Skip to content

Commit f0a95fe

Browse files
added posts for EMNLP and COLING
1 parent 7525735 commit f0a95fe

File tree

2 files changed

+75
-0
lines changed

2 files changed

+75
-0
lines changed

content/post/coling2025/index.md

+41
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,41 @@
1+
---
2+
# Documentation: https://wowchemy.com/docs/managing-content/
3+
4+
title: "One paper by DFKI-NLP authors accepted to COLING 2025"
5+
subtitle: ""
6+
summary: ""
7+
authors: []
8+
tags: []
9+
categories: []
10+
date: 2025-02-03T09:24:01+02:00
11+
lastmod: 2025-02-03T09:24:01+02:00
12+
featured: false
13+
draft: false
14+
15+
# Featured image
16+
# To use, add an image named `featured.jpg/png` to your page's folder.
17+
# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
18+
image:
19+
caption: ""
20+
focal_point: ""
21+
preview_only: false
22+
23+
# Projects (optional).
24+
# Associate this post with one or more of your projects.
25+
# Simply enter your project's folder or file name without extension.
26+
# E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`.
27+
# Otherwise, set `projects = []`.
28+
projects: []
29+
---
30+
31+
One paper originating from research in the TRAILS project has been accepted to the Main Track at the 31st International Conference on Computational Linguistics 2025 (COLING 2025). In the paper, we present CROSS-REFINE, a generator-critic framework that enhances natural language explanations by refining initial outputs using feedback from a second LLM, outperforming SELF-REFINE and working effectively even with less powerful models.
32+
33+
{{< cite page="/publication/wang-etal-2025-cross" view="4" >}}
34+
35+
36+
37+
38+
39+
40+
41+

content/post/emnlp2024/index.md

+34
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
---
2+
# Documentation: https://wowchemy.com/docs/managing-content/
3+
4+
title: "One paper by DFKI-NLP authors accepted to EMNLP 2024"
5+
subtitle: ""
6+
summary: ""
7+
authors: []
8+
tags: []
9+
categories: []
10+
date: 2024-11-10T09:24:01+02:00
11+
lastmod: 2024-11-10T09:24:01+02:00
12+
featured: false
13+
draft: false
14+
15+
# Featured image
16+
# To use, add an image named `featured.jpg/png` to your page's folder.
17+
# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
18+
image:
19+
caption: ""
20+
focal_point: ""
21+
preview_only: false
22+
23+
# Projects (optional).
24+
# Associate this post with one or more of your projects.
25+
# Simply enter your project's folder or file name without extension.
26+
# E.g. `projects = ["internal-project"]` references `content/project/deep-learning/index.md`.
27+
# Otherwise, set `projects = []`.
28+
projects: []
29+
---
30+
31+
One paper from researchers in the DFKI-NLP group has been accepted as a Findings paper at the [2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)](https://2024.emnlp.org/). EMNLP will take place November 12-16 in Miami, Florida. The paper presents CoXQL, a dataset for user intent recognition for conversational XAI systems, covering 31 intents, seven of which require filling multiple slots. The paper also presents an improved parsing approach for intent recognition and slot filling on this dataset, which is evaluated using different LLMs.
32+
33+
{{< cite page="/publication/wang-etal-2024-coxql" view="4" >}}
34+

0 commit comments

Comments
 (0)