Papers by Tomoko Ohkuma
CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding (D19-58)
Copied to clipboard
| Challenge: | In-domain datasets are used to train and validate our model, and other out-of-domain data are used for validation. |
| Approach: | They propose a model which uses cross-task learning with expert representation for the generalization of reading and understanding. |
| Outcome: | The proposed model achieved an average F1 score of 66.1 % in the out-of-domain setting, which is a 4.3 percentage point improvement over the official BERT baseline model. |
Reinforcement Learning with Imbalanced Dataset for Data-to-Text Medical Report Generation (2020.findings-emnlp)
Copied to clipboard
Toru Nishino, Ryota Ozaki, Yohei Momoki, Tomoki Taniguchi, Ryuji Kano, Norihisa Nakano, Yuki Tagawa, Motoki Taniguchi, Tomoko Ohkuma, Keigo Nakamura
| Challenge: | Medical datasets are imbalanced in their finding labels because incidence rates differ among diseases . authors propose a novel reinforcement learning method with a reconstructor to improve clinical correctness of generated reports. |
| Approach: | They propose a reinforcement learning method with a reconstructor to improve clinical correctness of generated reports. |
| Outcome: | The proposed method improves clinical correctness of generated reports . it also trains the model on infrequent findings . |
Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning (D19-1)
Copied to clipboard
| Challenge: | Existing automated generation of articles' characteristics is inconsistent if they are generated individually. |
| Approach: | They propose a multi-task learning model with a shared encoder and multiple decoders for each task. |
| Outcome: | The proposed model generates more consistent headlines, key phrases and categories . it outperforms baseline model on the ROUGE scores and generates fluent headlines . |
Harnessing Popularity in Social Media for Extractive Summarization of Online Conversations (D18-1)
Copied to clipboard
| Challenge: | Existing methods for summarizing online conversations require large amounts of training data. |
| Approach: | They propose a disjunctive model that computes the contribution of content and context separately. |
| Outcome: | The proposed model outperforms baseline models which use popularity as informativeness measure. |
Integrating Tree Structures and Graph Structures with Neural Networks to Classify Discussion Discourse Acts (C18-1)
Copied to clipboard
| Challenge: | Existing models that analyze textual contents and discussion structures require understanding of textual content and discussion structure. |
| Approach: | They propose a model that integrates discussion structures with neural networks to classify discourse acts. |
| Outcome: | The proposed model improves accuracy and FB1 score by 1.5% compared to the previous best model. |
Relation Prediction for Unseen-Entities Using Entity-Word Graphs (D19-53)
Copied to clipboard
Yuki Tagawa, Motoki Taniguchi, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma, Takayuki Yamamoto, Keiichi Nemoto
| Challenge: | Knowledge graphs (KGs) are incomplete and miss some information. |
| Approach: | They propose to learn entity representations via a graph structure that uses Seen-entities, Unseen-Entities and words as nodes created from the descriptions of all entities. |
| Outcome: | The proposed method improves relation prediction for the entity pairs containing Unseen-entities. |
Identifying Implicit Quotes for Unsupervised Extractive Summarization of Conversations (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods of unsupervised summarization are lacking. |
| Approach: | They propose an unsupervised unsupervised extractive neural summarization model that extracts quotes as summaries from conversational texts. |
| Outcome: | The proposed model can extract quoted sentences as summaries from two email and social media datasets. |
Quantifying Appropriateness of Summarization Data for Curriculum Learning (2021.eacl-main)
Copied to clipboard
| Challenge: | Summarization datasets are noisy, and summaries often do not reflect what is written in the source texts. |
| Approach: | They propose a method of curriculum learning to train summarization models from noisy data. |
| Outcome: | The proposed method improves the performance of pretrained and non-pretrained models on human evaluation. |
A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations (2020.coling-main)
Copied to clipboard
| Challenge: | e-mail conversations have domain-agnostic and two-level dialogue act annotations . et al. (2017): a better understanding of asynchronous conversations. |
| Approach: | They present a large-scale corpus of e-mail conversations with domain-agnostic and two-level dialogue act annotations . they use ISO standard 24617-2 as the annotation scheme to annotate over 6,000 messages and 35,000 sentences . |
| Outcome: | The proposed model outperforms other neural networks but falls short of human performance. |
Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement (2026.acl-industry)
Copied to clipboard
Wataru Hirota, Tomoki Taniguchi, Tomoko Ohkuma, Kosuke Takahashi, Takahiro Omi, Kosuke Arima, Takuto Asakura, Chung-Chi Chen, Tatsuya Ishigaki
| Challenge: | Large language models (LLMs) make it easy to generate large numbers of product ideas. |
| Approach: | They propose to use a dataset of 3,000 individual scores across 300 patent-grounded product ideas to assess whether an automatic judge approximates an aggregate consensus. |
| Outcome: | The proposed model evaluators disagree on fine-grained ordinal scores, suggesting structured heterogeneity rather than random noise. |
Factual Accuracy is not Enough: Planning Consistent Description Order for Radiology Report Generation (2022.emnlp-main)
Copied to clipboard
Toru Nishino, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma, Yuki Suzuki, Shoji Kido, Noriyuki Tomiyama
| Challenge: | Radiology report generation systems can reduce the workload of radiologists by automatically describing the findings in medical images. |
| Approach: | They propose a planning-based radiology report generation system that generates the overall structure of reports as “plans” prior to generating reports that are accurate and consistent in order. |
| Outcome: | The proposed system improves the content order score by 5.1 pt in time series critical scenarios and the clinical factual accuracy F-score by 9.1 p.t. in time-series irrelevant scenarios. |