paper-with-me

홈 › Papers

Towards an open-domain chatbot for language practice

2022-07-01 · NAACL (BEA) 2022 7 · Gladys Tyen, Mark Brenchley, Andrew Caines, Paula Buttery

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.

📄 PDF Abstract BibTeX

Code (1)

whgtyen/controllablecomplexitychatbot 공식 구현 pytorch

Tasks

ChatbotDialogue GenerationRe-Ranking

Similar Papers 제목 키워드 기반

Evaluating Chatbots to Promote Users' Trust -- Practices and Open Problems

2023-09-09 · Biplav Srivastava, Kausik Lakkaraju, Tarmo Koppel, Vignesh Narayanan 외

Chatbots, the common moniker for collaborative assistants, are Artificial Intelligence (AI) software that enables people to naturally interact with them to get tasks done. Although chatbots have been studied since the da…

ChatbotLanguage ModelingLanguage ModellingLarge Language Model

Large Language Models in Fire Engineering: An Examination of Technical Questions Against Domain Knowledge

2024-03-04 · Haley Hostetter, M. Z. Naser, Xinyan Huang, John Gales

This communication presents preliminary findings from comparing two recent chatbots, OpenAI's ChatGPT and Google's Bard, in the context of fire engineering by evaluating their responses in handling fire safety related qu…

Chatbot

ChatEval: A Tool for Chatbot Evaluation

2019-06-01 · NAACL 2019 6 · Jo{\~a}o Sedoc, Daphne Ippolito, Arun Kirubarajan, Jai Thirani 외

Open-domain dialog systems (i.e. chatbots) are difficult to evaluate. The current best practice for analyzing and comparing these dialog systems is the use of human judgments. However, the lack of standardization in eval…

ChatbotOpen-Domain Dialog

Prompted LLMs as Chatbot Modules for Long Open-domain Conversation

2023-05-08 · Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos 외

In this paper, we propose MPC (Modular Prompted Chatbot), a new approach for creating high-quality conversational agents without the need for fine-tuning. Our method utilizes pre-trained large language models (LLMs) as i…

Chatbot

The Open-domain Paradox for Chatbots: Common Ground as the Basis for Human-like Dialogue

2023-03-21 · Gabriel Skantze, A. Seza Doğruöz

There is a surge in interest in the development of open-domain chatbots, driven by the recent advancements of large language models. The "openness" of the dialogue is expected to be maximized by providing minimal informa…

Position