EXISTS) and this binding is also valid within the second NOT EXISTS construct, but not outside the outer NOT EXISTS construct.

- In the related work section you should not just describe other works of the same or similar nature, but you should try to compare your system with them and bring out the advantages/disadvantages and differences of your system.

Review #2
Anonymous submitted on 16/Dec/2016
Suggestion:
Reject
Review Comment:

The paper describes a method for expressing and answering natural language queries about rehabilitation robots. The method consists of a controlled natural language for queries, a translation of queries expressed in this languages into SPARQL queries making use of the terms of an ontology for rehabilitation robotics (REHABROBO-ONTO), and the use of a DL reasoner (Pellet) for answering the SPARQL queries. The paper also presents a query interface, which facilitates the formation of the natural language queries.

Given the increased use of robots in rehabilitation environments and the extensive research in this area, the topic of the paper is very interesting, and the method it proposes is very helpful especially for researchers working in this area.

However, I have major concerns regarding the original contributions of the paper.

This paper does not really present much new compared to the previous conference paper (KEOD, 2014) of the same authors. As the authors also state in the last paragraph of Section 1, it only provides some more details about the language, the query interface, and the query answering system and some more clarifying examples. Such contributions, in my opinion, are not sufficient for a journal paper.

Some useful additions/extensions that I would expect to see in the journal paper are:

- A more extended introduction on rehabilitation robotics, including a presentation of the state of the art, the challenges that still need to be addressed, and the current trends of the research in this domain.

- A description of an example scenario in the beginning of the paper, which would help in clarifying the scope of the paper and the specific challenges it addresses, and which could be used as a running example throughout the paper.

- Most importantly, an evaluation of the language and the query interface with real users, which would demonstrate how the proposed approach fits the needs of the people working in this domain.

- An evaluation of the proposed algorithms for the translation of the natural language queries. This could either have the form of formally proving the properties (e.g. complexity) of the algorithms or of an experimental evaluation of their performance.

- A more extensive comparison with related work in this area. For example, why was SPARQL preferred over ASP or other languages proposed in other similar studies?

Overall my recommendation to the editors is to reject the publication of the paper. But at the same time, I would encourage the authors of the paper to evaluate their method and present the results in a new paper.

Review #3
Anonymous submitted on 23/Feb/2017
Suggestion:
Minor Revision
Review Comment:

The paper proposes a controlled natural language for expressing quires about rehabilitation robotics, an intelligent and interactive user interface for auto-completion of quires and algorithms for transforming a query in controlled natural language into a SPARQL query.
(1) Originality
The article documents the relevant state of the art (section 7) as well as the motivational need behind the paper’s idea (section 1) in different sections. However, an insightful analysis of the state of the art discussing the current research initiatives in the field and the gaps that led to the specific paper is missing from both sections. In addition, the paper’s introductory section (section 1) gives more emphasis on authors’ past research than on the actual problem and the motives behind the solution. Thus, a restructure would be suggested.
(2) Significance of the results
Although the methods are well documented and several examples are given to describe algorithms’ operation, the article lacks an adequate evaluation. Even if the proof-of-concept is useful, it does not support the computational feasibility of the proposed approach. This makes it impossible to evaluate the proposed model. The same problem is present about the translation of queries in controlled natural language into SPARQL queries. How is it performed? What is the performance of such automated framework?
(3) Quality of writing
The paper is coherent, easily followed and well-organized with clearly marked sections. Throughout the document, there is appropriate use of examples, figures and tables that either demonstrate or exemplify parts of the functionality of the proposed solution.
Other comments/recommendations (lexical and syntactical):
*As regards section 1, the paragraph “The ontology system… medicine.” contains parts such as “The ontology system… process” and “on the other hand, … disorders” that are repeated earlier in paragraph 2 “This article…automatically”.
*”concerned about”-> concerned with
*”can easily add information” I would rephrase it as follows: use it in order to publish/represent information
* “access to the related publications”-> access the related publications
* “by describing more details about the query answering” -> by providing/giving more details about the query answering