MyrrorBot : A Digital Assistant Based on Holistic User Models for Personalized Access to Online Services

2021 ◽  
Vol 39 (4) ◽  
pp. 1-34
Author(s):  
Cataldo Musto ◽  
Fedelucio Narducci ◽  
Marco Polignano ◽  
Marco De Gemmis ◽  
Pasquale Lops ◽  
...  
Keyword(s):  
Natural Language ◽  
Information Needs ◽  
Effective Interaction ◽  
Personal Digital Assistant ◽  
User Profiling ◽  
Online Services ◽  
Intent Recognition ◽  
User Models ◽  
Time Required ◽  
The Way

In this article, we present MyrrorBot , a personal digital assistant implementing a natural language interface that allows the users to: (i) access online services, such as music, video, news, and food recommendation s, in a personalized way, by exploiting a strategy for implicit user modeling called holistic user profiling ; (ii) query their own user models, to inspect the features encoded in their profiles and to increase their awareness of the personalization process. Basically, the system allows the users to formulate natural language requests related to their information needs. Such needs are roughly classified in two groups: quantified self-related needs (e.g., Did I sleep enough? Am I extrovert? ) and personalized access to online services (e.g., Play a song I like ). The intent recognition strategy implemented in the platform automatically identifies the intent expressed by the user and forwards the request to specific services and modules that generate an appropriate answer that fulfills the query. In the experimental evaluation, we evaluated both qualitative (users’ acceptance of the system, usability) as well as quantitative (time required to complete basic tasks, effectiveness of the personalization strategy) aspects of the system, and the results showed that MyrrorBot can improve the way people access online services and applications. This leads to a more effective interaction and paves the way for further development of our system.

PRINCIPAL PROBLEMS OF NATURAL LANGUAGE PROCESSING SYSTEMS

2018 ◽  
pp. 35-38
Author(s):  
O. Hyryn
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Syntactic Analysis ◽  
Syntactic Ambiguity ◽  
Grammatical Structure ◽  
English Sentence ◽  
Analysis Methods ◽  
The Way

The article deals with natural language processing, namely that of an English sentence. The article describes the problems, which might arise during the process and which are connected with graphic, semantic, and syntactic ambiguity. The article provides the description of how the problems had been solved before the automatic syntactic analysis was applied and the way, such analysis methods could be helpful in developing new analysis algorithms. The analysis focuses on the issues, blocking the basis for the natural language processing — parsing — the process of sentence analysis according to their structure, content and meaning, which aims to analyze the grammatical structure of the sentence, the division of sentences into constituent components and defining links between them.

scholarly journals BioVerbNet: a large semantic-syntactic classification of verbs in biomedicine

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Olga Majewska ◽  
Charlotte Collins ◽  
Simon Baker ◽  
Jari Björne ◽  
Susan Windisch Brown ◽  
...  
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Model Performance ◽  
Representation Learning ◽  
Verb Classes ◽  
Expert Annotation ◽  
Biomedical Texts ◽  
Time Required ◽  
Verb Meaning

Abstract Background Recent advances in representation learning have enabled large strides in natural language understanding; However, verbal reasoning remains a challenge for state-of-the-art systems. External sources of structured, expert-curated verb-related knowledge have been shown to boost model performance in different Natural Language Processing (NLP) tasks where accurate handling of verb meaning and behaviour is critical. The costliness and time required for manual lexicon construction has been a major obstacle to porting the benefits of such resources to NLP in specialised domains, such as biomedicine. To address this issue, we combine a neural classification method with expert annotation to create BioVerbNet. This new resource comprises 693 verbs assigned to 22 top-level and 117 fine-grained semantic-syntactic verb classes. We make this resource available complete with semantic roles and VerbNet-style syntactic frames. Results We demonstrate the utility of the new resource in boosting model performance in document- and sentence-level classification in biomedicine. We apply an established retrofitting method to harness the verb class membership knowledge from BioVerbNet and transform a pretrained word embedding space by pulling together verbs belonging to the same semantic-syntactic class. The BioVerbNet knowledge-aware embeddings surpass the non-specialised baseline by a significant margin on both tasks. Conclusion This work introduces the first large, annotated semantic-syntactic classification of biomedical verbs, providing a detailed account of the annotation process, the key differences in verb behaviour between the general and biomedical domain, and the design choices made to accurately capture the meaning and properties of verbs used in biomedical texts. The demonstrated benefits of leveraging BioVerbNet in text classification suggest the resource could help systems better tackle challenging NLP tasks in biomedicine.

Who is allowed to read and write?

2020 ◽  
Vol 19 (3) ◽  
pp. 116-117
Author(s):  
Christian P Subbe ◽  
Keyword(s):  
Information Needs ◽  
Healthcare Professionals ◽  
Personal Health Records ◽  
High Rate ◽  
Personal Health ◽  
Care Needs ◽  
Serious Adverse Events ◽  
Health Records ◽  
Clinical Records ◽  
The Way

What makes us human? In 2015 Jeremy Vine asked this question to a selection of leading British thinkers and writers. The answers were as diverse as the people he interviewed. While you might have your own views about the complexity of being human I would suggest that being able to articulate thoughts and communicate them to others might be one of the characteristics that distinguishes us from other life forms. And if we think more about the achievements of human culture then being able to communicate thoughts in writing and reading other people’s thoughts is one of the unique abilities that humanity has acquired during its evolution: Young humans spend extensive time to learn how to read and write. They write on paper, they read books and they do the same on computers. They become adults. They read and write most days: they e-mail their telephone company, file online forms to the tax office and or write romantic notes to their partner. Then they get older and become unwell and enter large modern building full of the most state-of-the-art technology. But here, in hospitals, none of them are allowed to read or write. They are being asked questions by someone who is often younger and in a rush. That person usually speaks a different language called jargon and try their best to translate their jargon to normal language.1 Patients are not allowed to write their own records and access to read the records is cumbersome. And if this is how we structure communication in our clinical practice then why are we surprised about the hierarchical relationship between patients and healthcare professionals and the high rate of error due to miscommunication? There might be good reasons for the way we document in healthcare: historically only the educated few like doctors were able to read and write and therefore the way to record patient histories had to be by those who were educated to do so. Additionally professions have always defined themselves by their own professional language and jargon that allows their members to describe matters precisely and at the same time create a sense of identity. Things have however changed in the last 100 years and a large proportion of our patients is able to read and write and might be perfectly capable to document their own information (and subsequently read all information that relates to them). The paper from Renggli et al in this issue of Acute Medicine explores the feasibility of documentation by patients on admission to hospital in Switzerland by using a web-based platform: at least half of the patients who were admitted with an emergency to hospital could document important parts their own medical history. The study demonstrated that documentation by patients added additional new information over and beyond of that collected by doctors and improved completeness of records, especially for the increasingly important social history. The paper has three important implications: Good information needs time: Patients can add more information if given the questions and their own time – rushing through an unprepared face-to-face consultation is unlikely to bring out the most relevant information in a reliable fashion. Sharing with patients might improve work-efficiency. Up to 25% of the time of doctors and nurses working in hospitals is taken up by documentation2,3: at a time when so many employed in healthcare are overworked and burnt out it would be reckless not to consider changes in information flow through the lens of work-load and efficiency. Quality care needs joint ownership with patients: Patients participation in the co-design and delivery of new services and shared decision of patients and clinicians in making of complex decision has been challenging to say the least. Co-ownership of clinical records is potentially a key strategic lever to achieve better decisions and services. Patient organisations and policy makers are expecting for patients to access medical records. Personal health records are now compulsory in some countries with roll-out of access for all citizens completed in countries like Estonia since 20084 and Sweden since 2018.5 It is National Health Service (NHS) policy to make a “personalized healthcare” available to everybody by 2020.6 That is now. Despite this there is virtually no evidence for the usage of personal health records in hospital.7,8 There are significant caveats to the current study: Half of the patients approached declined to take part and it is unclear why this was the case. Maybe they did not want to take part in any research. Maybe they felt too unwell to write. And maybe they were unable to read and write. While most people reaching adulthood in European countries have gone to school there is also evidence that up to 7 million adults in England are functionally illiterate and not able to read and write beyond the most basic level9 and relying on friends and family members, signs and symbols to travel through modern life. There is also an increasing body of work about digital exclusion and concerns that those who are unable to navigate the online world are at risk of being left behind by society.10 There are additional questions about ownership: do patients own all data that relates to their care or is documentation by healthcare professionals their intellectual property. There are strong arguments for both perspectives. From a patient safety point of view their would seem to be a strong imperative to come to pragmatic agreements. Research suggests that the majority of serious adverse events was flagged by patients and relatives at a time when they could have been predicted and potentially prevented by clinical teams.11 But safety critical information is often hidden from those who are most affected by it, the patients. The paper by Renggli et all does therefore provide important evidence for the development of a more co-operative and democratic way of providing acute care by using something that is a key part of being human: the ability to read and write.

scholarly journals How Efficiency Shapes Human Language, TICS 2019

2019 ◽  
Author(s):  
Edward Gibson ◽  
Richard Futrell ◽  
Steven T. Piantadosi ◽  
Isabelle Dautriche ◽  
Kyle Mahowald ◽  
...  
Keyword(s):  
Information Theory ◽  
Cognitive Psychology ◽  
Natural Language ◽  
Cognitive Science ◽  
Human Language ◽  
Language Research ◽  
The Way

Cognitive science applies diverse tools and perspectives to study human language. Recently, an exciting body of work has examined linguistic phenomena through the lens of efficiency in usage: what otherwise puzzling features of language find explanation in formal accounts of how language might be optimized for communication and learning? Here, we review studies that deploy formal tools from probability and information theory to understand how and why language works the way that it does, focusing on phenomena ranging from the lexicon through syntax. These studies show how apervasive pressure for efficiency guides the forms of natural language and indicate that a rich future for language research lies in connecting linguistics to cognitive psychology and mathematical theories of communication and inference.

Intention‐Based Semantics

2009 ◽  
Author(s):  
Emma Borg
Keyword(s):  
Natural Language ◽  
Acoustic Properties ◽  
Possible World ◽  
Important Respect ◽  
Physical Objects ◽  
Intentional Agents ◽  
The Way

There is a sense in which it is trivial to say that one accepts intention- (or convention-)based semantics. For if what is meant by this claim is simply that there is an important respect in which words and sentences have meaning (either at all or the particular meanings that they have in any given natural language) due to the fact that they are used, in the way they are, by intentional agents (i.e. speakers), then it seems no one should disagree. For imagine a possible world where there are physical things which share the shape and form of words of English or Japanese, or the acoustic properties of sentences of Finnish or Arapaho, yet where there are no intentional agents (or where any remaining intentional agents don't use language). In such a world, it seems clear that these physical objects, which are only superficially language-like, will lack all meaning.

Information Seeking Behavior of Users and Strategies to Overcome the Challenges in the Current Era

2013 ◽  
pp. 284-288
Author(s):  
A. Dakshayani ◽  
S. Srinivasan
Keyword(s):  
Research And Development ◽  
Information Seeking ◽  
Information Needs ◽  
Information Overload ◽  
User Community ◽  
Seeking Behavior ◽  
Nature Of Information ◽  
Information Professionals ◽  
Almost All ◽  
The Way

Due to the continuous research and development activities taking place in almost all the disciplines, information overload and information explosion has occurred, which in turn poses a challenge to the user community to keep up with the knowledge in their discipline. The dynamic nature of information has forced the users to change the way of seeking information. Hence, there is an immediate need for the information professionals to update the services and facilities of the library. He/she should act as a ultimate search engine and satisfy the information needs of the users. This chapter highlights the changing approach to information by the user community in the present scenario and also provides the solutions to information professionals to tackle the information expectations of the users. This chapter has been written based on the observation of library users and the way they seek information for their business requirements and research and development activities.

Question Answering and Generation

2012 ◽  
pp. 1-16 ◽  
Author(s):  
Arthur C. Graesser ◽  
Vasile Rus ◽  
Zhiqiang Cai ◽  
Xiangen Hu
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Information Needs ◽  
Question Answering ◽  
Learning Technologies ◽  
Question Asking ◽  
Tutoring Systems ◽  
Computer Based Training ◽  
Recent Developments ◽  
Text Meaning Representation

Automated Question Answering and Asking are two active areas of Natural Language Processing with the former dominating the past decade and the latter most likely to dominate the next one. Due to the vast amounts of information available electronically in the Internet era, automated Question Answering is needed to fulfill information needs in an efficient and effective manner. Automated Question Answering is the task of providing answers automatically to questions asked in natural language. Typically, the answers are retrieved from large collections of documents. While answering any question is difficult, successful automated solutions to answer some type of questions, so-called factoid questions, have been developed recently, culminating with the just announced Watson Question Answering system developed by I.B.M. to compete in Jeopardy-like games. The flip process, automated Question Asking or Generation, is about generating questions from some form of input such as a text, meaning representation, or database. Question Asking/Generation is an important component in the full gamut of learning technologies, from conventional computer-based training to tutoring systems. Advances in Question Asking/Generation are projected to revolutionize learning and dialogue systems. This chapter presents an overview of recent developments in Question Answering and Generation starting with the landscape of questions that people ask.

Comments on Friederike Moltmann’s “Variable Objects and Truth-Making”

2020 ◽  
pp. 496-502
Author(s):  
Kit Fine
Keyword(s):  
Natural Language ◽  
Possible Worlds ◽  
Broad Agreement ◽  
Montague Semantics ◽  
The Subject ◽  
The Many ◽  
The Way

I have long admired Friederike Moltmann’s work at the intersection of linguistics and philosophy; and I have always been especially impressed by the way in which she has attempted to break free of the stranglehold of the possible worlds approach by showing how the diversified ontology of objects commonly associated with traditional metaphysics provides a much better tool for the investigation of natural language than the simple and stylized ontology of Montague semantics. The present paper is a characteristically rich, original and thought-provoking contribution to the subject; and I am afraid that I can do no more than pick my way through one or two of the many interesting issues that she raises. However, any criticisms I make on this score should not be seen to detract from my broad agreement with much of what she says....

Smart Refrigerator with Recipe Assistance

2017 ◽  
Vol 8 (2) ◽  
pp. 51-61
Author(s):  
Aishwarya Gadgil ◽  
Vedija Jagtap ◽  
Pooja Kulkarni
Keyword(s):  
Internet Of Things ◽  
Smart Home ◽  
Rfid Tags ◽  
Creative Processes ◽  
Rfid Tag ◽  
Technological Revolution ◽  
Load Cells ◽  
Time Required ◽  
Intellectual Power ◽  
The Way

Internet of Things (IoT) will lead to a technological revolution that will change the way people live and interact with their surroundings. Intelligent appliances combined with multimedia capability have been emerging in everyone's life. Smart home is one of the prominent areas of intelligent advances. Kitchen is considered as the center of our house, where the refrigerator plays an important role. Smart Refrigerator with Recipe Assistance will help in automating the refrigerator. The authors propose a system that would track the stock of ingredients in the refrigerator with the help of RFID tags and load cells. According to the availability of ingredients a list of possible recipes is predicted and suggestions will be given to the user. Whenever an item is identified by a RFID tag, estimations on the usage of ingredients are made and we can get notifications about the scarce products. The system will also help in checking the availability of ingredients based on the recipe user wishes to cook. The time required by an individual for manually checking the availability of ingredients in the refrigerator and then thinking about what to cook is greatly reduced using this system. Most of the information is automatically generated using RFID tags. Once the user logins into the application he/ she will be suggested the possible list of recipes based on the availability. Human intellectual power then can be used for new creative processes rather than using it for routine chores.

scholarly journals LOGICS FOR PROPOSITIONAL DETERMINACY AND INDEPENDENCE

2018 ◽  
Vol 11 (3) ◽  
pp. 470-506 ◽  
Author(s):  
VALENTIN GORANKO ◽  
ANTTI KUUSISTO
Keyword(s):  
Natural Language ◽  
Kripke Semantics ◽  
Dependence Logic ◽  
Team Semantics ◽  
Reasoning Tasks ◽  
Image Position ◽  
The Way

AbstractThis paper investigates formal logics for reasoning about determinacy and independence. Propositional Dependence Logic${\cal D}$and Propositional Independence Logic${\cal I}$are recently developed logical systems, based on team semantics, that provide a framework for such reasoning tasks. We introduce two new logics${{\cal L}_D}$and${{\cal L}_{\,I\,}}$, based on Kripke semantics, and propose them as alternatives for${\cal D}$and${\cal I}$, respectively. We analyse the relative expressive powers of these four logics and discuss the way these systems relate to natural language. We argue that${{\cal L}_D}$and${{\cal L}_{\,I\,}}$naturally resolve a range of interpretational problems that arise in${\cal D}$and${\cal I}$. We also obtain sound and complete axiomatizations for${{\cal L}_D}$and${{\cal L}_{\,I\,}}$.

Sign in / Sign up

Export Citation Format

Share Document