Skip to content

Commit 2d2e9e5

Browse files
cowolffcowolff
committed
feat: Added talks
1 parent b034dde commit 2d2e9e5

File tree

4 files changed

+79
-0
lines changed

4 files changed

+79
-0
lines changed

‎_pages/seminar_talks/202600.md‎

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
<h4><a href="https://www.daniel-gomm.com/" target="blank">Daniel Gomm</a>, CWI & University of Amsterdam</h4>
2+
3+
23rd January, 4:00pm, room L302, CWI, Amsterdam Science Park, in-person talk and streamed through Zoom
4+
5+
<details><summary>Unfold Bio</summary>
6+
<p>
7+
Daniel Gomm is a PhD student at the Table Representation Learning Lab within the Database Architectures Group at Centrum Wiskunde & Informatica (CWI) and the Information Retrieval Lab at the University of Amsterdam. His research lies at the intersection of generative AI, information retrieval, and structured data, with the goal of democratizing access to insights from tables, relational databases, and spreadsheets by contextualizing generative methods in structured data settings. He brings an interdisciplinary background spanning engineering, economics, and computer science, with experience across industry, academia, and policy.
8+
</p>
9+
</details>
10+
<br>
11+
<b>"Are We Asking the Right Questions? On Ambiguity in Natural Language Queries for Tabular Data Analysis"</b>
12+
<br>
13+
14+
<p>
15+
Natural language interfaces for tabular data analysis must contend with ambiguity in user queries. Rather than treating ambiguity as a flaw to be eliminated, this talk argues that ambiguity is often an intentional and productive aspect of user–system interaction.
16+
<br>
17+
Daniel presents a principled framework that conceptualizes analytical queries through the lens of cooperative interaction, distinguishing between unambiguous queries, cooperative but underspecified queries that systems can reasonably resolve, and uncooperative queries that lack sufficient information for any actionable interpretation. The framework is grounded in linguistic theory and formalizes how responsibility for query specification is shared between user and system.
18+
<br>
19+
Applying this framework, the talk analyzes queries from 15 widely used benchmarks for tabular question answering, text-to-SQL, and data analysis. The results reveal that current datasets conflate different query types, undermining meaningful evaluation of both execution accuracy and interpretation capabilities. The talk concludes with implications for designing more realistic benchmarks and for building tabular data systems that explicitly support cooperative grounding, selective inference, and iterative clarification.
20+
</p>
21+
22+
<p>
23+
<b>Join the seminar remotely via Zoom:</b> <a href="https://cwi-nl-zoom.zoom.us/j/86289891036?pwd=5DGnyc3jpaucipnIjpEVa9wdGEISM1.1" target="_blank">https://cwi-nl-zoom.zoom.us/j/86289891036?pwd=5DGnyc3jpaucipnIjpEVa9wdGEISM1.1</a>
24+
</p>

‎_pages/seminar_talks/202601.md‎

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
<h4><a href="https://cornelius-wolff.de/" target="blank">Cornelius Wolff</a>, CWI & University of Amsterdam</h4>
2+
3+
23rd January, 4:15pm, room L302, CWI, Amsterdam Science Park, in-person talk and streamed through Zoom
4+
5+
<details><summary>Unfold Bio</summary>
6+
<p>
7+
Cornelius Wolff is a PhD researcher at the TRL Lab at Centrum Wiskunde & Informatica (CWI) and the University of Amsterdam, supervised by Madelon Hulsebos and Maarten de Rijke. His main focus is the autonomous retrieval of relevant insight from structured data in realistic settings, with an emphasis on scalable and interpretable AI systems for databases and tabular data. He is also interested in text-to-SQL, small and efficient language models and in-context learning beyond natural language.
8+
</p>
9+
</details>
10+
<br>
11+
<b>"SQALE: Scaling Text-to-SQL with Realistic Database Schemas"</b>
12+
<br>
13+
14+
<p>
15+
Natural language interfaces for databases rely on text-to-SQL models that can translate user questions into executable SQL queries. While recent advances in large language models have significantly improved performance, progress remains constrained by the limited scale, diversity, and realism of available training data.
16+
<br>
17+
In this talk, Cornelius presents <i>SQALE</i>, a large-scale semi-synthetic text-to-SQL dataset grounded in real-world database schemas. SQALE comprises over 517,000 validated (question, schema, query) triples built on 135,000+ relational schemas derived from SchemaPile. The dataset is constructed using a principled generation pipeline that combines schema extension, natural language question synthesis, and SQL generation with execution-based validation.
18+
<br>
19+
The talk will discuss the design criteria behind SQALE, its statistical properties in comparison to existing benchmarks such as Spider 2.0 and BIRD, and how SQALE enables more realistic training and evaluation of text-to-SQL models.
20+
</p>
21+
22+
<p>
23+
<b>Join the seminar remotely via Zoom:</b> <a href="https://cwi-nl-zoom.zoom.us/j/86289891036?pwd=5DGnyc3jpaucipnIjpEVa9wdGEISM1.1" target="_blank">https://cwi-nl-zoom.zoom.us/j/86289891036?pwd=5DGnyc3jpaucipnIjpEVa9wdGEISM1.1</a>
24+
</p>

‎_pages/seminar_talks/202602.md‎

Lines changed: 22 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,22 @@
1+
<h4><a href="https://www.linkedin.com/in/erkan-karabulut/" target="blank">Erkan Karabulut</a>, University of Amsterdam</h4>
2+
3+
23rd January, 4:30pm, room L302, CWI, Amsterdam Science Park, in-person talk and streamed through Zoom
4+
5+
<details><summary>Unfold Bio</summary>
6+
<p>
7+
Erkan is a PhD student at the INtelligent Data Engineering Lab (INDElab), University of Amsterdam. His research focuses on knowledge discovery and interpretable inference via rule learning on tabular data, including sensor data, with and without structured background knowledge (knowledge graphs) or prior knowledge from foundation models.
8+
</p>
9+
</details>
10+
<br>
11+
<b>"Scalable Knowledge Discovery from Tabular Data"</b>
12+
<br>
13+
14+
<p>
15+
Discovering patterns from data in human-understandable forms is a valuable task for both knowledge discovery and interpretable inference. A prominent method is Association Rule Mining (ARM), which identifies patterns in the form of logical rules describing relationships between data attributes. Popular ARM methods, however, rely on algorithmic or optimization-based solutions that struggle to scale to high-dimensional datasets (i.e., tables with many columns) without effective search space reduction.
16+
<br>
17+
This talk introduces Aerial+, a novel ARM method that leverages neural networks’ ability to handle high-dimensional data to learn a concise set of prominent patterns from tabular datasets. Aerial+ has been evaluated on both digital twin datasets (sensor data enriched with semantics) and on generic tabular datasets, demonstrating its versatility across domains. In addition, Aerial+ can incorporate prior knowledge to enhance discovery: either from knowledge graphs (structured semantic information about a domain) or from tabular foundation models, large pre-trained neural networks that capture table semantics and support diverse downstream tasks.
18+
</p>
19+
20+
<p>
21+
<b>Join the seminar remotely via Zoom:</b> <a href="https://cwi-nl-zoom.zoom.us/j/86289891036?pwd=5DGnyc3jpaucipnIjpEVa9wdGEISM1.1" target="_blank">https://cwi-nl-zoom.zoom.us/j/86289891036?pwd=5DGnyc3jpaucipnIjpEVa9wdGEISM1.1</a>
22+
</p>

‎_pages/trl-seminar.md‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,15 @@ profiles:
99
- align: right
1010
content: seminar_talks/info.md
1111

12+
- align: right
13+
content: seminar_talks/202600.md
14+
15+
- align: right
16+
content: seminar_talks/202601.md
17+
18+
- align: right
19+
content: seminar_talks/202602.md
20+
1221
- align: right
1322
content: seminar_talks/past-talks.md
1423

0 commit comments

Comments
 (0)