• Corpus ID: 209092287

KINO: an approach for rule-based chatbot development, monitoring and evaluation

@inproceedings{Dvila2018KINOAA,
  title={KINO: an approach for rule-based chatbot development, monitoring and evaluation},
  author={Thiago Carvalho D'{\'A}vila},
  year={2018}
}
Chatbots are software conversational agents invented in the 1960’s that answer in human language. There are still many challenges and opportunities to be explored, even though more than fifty years have gone by since the first chatbot was created. The aim of this research is to develop the implementation, evaluation, and monitoring for a rule-based chatbot. Having this in mind, KINO, a bot that answers questions about movies, was developed. KINO’s architecture is presented, along with… 

Comparing users' perception of different chatbot interaction paradigms: a case study

In this work, we used the results of applying the Semiotic Inspection Method (SIM) to popular chatbots[12, 13], which yielded eleven strategies for conveying features to users, as well as six sign

References

SHOWING 1-10 OF 63 REFERENCES

Evaluation of Modern Tools for an OMSCS Advisor Chatbot

TLDR
A survey of modern chatbot platforms, Natural Language Processing tools, and their application and design is proposed for the GA Tech.

Survey on Chatbot Design Techniques in Speech Conversation Systems

TLDR
This paper presents a survey on the techniques used to design Chatbots and a comparison is made between different design techniques from nine carefully selected papers according to the main methods adopted.

DocChat: An Information Retrieval Approach for Chatbot Engines Using Unstructured Documents

TLDR
This paper presents DocChat, a novel information retrieval approach for chatbot engines that can leverage unstructured documents, instead of Q-R pairs, to respond to utterances.

Enhancing Community Interactions with Data-Driven Chatbots--The DBpedia Chatbot

TLDR
The DBpedia chatbot is introduced, a knowledge-graph-driven chatbot designed to optimize community interaction that was designed for integration into community software to facilitate the answering of recurrent questions.

Bots as Language Learning Tools

TLDR
Online chatbots could provide a means of language practice for students anytime and virtually anywhere and should be brought into the FLL classroom as a permanent tool for language practice.

A Normalizer for UGC in Brazilian Portuguese

TLDR
UGCNormal is presented, a lexicon-based tool for UGC normalization that encompasses a tokenizer, a sentence segmentation tool, a phonetic-based speller and some lexicons, which were originated from a deep analysis of a corpus of product reviews in Brazilian Portuguese.

Automated Assistance in E-commerce: An Approach Based on Category-Sensitive Retrieval

TLDR
This paper builds a multi-instance SVM classifier to automatically classify live chat messages between human agents and buyers and finds that using class information along with the base dual encoder model helps in improving the quality of the retrieved responses in terms of BLEU scores.

A Retrieval-Based Dialogue System Utilizing Utterance and Context Embeddings

  • A. BartlGerasimos Spanakis
  • Computer Science
    2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)
  • 2017
TLDR
Experimental results on the well-known Ubuntu Corpus and a customer service chat dataset show that, in combination with a candidate selection method, retrieval-based approaches outperform generative ones and reveal promising future research directions towards the usability of such a system.

Representando o conhecimento através de ontologias: o caso do chatterbot Lunmi

TLDR
This work presents a chatterbot named Lunmi, which purpose is to answer questions about a scientific electronic journal available in a site, which was supported by the ALICE technology and AIML language.

Qanary - A Methodology for Vocabulary-Driven Open Question Answering Systems

TLDR
This work provides an approach driven by a core QA vocabulary that is aligned to existing, powerful ontologies provided by domain-specific communities, and is agnostic to implementation details and that inherently follows the linked data principles.
...