Results from a 32 participant study, show that the fuzzy measure improves rule matching within the dialogue system by 21.88% compared with the crisp measure known as STASIS, thus providing a more natural and fluid dialogue exchange.
Abstract:
Dialogue systems are automated systems that interact with humans using natural language. Much work has been done on dialogue management and learning using a range of computational intelligence based approaches, however the complexity of human dialogue in different contexts still presents many challenges. The key impact of work presented in this paper is to use fuzzy semantic similarity measures embedded within a dialogue system to allow a machine to semantically comprehend human utterances in a given context and thus communicate more effectively with a human in a specific domain using natural language. To achieve this, perception based words should be understood by a machine in context of the dialogue. In this work, a simple question and answer dialogue system is implemented for a cafe customer satisfaction feedback survey. Both fuzzy and crisp semantic similarity measures are used within the dialogue engine to assess the accuracy and robustness of rule firing. Results from a 32 participant study, show that the fuzzy measure improves rule matching within the dialogue system by 21.88% compared with the crisp measure known as STASIS, thus providing a more natural and fluid dialogue exchange.
TL;DR: In this article, a fuzzy influence factor is introduced into an existing measure known as FUSE, which computes the similarity between two short texts based on weighted syntactic and semantic components in order to address the issue of comparing fuzzy words that exist in different word categories.
TL;DR: In this article , the authors present a process for transforming unstructured dialogues into a structured schema, which comprises four stages: processing the dialogues through entity extraction and data aggregation, storing them as NoSQL documents on the cloud, transforming them into a star schema for online analytical processing and building an extract-transform-load workflow, and creating a web-based dashboard for visualizing summarized data and reports.
TL;DR: The research work is able to identify the best method to be used for the reviews identification in the best possible method based on the comparison of the other traditional based Sentiment Analysis methodology with the ANFIS.
TL;DR: Experiments demonstrate that the proposed method provides a similarity measure that shows a significant correlation to human intuition and can be used in a variety of applications that involve text knowledge representation and discovery.
TL;DR: An agent application taxonomy was developed, the main challenges in the field were identified, and the main types of dialog and contexts related to conversational agents in health were defined.
TL;DR: The results show that learners experiencing a conversational tutorial personalised to their learning styles performed significantly better during the tutorial than those with an unmatched tutorial.
Q1. What are the contributions mentioned in the paper "Interpreting human responses in dialogue systems using fuzzy semantic similarity measures" ?
The key impact of work presented in this paper is to use fuzzy semantic similarity measures embedded within a dialogue system to allow a machine to semantically comprehend human utterances in a given context and thus communicate more effectively with a human in a specific domain using natural language. In this work, a simple question and answer dialogue system is implemented for a café customer satisfaction feedback survey. Results from a 32 participant study, show that the fuzzy measure improves rule matching within the dialogue system by 21.
Q2. What did the DS say about the light level of the cafe?
The light level of the cafe is not brightBoth FUSE and STASIS picked this up as the high threshold because of the word bright, when in effect due to the use of the word not, it actually means it was dark.
Q3. What is the definition of the term "Low"?
The physical appearance of the barista tells that she was in her 30'sBoth FUSE and STASIS picked this up as belonging to the low category, consisting of words such as baby, young, child, etc;when according to the two English language experts, it should be in the mid threshold containing words such as adult, middleaged, grownup etc.
Q4. What is the high threshold for a FSSM?
Given the original research question, the authors conclude that a Fuzzy Sentence Similarity Measure (FSSM) can be incorporated into a dialogue system to improve rule matching ability from a user utterance compared with a traditional STSM.
Q5. What is the effect of the FSSM on the user?
D) Effect on UsabilityAll participants completed a short usability survey comprising of 13 Likert scale questions with allowable free text, following completion of the task.
Q6. What was the definition of the term?
An additional example of negations leading to an incorrect rule firing was when the DS asked the question relating to the category Strength:User Utterance: The authorwould describe them as lean and not very strong.