most citedInstance-Based Learning of Span Representations: A Case Study through Named Entity Recognition

4 citations · 8 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CL20202 cited

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…

cs.CL2020

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…

cs.CL2020

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…

cs.CL20204 cited

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…

cs.CL20202 cited

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…

cs.CL2018

Suspicious News Detection Using Micro Blog Text

Tsubasa Tagami, Hiroki Ouchi, Hiroki Asano +9

We present a new task, suspicious news detection using micro blog text. This task aims to support human experts to detect suspicious news articles to be verified, which is costly b…