An Answer Verbalization Dataset for Conversational Question Answerings over Knowledge Graphs
This work addresses the need for verbalized answers in real-world applications like voice assistants, but it is incremental as it builds upon an existing dataset.
The authors tackled the lack of verbalized answers in conversational question answering over knowledge graphs by extending an existing dataset with multiple paraphrased verbalized answers, achieving results with five sequence-to-sequence models that maintained grammatical correctness, though specific numerical performance metrics were not provided.
We introduce a new dataset for conversational question answering over Knowledge Graphs (KGs) with verbalized answers. Question answering over KGs is currently focused on answer generation for single-turn questions (KGQA) or multiple-tun conversational question answering (ConvQA). However, in a real-world scenario (e.g., voice assistants such as Siri, Alexa, and Google Assistant), users prefer verbalized answers. This paper contributes to the state-of-the-art by extending an existing ConvQA dataset with multiple paraphrased verbalized answers. We perform experiments with five sequence-to-sequence models on generating answer responses while maintaining grammatical correctness. We additionally perform an error analysis that details the rates of models' mispredictions in specified categories. Our proposed dataset extended with answer verbalization is publicly available with detailed documentation on its usage for wider utility.