activity
20202026
most citedA Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT

6 citations · 12 across the 7 of their papers we have counts for

collaborators

9 papers

cs.AI2026

Constraint-Based Analysis of Reasoning Shortcuts in Neurosymbolic Learning

Akihiro Takemura, Katsumi Inoue, Masaaki Nishino

Neurosymbolic systems can satisfy logical constraints during learning without achieving the intended concept-label correspondence; this is a problem known as reasoning shortcuts. W…

cs.LG2022

Generalization Analysis on Learning with a Concurrent Verifier

Masaaki Nishino, Kengo Nakamura, Norihito Yasuda

Machine learning technologies have been used in a wide range of practical systems. In practical situations, it is natural to expect the input-output pairs of a machine learning mod…

cs.DM20212 cited

Solving Rep-tile by Computers: Performance of Solvers and Analyses of Solutions

Mutsunori Banbara, Kenji Hashimoto, Takashi Horiyama +7

A rep-tile is a polygon that can be dissected into smaller copies (of the same size) of the original polygon. A polyomino is a polygon that is formed by joining one or more unit sq…

cs.AI20213 cited

Differentiable Inductive Logic Programming for Structured Examples

Hikaru Shindo, Masaaki Nishino, Akihiro Yamamoto

The differentiable implementation of logic yields a seamless combination of symbolic reasoning and deep neural networks. Recent research, which has developed a differentiable frame…

cs.CL2020

Bilingual Text Extraction as Reading Comprehension

Katsuki Chousa, Masaaki Nagata, Masaaki Nishino

In this paper, we propose a method to extract bilingual texts automatically from noisy parallel corpora by framing the problem as a token-level span prediction, such as SQuAD-style…

cs.CL20206 cited

A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT

Masaaki Nagata, Chousa Katsuki, Masaaki Nishino

We present a novel supervised word alignment method based on cross-language span prediction. We first formalize a word alignment problem as a collection of independent predictions…