Taro Watanabe

User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization

2021 · arXiv (Cornell University)

Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT). To evaluate and compare different MA/LN systems, we have constructed a publicly available Japanese UGT corpus. Our corpus comprises …

Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding

2021

For knowledge graph completion, two major types of prediction models exist: one based on graph embeddings, and the other based on relation path rule induction. They have different advantages and disadvantages. To take advantage of …

Model-based Subsampling for Knowledge Graph Completion

2023

Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: …

mbrs: A Library for Minimum Bayes Risk Decoding

2024 · arXiv (Cornell University)

Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than …

Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection

2018

Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet. Denoising is concerned with a different type of data quality …