Heinzerling Benjamin ＨＥＩＮＺＥＲＬＩＮＧＢＥＮＪＡＭＩＮ

Researcher Number	50846491
Other IDs
Affiliation (Current)	2025: 国立研究開発法人理化学研究所, 革新知能統合研究センター, 副チームディレクター
Affiliation (based on the past Project Information) *help	2022 – 2024: 国立研究開発法人理化学研究所, 革新知能統合研究センター, 副チームリーダー 2022: 国立研究開発法人理化学研究所, 革新知能統合研究センター, 研究員 2021: 国立研究開発法人理化学研究所, 革新知能統合研究センター, 特別研究員
Review Section/Research Field	Principal Investigator Basic Section 61030:Intelligent informatics-related Except Principal Investigator Medium-sized Section 61:Human informatics and related fields
Keywords	Principal Investigator NLP / grounding / numeric properties / world knowledge / language model / knowledge base / knowledge representation / explainability / interpretability / structured knowledge / Language models … More Except Principal Investigator … More 自然言語処理 / 論述学習支援 / 論理構造解析 / 論述診断 / 自然言語処理学 Less

Computational Modeling of Argumentation Understanding
- Principal Investigator
  
  乾健太郎
- Project Period (FY)
  2022 – 2026
- Research Category
  
  Grant-in-Aid for Scientific Research (A)
- Review Section
  
  Medium-sized Section 61:Human informatics and related fields
- Research Institution
  Tohoku University
Knowledge-Base-Grounded Language ModelsPrincipal Investigator
- Principal Investigator
  
  Heinzerling Benjamin
- Project Period (FY)
  2021 – 2023
- Research Category
  
  Grant-in-Aid for Early-Career Scientists
- Review Section
  
  Basic Section 61030:Intelligent informatics-related
- Research Institution
  Institute of Physical and Chemical Research

All 2024 2023 2022

All Journal Article Presentation

[Journal Article] Monotonic Representation of Numeric Properties in Language Models2024
- Author(s)
  Heinzerling Benjamin, Inui Kentaro
- Journal Title
  
  preprint
  
  Volume: -
- Open Access
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] Examining the effect of whitening on static and contextualized word embeddings2023
- Author(s)
  Sasaki Shota、Heinzerling Benjamin、Suzuki Jun、Inui Kentaro
- Journal Title
  
  Information Processing & Management
  
  Volume: 60 Issue: 3 Pages: 103272-103272
- DOI
  10.1016/j.ipm.2023.103272
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}2023
- Author(s)
  Kavumba Pride、Brassard Ana、Heinzerling Benjamin、Inui Kentaro
- Journal Title
  
  : Findings of the Association for Computational Linguistics: EACL 2023
  
  Volume: 1 Pages: 2165-2180
- DOI
  10.18653/v1/2023.findings-eacl.162
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] Can LMs Store and Retrieve 1-to-N Relational Knowledge?2023
- Author(s)
  Nagasawa Haruki、Heinzerling Benjamin、Kokuta Kazuma、Inui Kentaro
- Journal Title
  
  Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
  
  Volume: 4 Pages: 130-138
- DOI
  10.18653/v1/2023.acl-srw.22
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] Test-time Augmentation for Factual Probing2023
- Author(s)
  Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui
- Journal Title
  
  Findings of the Association for Computational Linguistics: EMNLP 2023
  
  Volume: 0 Pages: 3650-3661
- DOI
  10.18653/v1/2023.findings-emnlp.236
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-21K21343, KAKENHI-PROJECT-21K17814
[Journal Article] Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction2023
- Author(s)
  Qin Dai, Benjamin Heinzerling, Kentaro Inui
- Journal Title
  
  言語処理学会第29回年次大会発表論文集 (2023年3月)
  
  Volume: 1 Pages: 0-0
- Open Access
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] Transformer モデルのニューロンには局所的に概念についての知識がエンコードされている2022
- Author(s)
  有山知希, Benjamin Heinzerling, 乾健太郎
- Journal Title
  
  言語処理学会第28回年次大会発表論文集 (2022年3月)
  
  Volume: 0 Pages: 599-603
- Open Access
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] ニューラル言語モデルによる一対多関係知識の記憶と操作2022
- Author(s)
  松本悠太, 吉川将司, Benjamin Heinzerling, 乾健太郎
- Journal Title
  
  言語処理学会第28回年次大会発表論文集 (2022年3月)
  
  Volume: 0 Pages: 556-561
- Open Access
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction2022
- Author(s)
  Qin Dai, Benjamin Heinzerling, Kentaro Inui
- Journal Title
  
  Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
  
  Volume: 1 Pages: 0-0
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] ニューラル言語モデルによる一対多関係知識の記憶と操作2022
- Author(s)
  長澤春希, Benjamin Heinzerling, 乾健太郎
- Journal Title
  
  言語処理学会第28回年次大会発表論文集 (2022年3月)
  
  Volume: 0 Pages: 1203-1208
- Open Access
- Data Source
  KAKENHI-PROJECT-21K17814
[Journal Article] COPA-SSE: Semi-structured Explanations for Commonsense Reasoning2022
- Author(s)
  Ana Brassard, Benjamin Heinzerling, Pride Kavumba and Kentaro Inui
- Journal Title
  
  Proceedings of the 13th Language Resources and Evaluation Conference
  
  Volume: 0
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-21K17814
[Presentation] Geometric Locality of Entity Embeddings in Masked Language Models.2023
- Author(s)
  Masaki Sakata, Sho Yokoi, Benjamin Heinzerling, Kentaro Inui
- Organizer
  Non-archival submission for the ACL Student Research Workshop
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-22H00524

1. 乾健太郎 (60272689)

# of Collaborated Projects: 1 results

# of Collaborated Products: 1 results
2. 中川智皓 (70582336)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
3. 井之上直也 (80778605)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
4. 吉川将司 (80883470)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
5. 坂口慶祐

# of Collaborated Projects: 0 results

# of Collaborated Products: 1 results

Heinzerling Benjamin ＨＥＩＮＺＥＲＬＩＮＧ ＢＥＮＪＡＭＩＮ

Research Projects

Research Products

Co-Researchers

Computational Modeling of Argumentation Understanding

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Knowledge-Base-Grounded Language ModelsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

[Journal Article] Monotonic Representation of Numeric Properties in Language Models2024

Author(s)

Journal Title

Data Source

[Journal Article] Examining the effect of whitening on static and contextualized word embeddings2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Can LMs Store and Retrieve 1-to-N Relational Knowledge?2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Test-time Augmentation for Factual Probing2023

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction2023

Author(s)

Journal Title

Data Source

[Journal Article] Transformer モデルのニューロンには 局所的に概念についての知識がエンコードされている2022

Author(s)

Journal Title

Data Source

[Journal Article] ニューラル言語モデルによる一対多関係知識の記憶と操作2022

Author(s)

Journal Title

Data Source

[Journal Article] Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction2022

Author(s)

Journal Title

Data Source

[Journal Article] ニューラル言語モデルによる一対多関係知識の記憶と操作2022

Author(s)

Journal Title

Data Source

[Journal Article] COPA-SSE: Semi-structured Explanations for Commonsense Reasoning2022

Author(s)

Journal Title

Data Source

[Presentation] Geometric Locality of Entity Embeddings in Masked Language Models.2023

Author(s)

Organizer

Data Source

Heinzerling Benjamin ＨＥＩＮＺＥＲＬＩＮＧＢＥＮＪＡＭＩＮ

[Journal Article] Transformer モデルのニューロンには局所的に概念についての知識がエンコードされている2022