Author name cluster

Paul Buitelaar

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

AAAI Conference 2026 Conference Paper

EvalQAG: A Framework for Automatic Complex QA Generation and a Benchmark QA Dataset for Policy Documents

Kirtan Brijeshbhai Soni
Krish Rupapara
Arpit Rana
Ghanshyam Verma
Paul Buitelaar

Accelerating research in renewable energy policy is critical for addressing climate change and enabling informed decision-making. Question answering (QA) over public policy documents presents unique challenges due to their legal structure, conditional dependencies, and domain-specific vocabulary. In this paper, we introduce EvalQAG, a framework for generating high-quality QA pairs from renewable energy policy documents. EvalQAG combines structured prompts, retrieval-augmented inputs, and multi-stage evaluation using large language models (LLMs) to support accurate and diverse QA generation. Using this framework, we construct REPolicyQA, a domain-specific QA dataset comprising approximately 160,000 QA pairs from over 1,000 U.S. renewable energy policy documents. The dataset covers five policy-relevant question types: Yes/No, Yes/No with Conditions, Factual, Legal Obligation, and Descriptive, which capture a wide range of reasoning patterns grounded in regulatory texts. We evaluate multiple QA models and uncover significant performance gaps, particularly in legal reasoning and conditional inference, highlighting major shortcomings in current systems. Our results establish EvalQAG as a generalizable QA generation pipeline for policy texts and position REPolicyQA as a new benchmark for advancing QA research in policy and regulatory domains. We believe this work can foster impactful research in the renewable energy sector, particularly by enabling more robust and explainable QA systems for legal and condition-heavy regulatory documents.

PDF Details DOI

AAAI Conference 2018 Conference Paper

Few Shot Transfer Learning BetweenWord Relatedness and Similarity Tasks Using A Gated Recurrent Siamese Network

James O' Neill
Paul Buitelaar

Word similarity and word relatedness are fundamental to natural language processing and more generally, understanding how humans relate concepts in semantic memory. A growing number of datasets are being proposed as evaluation benchmarks, however, the heterogeneity and focus of each respective dataset makes it difﬁcult to draw plausible conclusions as to how a uniﬁed semantic model would perform. Additionally, we want to identify the transferability of knowledge obtained from one task to another, within the same domain and across domains. Hence, this paper ﬁrst presents an evaluation and comparison of eight chosen datasets tested using the best performing regression models. As a baseline, we present regression models that incorporate both lexical features and word embeddings to produce consistent and competitive results compared to the state of the art. We present our main contribution, the best performing model across seven of the eight datasets - a Gated Recurrent Siamese Network that learns relationships between lexical word deﬁnitions. A parameter transfer learning strategy is employed for the Siamese Network. Subsequently, we present a secondary contribution which is the best performing non-sequential model: an Inductive and Transductive Transfer Learning strategy for transferring decision trees within a Random Forest to a target task that is learned from only few instances. The method involves measuring semantic distance between hidden factored matrix representations of decision tree traversal matrices.

PDF Details

ECAI Conference 2008 Conference Paper

Multilingual Evidence Improves Clustering-based Taxonomy Extraction

Hans Hjelm
Paul Buitelaar

We present a system for taxonomy extraction, aimed at providing a taxonomic backbone in an ontology learning environment. We follow previous research in using hierarchical clustering based on distributional similarity of the terms in texts. We show that basing the clustering on a comparable corpus in four languages gives a considerable improvement in accuracy compared to using only the monolingual English texts. We also show that hierarchical k-means clustering increases the similarity to the original taxonomy, when compared with a bottom-up agglomerative clustering approach.

Details