Chatbot

About: Chatbot is a research topic. Over the lifetime, 2415 publications have been published within this topic receiving 24372 citations. The topic is also known as: IM bot & AI chatbot.

Externalization of tacit knowledge in a knowledge management system using chat bots

Abstract: Knowledge is the most valued asset in today's world. Knowledge is an asset that is difficult to be replicated. In the competitive era, every firm would want to have a system wherein they can store and manage the knowledge. Any organizations performance can be assessed by the intellectual assets that they have. Every type of knowledge cannot be acquired and stored. The most important and critical type of knowledge is the tacit knowledge, which is difficult to be articulated. The tacit knowledge is the asset that brings more value to any Knowledge management system. Formal and informal methods, structural representations, mathematical models can be used to store the tacit information, acquired from experts. Retrieval of knowledge stored will not work better with the traditional search methods. Intelligent search techniques will have to be used to retrieve the right information. One of the concepts suggested for sharing the knowledge suggested is by using a query management system An expert can share his/her knowledge only at one place, whereas with the Knowledge management System, a Knowledge expert can be present virtually anywhere. To enable this, Chat bots can be used, thus making location redundant. A Chatbot has no limitation of how many queries it can accept, since a Chatbot allow users to seamlessly interact with multiple users from one location. Use of Chat Bots will make the sharing of Knowledge more effective and efficient.

A Neural Network based Vietnamese Chatbot

Abstract: Nowadays, chatbot is a hot topic, chatbots are built from generative models are gaining success. The purpose of this article is to build a Vietnamese chatbot based on the seq2seq model incorporating the attention mechanism. We have built the model and tested on deep learning framework Pytorch using GPU. The model was trained end-to-end with no hand-crafted rules. Model is built from a small dataset and can generate responses to a user. However, generated responses still need to be improved to get a meaningful conversation.

Learning Implicit User Profile for Personalized Retrieval-Based Chatbot

Abstract: In this paper, we explore the problem of developing personalized chatbots. A personalized chatbot is designed as a digital chatting assistant for a user. The key characteristic of a personalized chatbot is that it should have a consistent personality with the corresponding user. It can talk the same way as the user when it is delegated to respond to others' messages. Many methods have been proposed to assign a personality to dialogue chatbots, but most of them utilize explicit user profiles, including several persona descriptions or key-value-based personal information. In a practical scenario, however, users might be reluctant to write detailed persona descriptions, and obtaining a large number of explicit user profiles requires tremendous manual labour. To tackle the problem, we present a retrieval-based personalized chatbot model, namely IMPChat, to learn an implicit user profile from the user's dialogue history. We argue that the implicit user profile is superior to the explicit user profile regarding accessibility and flexibility. IMPChat aims to learn an implicit user profile through modeling user's personalized language style and personalized preferences separately. To learn a user's personalized language style, we elaborately build language models from shallow to deep using the user's historical responses; To model a user's personalized preferences, we explore the conditional relations underneath each post-response pair of the user. The personalized preferences are dynamic and context-aware: we assign higher weights to those historical pairs that are topically related to the current query when aggregating the personalized preferences. We match each response candidate with the personalized language style and personalized preference, respectively, and fuse the two matching signals to determine the final ranking score. We conduct comprehensive experiments on two large datasets, and the results show that our method outperforms all baseline models.

Towards an open-domain chatbot for language practice

Abstract: State-of-the-art chatbots for English are now able to hold conversations on virtually any topic (e.g. Adiwardana et al., 2020; Roller et al., 2021). However, existing dialogue systems in the language learning domain still use hand-crafted rules and pattern matching, and are much more limited in scope. In this paper, we make an initial foray into adapting open-domain dialogue generation for second language learning. We propose and implement decoding strategies that can adjust the difficulty level of the chatbot according to the learner’s needs, without requiring further training of the chatbot. These strategies are then evaluated using judgements from human examiners trained in language education. Our results show that re-ranking candidate outputs is a particularly effective strategy, and performance can be further improved by adding sub-token penalties and filtering.

Query Expansion Evaluation for Chatbot Application

Abstract: At this digital era, the recent stage of business system makes so many opportunity and innovation, such as online shopping. The system provides easier interaction between seller and customer. But the problem is, the seller can't response immediately while the customer asks. Therefore, a chatbot can be a solution so the seller can response a question quickly. This research proposes a chatbot system with a frequently asked question knowledge base. An additional query expansion mechanism based on thesaurus dictionary is implemented. Cosine similarity metric then being used to measure similary between query and question in frequently asked question. This research reveals the experimental results of this approach not as good as of similarity logic system.