4 citations · 23 across the 15 of their papers we have counts for
5 papers · 1 filter
An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution
Ryuto Konno, Yuichiroh Matsubayashi, Shun Kiyono +3
One critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation. We ad…
Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring
Farjana Sultana Mim, Naoya Inoue, Paul Reisert +2
Existing approaches for automated essay scoring and document representation learning typically rely on discourse parsers to incorporate discourse structure into text representation…
Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition
Takuma Kato, Kaori Abe, Hiroki Ouchi +3
In general, the labels used in sequence labeling consist of different types of elements. For example, IOB-format entity labels, such as B-Person and I-Person, can be decomposed int…
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi +4
Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for struc…
Evaluating Dialogue Generation Systems via Response Selection
Shiki Sato, Reina Akama, Hiroki Ouchi +2
Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation system…