MFAQ: a Multilingual FAQ Dataset

Bruyn, Maxime De; Lotfi, Ehsan; Buhmann, Jeska; Daelemans, Walter

doi:10.18653/v1/2021.mrqa-1.1

Cited by 9 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For Korean, we select a question-answering corpus from AI Hub, 2 which includes civil complaints and replies from public organizations. For Turkish, we identify FAQ (i.e., Frequently Asked Questions) and CQA (i.e., Community Question Answering) datasets from MFAQ (De Bruyn et al, 2021). All of these corpora are used in accordance with their licenses.…”

Section: Distant Supervision For New Languagesmentioning

confidence: 99%

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages

Wang,

Hossain,

Mathur

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

Yes-no questions expect a yes or no for an answer, but people often skip polar keywords.Instead, they answer with long explanations that must be interpreted. In this paper, we focus on this challenging problem and release new benchmarks in eight languages. We present a distant supervision approach to collect training data. We also demonstrate that direct answers (i.e., with polar keywords) are useful to train models to interpret indirect answers (i.e., without polar keywords). Experimental results demonstrate that monolingual fine-tuning is beneficial if training data can be obtained via distant supervision for the language of interest (5 languages). Additionally, we show that cross-lingual fine-tuning is always beneficial (8 languages).

show abstract

Section: Distant Supervision For New Languagesmentioning

confidence: 99%

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages

Wang,

Hossain,

Mathur

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

show abstract

“…Notably, other studies [41][42][43] have explored the possibility of knowledge selection from a small set of knowledge, without employing a retrieval step or search engine, as was performed in this study. It is worth mentioning that the utilization of search engines for machine translation tasks has been shown to produce effective results [44].…”

Section: Related Workmentioning

confidence: 99%

Internet Wizard for Enhancing Open-Domain Question-Answering Chatbot Knowledge Base in Education

Mzwri

Turcsányi-Szabó

2023

Applied Sciences

View full text Add to dashboard Cite

Chatbots have gained widespread popularity for their task automation capabilities and consistent availability in various domains, including education. However, their ability to adapt to the continuously evolving and dynamic nature of knowledge is limited. This research investigates the implementation of an internet wizard to enhance the knowledge base of an open-domain question-answering chatbot. The proposed approach leverages search engines, particularly Google, and its features, including feature snippets, knowledge graph, and organic search, in conjunction with data science and natural language models. This mechanism empowers the chatbot to dynamically access the extensive and up-to-date knowledge available on the web, enabling the provision of real time and pertinent answers to user queries sourced from web documents. A pilot study in a higher education context evaluated the chatbot’s mechanism and features, confirming its proficiency in generating responses across a broad range of educational and non-educational topics. Positive feedback and high user satisfaction validate these findings. Notably, the chatbot’s dynamic feature of retrieving related or follow-up questions from search engines significantly enhances student engagement and facilitates exploration of supplementary information beyond the curriculum.

show abstract

“…In other words, these models are trained based on the data collected at the time of their creation, and the knowledge acquired is static and not adaptive to changes. Other studies [39][40][41] have explored the possibility of knowledge selection from a small set of knowledge, without employing a retrieval step or search engine, as was done in this study. Notably, using search engines for machine translation tasks has been shown to produce effective results [42].…”

Section: Introductionmentioning

confidence: 99%

Internet Wizard for Enhancing Open Domain Question Answering Chatbot Knowledge-base in Education

Mzwri¹,

Turcsányi-Szabó²

2023

Preprint

View full text Add to dashboard Cite

Chatbots have gained widespread popularity for their task automation capabilities and consistent availability in various domains, including education. However, their ability to adapt to the continuously evolving and dynamic nature of knowledge is limited. This research investigates the implementation of an internet wizard to enhance the knowledge base of an open-domain question-answering chatbot. The proposed approach leverages search engines, particularly Google, and its features, including feature snippets, knowledge graph, and organic search, in conjunction with data science and natural language models. This mechanism empowers the chatbot to dynamically access the extensive and up-to-date knowledge available on the web, enabling the provision of real-time and pertinent answers to user queries sourced from web documents. A pilot study in a higher education context evaluated the chatbot's mechanism and features, confirming its proficiency in generating responses across a broad range of educational and non-educational topics. Positive feedback and high user satisfaction validate these findings. Notably, the chatbot's dynamic feature of retrieving related or follow-up questions from search engines significantly enhances student engagement and facilitates exploration of supplementary information beyond the curriculum.

show abstract

MFAQ: a Multilingual FAQ Dataset

Cited by 9 publications

References 22 publications

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages

Internet Wizard for Enhancing Open-Domain Question-Answering Chatbot Knowledge Base in Education

Internet Wizard for Enhancing Open Domain Question Answering Chatbot Knowledge-base in Education

Contact Info

Product

Resources

About