added RepL4NLP paper and fixed some bugs

Author: leonhardhennig

content/publication/anikina-etal-2025-reverse/index.md

@@ -1,23 +1,67 @@
 ---
-title: 'Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution'
-authors:
-- Tatiana Anikina
-- Arne Binder
-- David Harbecke
-- Stalin Varanasi
-- Leonhard Hennig
-- Simon Ostermann
-- Sebastian Möller
-- Josef van Genabith
-date: '2025-03-17'
-publication_types:
-- paper-conference
-publication: '*Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)*'
-publication_short: RepL4NLP 2025
-abstract: In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as usually done in probing), we explore the effectiveness of embeddings from multiple simple source tasks on a single target task. We select coreference resolution, a linguistically complex problem requiring contextual understanding, as focus target task, and test the usefulness of embeddings from comparably simpler tasks tasks such as paraphrase detection, named entity recognition, and relation extraction. Through systematic experiments, we evaluate the impact of individual and combined task embeddings. Our findings reveal that task embeddings vary significantly in utility for coreference resolution, with semantic similarity tasks (e.g., paraphrase detection) proving most beneficial. Additionally, representations from intermediate layers of fine-tuned models often outperform those from final layers. Combining embeddings from multiple tasks consistently improves performance, with attention-based aggregation yielding substantial gains. These insights shed light on relationships between task-specific representations and their adaptability to complex downstream tasks, encouraging further exploration of embedding-level task transfer.
-
-url_pdf: https://openreview.net/pdf?id=V4ssTPCogS
-links:
-- name: URL
-  url: https://openreview.net/forum?id=V4ssTPCogS
----
+# Documentation: https://wowchemy.com/docs/managing-content/
+
+title: "Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution"
+authors: ["Tatiana Anikina", "Arne Binder", "David Harbecke", "Stalin Varanasi", "Leonhard Hennig", "Simon Ostermann", "Sebastian Möller", "Josef van Genabith"]
+date: 2025-03-17T10:42:03+02:00
+doi: ""
+
+# Schedule page publish date (NOT publication's date).
+publishDate: 2025-03-17T10:33:03+02:00
+
+# Publication type.
+# Legend: 0 = Uncategorized; 1 = Conference paper; 2 = Journal article;# 3 = Preprint / Working Paper; 4 = Report; 5 = Book; 6 = Book section;# 7 = Thesis; 8 = Patent
+publication_types: ["1"]
+
+# Publication name and optional abbreviated publication name.
+publication: "Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)"
+publication_short: "Rep4NLP-2025"
+
+abstract: "In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as usually done in probing), we explore the effectiveness of embeddings from multiple simple source tasks on a single target task. We select coreference resolution, a linguistically complex problem requiring contextual understanding, as focus target task, and test the usefulness of embeddings from comparably simpler tasks tasks such as paraphrase detection, named entity recognition, and relation extraction. Through systematic experiments, we evaluate the impact of individual and combined task embeddings. Our findings reveal that task embeddings vary significantly in utility for coreference resolution, with semantic similarity tasks (e.g., paraphrase detection) proving most beneficial. Additionally, representations from intermediate layers of fine-tuned models often outperform those from final layers. Combining embeddings from multiple tasks consistently improves performance, with attention-based aggregation yielding substantial gains. These insights shed light on relationships between task-specific representations and their adaptability to complex downstream tasks, encouraging further exploration of embedding-level task transfer."
+
+# Summary. An optional shortened abstract.
+summary: ""
+
+tags: []
+categories: []
+featured: false
+
+# Custom links (optional).
+#   Uncomment and edit lines below to show custom links.
+# links:
+# - name: Follow
+#   url: https://twitter.com
+#   icon_pack: fab
+#   icon: twitter
+
+url_pdf: "https://openreview.net/pdf?id=V4ssTPCogS"
+url_code: ""
+url_dataset: ""
+url_poster:
+url_project:
+url_slides:
+url_source:
+url_video:
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder. 
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:  
+  caption: ""  
+  focal_point: ""  
+  preview_only: false
+
+# Associated Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `internal-project` references `content/project/internal-project/index.md`.
+#   Otherwise, set `projects: []`.
+projects: [TRAILS]
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides: "example"` references `content/slides/example/index.md`.
+#   Otherwise, set `slides: ""`.
+slides: ""
+---