COMP 10261: The FAQ Bot Plus Project Sam Scott, Mohawk Colle ✓ Solved

COMP 10261: The FAQ Bot Plus Project Sam Scott, Mohawk College

An FAQ Bot answers questions about a particular topic. It is a conversational interface to a stock set of questions and answers. When an FAQ Bot receives an utterance, it determines the user’s intent by matching that utterance to one of its stored question and answer pairs. If it succeeds in determining intent in this way, it uses the answer as its response. If an FAQ Bot fails to determine intent, it usually outputs a standard message to let the user know that it does not know the answer. But your FAQ Bot Plus will use linguistic knowledge from spaCy to get a bit chattier in this case.

PHASE 1: FAQ BOT In this phase, the goal is to update your Phase 0 FAQ Bot using fuzzy regular expressions to determine a user’s intent.

1. From Phase 0 (Should already be complete). Determine your FAQ Bot’s knowledge domain and prepare a set of 20 question and answer pairs. One easy way to do this is to find a long Wikipedia page and copy sections of 1 to 3 sentences as each answer and generate a question to go with each answer. Make sure you reference all online sources in comments.

2. Generalize by generating at least one more possible question for each answer. Ideally, the new question should have a different wording, representing another way a user might ask for the information in the answer.

3. Create a fuzzy regular expression for each answer that is capable of matching key parts of both possible questions and is tolerant to a limited number of typos in each question.

4. Store questions, answers, and regular expressions in text files.

5. Create a Python program (or modify your Phase 0 FAQ Bot) to load the answers and regular expressions from files, then allow the user to make utterances. Try to find the best match for the user’s utterance from your list of regular expressions and output the corresponding answer. When there are multiple matches, you should have some strategy for determining which match is better.

6. The bot should also respond to “hello” by greeting the user, and “goodbye” or “quit” by ending the program. If it fails to match an utterance, the bot should politely let the user know that it didn’t recognize their question. Test your bot as much as possible. Use the original question, the alternate wordings, and any other wordings you can think of. If possible, give the bot to a friend or family member to play with and see how well it works for them. Tweak your regular expressions as necessary to get the best possible performance.

PHASE 2: FAQ BOT PLUS In this phase, the goal is to make the FAQ Bot a bit chattier or human-like using linguistic knowledge from the spaCy module. It should still answer the user’s questions as before, but if it fails to figure out a user’s intent, it should employ a range of strategies to try craft an appropriate response.

This part of the project is open-ended and creative, but you must make use of the spaCy pattern matcher with parts of speech and/or lemmas in at least one part of your bot. NAMED ENTITY RECOGNITION AND NOUN CHUNKS When the bot don’t know what the user is talking about, Named Entity Recognition or even Noun Chunks could help implement a fallback strategy.

To make the bot seem chattier or more human-like when it fails to match a user intent, you could attempt to classify the speech act of the utterance. You can think of a speech act as a very high-level intent that indicates what kind of action is the user trying to accomplish with their utterance.

PHASE 3: DISCORD Once the bot is working well in the Python shell, you should repackage it as a Discord bot and include a link to add the bot to a server. If you want to host your Discord bot on CSUNIX or some other server, go for it, but it’s not necessary as long as you hand in the code so that the instructor can run it themselves.

HANDING IN You should place all the following into a single project folder, then zip it up and hand it in on Canvas.

Paper For Above Instructions

The development of an FAQ Bot, particularly through the phases of this project, aims to enhance user interaction with artificial intelligence while providing accurate and insightful responses. The FAQ Bot operates through crucial phases: Phase 1 focuses on constructing a robust foundational bot, Phase 2 enhances conversational capabilities using linguistic tools, and Phase 3 integrates the bot into a social platform, namely Discord.

In Phase 1, the implementation of the basic FAQ Bot involves designing a knowledge domain populated with 20 question-answer pairs. This dataset can be curated from extensive resources like Wikipedia, ensuring that information is accurate and well-referenced. The selection of questions must be reflective of varied user inquiries to provide a comprehensive service. For example, if the bot is designed to answer queries regarding health information, pairs might include questions such as, "What is diabetes?" paired with an answer distilled from verified medical literature.

Once the foundational knowledge is set, the next step is to generalize the dataset by crafting multiple potential queries for each answer. This step serves to enrich the user experience by acknowledging the different ways individuals might ask for the same information, thus increasing the likelihood of successful query matches.

Creating fuzzy regular expressions is a crucial part of developing an FAQ Bot that accurately determines user intent amidst typographic errors or varied phrasing. Employing patterns that tolerate a manageable number of typos ensures that the bot remains user-friendly and accessible. Regular expressions should not only identify the phrases but also capture underlying meanings. It is beneficial to use libraries like `re` in Python to assist with this process.

In coding the bot, proper file handling becomes essential. Text files should be utilized to store the questions, answers, and corresponding regex patterns efficiently. This enables dynamic loading of data, enhancing the bot's functionality without the need for constant coding adjustments. Through user utterances, the bot will implement a matching algorithm to determine the best-fitting answer based on the constructed regex patterns.

Additional features must be incorporated to increase user engagement. Ideally, the bot should recognize greetings and farewells, providing a personable touch to the interaction. If the bot fails to comprehend a user inquiry, a polite message should acknowledge this shortfall. Furthermore, rigorous testing of the bot ensures reliability and user satisfaction. This includes soliciting feedback from test users to identify and rectify nuances in user interactions.

Phase 2 shifts the focus towards transforming the bot into a more dynamic interlocutor. By incorporating linguistic knowledge from tools such as spaCy, the bot can exhibit chattier responses when user intent is unclear. The use of Named Entity Recognition (NER) can drive decisions for fallback responses. For instance, if a user asks about a specific organization, the bot can acknowledge its limits by responding, "Sorry, I don’t know. I don’t work for [Entity]." This approach personalizes the interaction and retains user engagement even when the bot lacks specific knowledge.

Moreover, classifying the intent of user utterances facilitates more engaging responses. By analyzing the grammatical structure of questions, commands, or statements, the bot can adjust its reply accordingly, boosting user experience. For example, a question might evoke an apologetic response acknowledging ignorance, while a command might elicit a more active refusal indicating inability to perform the action.

Building upon the foundations of these phases, Phase 3 entails transitioning the bot into a Discord environment. This integration provides versatility and accessibility, allowing users to interact with the bot in popular social contexts. Code modifications may be necessary to ensure full functionality on the Discord platform, but these adjustments will largely build upon the Python code established in earlier phases.

To submit the project successfully, all components must be neatly packaged into a folder, accompanied by essential text files detailing the various phases of development. Documenting the testing procedures, anticipated user interactions, and special features will play a critical role in presenting a coherent understanding of what the bot is capable of achieving.

In the end, the success of the FAQ Bot Plus project lies in its ability to provide thoughtful responses while engaging users in a meaningful dialogue. By leveraging linguistic resources and maintaining a user-focused approach throughout development, the bot can successfully navigate the challenges presented by varied user intents and inquiries.

References

• Vajjala, S., & Meurers, D. (2019). Practical Natural Language Processing. O'Reilly Media.
• SpaCy Documentation. (n.d.). Retrieved from https://spacy.io/
• Amazone. (n.d.). Amazon Machine Learning. Retrieved from https://aws.amazon.com/machine-learning/
• Chomsky, N. (1957). Syntactic Structures. Mouton de Gruyter.
• Manning, C. D., & Schütze, H. (1999). Foundations of Statistical Natural Language Processing. MIT Press.
• Jurafsky, D., & Martin, J. H. (2009). Speech and Language Processing. Pearson Prentice Hall.
• Michaelis, L. A. (2003). Contextualization and the Socio-Cognitive Model. In Cognitive Linguistics: Foundations and Scope (pp. 265-290). Mouton de Gruyter.
• Mitkov, R. (2003). The Oxford Handbook of Computational Linguistics. Oxford University Press.
• Bird, S., Klein, E., & Loper, E. (2009). Natural Language Processing with Python. O'Reilly Media.
• Python Software Foundation. (n.d.). Python Documentation. Retrieved from https://docs.python.org/