Takumi Takahashi


2023

pdf bib
Few-shot Named Entity Recognition with Supported and Dependent Label Representations
Yasuhide Miura | Takumi Takahashi
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

2021

pdf bib
Quantifying Appropriateness of Summarization Data for Curriculum Learning
Ryuji Kano | Takumi Takahashi | Toru Nishino | Motoki Taniguchi | Tomoki Taniguchi | Tomoko Ohkuma
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Much research has reported the training data of summarization models are noisy; summaries often do not reflect what is written in the source texts. We propose an effective method of curriculum learning to train summarization models from such noisy data. Curriculum learning is used to train sequence-to-sequence models with noisy data. In translation tasks, previous research quantified noise of the training data using two models trained with noisy and clean corpora. Because such corpora do not exist in summarization fields, we propose a model that can quantify noise from a single noisy corpus. We conduct experiments on three summarization models; one pretrained model and two non-pretrained models, and verify our method improves the performance. Furthermore, we analyze how different curricula affect the performance of pretrained and non-pretrained summarization models. Our result on human evaluation also shows our method improves the performance of summarization models.

2019

pdf bib
CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding
Takumi Takahashi | Motoki Taniguchi | Tomoki Taniguchi | Tomoko Ohkuma
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

This paper describes our model for the reading comprehension task of the MRQA shared task. We propose CLER, which stands for Cross-task Learning with Expert Representation for the generalization of reading and understanding. To generalize its capabilities, the proposed model is composed of three key ideas: multi-task learning, mixture of experts, and ensemble. In-domain datasets are used to train and validate our model, and other out-of-domain datasets are used to validate the generalization of our model’s performances. In a submission run result, 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.

2018

pdf bib
Integrating Entity Linking and Evidence Ranking for Fact Extraction and Verification
Motoki Taniguchi | Tomoki Taniguchi | Takumi Takahashi | Yasuhide Miura | Tomoko Ohkuma
Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)

We describe here our system and results on the FEVER shared task. We prepared a pipeline system which composes of a document selection, a sentence retrieval, and a recognizing textual entailment (RTE) components. A simple entity linking approach with text match is used as the document selection component, this component identifies relevant documents for a given claim by using mentioned entities as clues. The sentence retrieval component selects relevant sentences as candidate evidence from the documents based on TF-IDF. Finally, the RTE component selects evidence sentences by ranking the sentences and classifies the claim simultaneously. The experimental results show that our system achieved the FEVER score of 0.4016 and outperformed the official baseline system.