Papers by Masatoshi Tsuchiya
Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment (L18-1)
Copied to clipboard
| Challenge: | a method to improve the quality of training data is needed . annotation errors of dialog act corpus mislead learning results of Bayesian network . |
| Approach: | They propose to introduce a null hypothesis for predictability of textual entailment labels and test it using a Naive Bayes model. |
| Outcome: | The proposed method does not reject the null hypothesis, but it improves on the existing models. |
Developing a Dataset of Overridden Information in Wikipedia (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to detect information overridden by the Web are not accurate and require a user's perspective to make the decision. |
| Approach: | They propose a task to detect whether a reference sentence has overridden a target sentence by using sentence pairs from the difference between two versions of Wikipedia. |
| Outcome: | The proposed task is formalized as a binary classification problem to determine whether a reference sentence has overridden a target sentence. |
Developing Dataset of Japanese Slot Filling Quizzes Designed for Evaluation of Machine Reading Comprehension (2020.lrec-1)
Copied to clipboard
| Challenge: | a novel dataset of slot filling quizzes is developed for evaluation of machine reading comprehension . the dataset consists of quizzed characters of target books as slots . |
| Approach: | They develop a Japanese dataset of slot filling quizzes for machine reading comprehension . they define each quiz as a 4-tuple: context passage, query holding a slot, answer character and set of possible answer characters . |
| Outcome: | The proposed dataset includes a 4-tuple quiz, a context passage, q and a query . the q&a is performed on characters of target books, which play important roles in narrative texts . |