Datasets on Phillip Schneiderhttps://philotron.github.io/datasets/Recent content in Datasets on Phillip SchneiderHugo -- 0.147.2enWed, 01 Jan 2025 00:00:00 +0000CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Boundinghttps://philotron.github.io/datasets/carmem/Wed, 01 Jan 2025 00:00:00 +0000https://philotron.github.io/datasets/carmem/This repository contains the CarMem dataset, dataset generation code, and experiment code for the COLING 2025 Industry Track paper on long-term memory in LLM voice assistants.Conversational Exploratory Search of Scholarly Publications Using Knowledge Graphshttps://philotron.github.io/datasets/cs_scholarly_kg/Tue, 01 Oct 2024 00:00:00 +0000https://philotron.github.io/datasets/cs_scholarly_kg/This repository contains the code, models, and data resources for building conversational search interfaces over scholarly publications presented at ICNLSP 2024.HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checkinghttps://philotron.github.io/datasets/healthfc/Sat, 01 Jun 2024 00:00:00 +0000https://philotron.github.io/datasets/healthfc/This repository provides the Medizin-transparent dataset and code used to verify medical claims via evidence-based fact-checking for an LREC-COLING 2024 paper.A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generationhttps://philotron.github.io/datasets/llm_kg_d2t/Wed, 01 May 2024 00:00:00 +0000https://philotron.github.io/datasets/llm_kg_d2t/This repository bundles data, prompts, and evaluation scripts for an EACL 2024 paper comparing how various conversational LLMs verbalize knowledge graph triples into text.MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answeringhttps://philotron.github.io/datasets/medreqal/Mon, 01 Apr 2024 00:00:00 +0000https://philotron.github.io/datasets/medreqal/This repository features the question-answering dataset and code used to examine the medical knowledge recall capabilities of large language models for an ACL 2024 paper.Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphshttps://philotron.github.io/datasets/llm_sp_cqa/Fri, 01 Mar 2024 00:00:00 +0000https://philotron.github.io/datasets/llm_sp_cqa/This repository hosts the data (SPICE test set) and scripts for fine-tuning, prompting, and evaluating various LLMs on semantic parsing for SPARQL query generation.Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphshttps://philotron.github.io/datasets/bridge_kg/Mon, 01 Jan 2024 00:00:00 +0000https://philotron.github.io/datasets/bridge_kg/This repository includes the dialogue corpus, source code, and evaluation outputs for a SIGDIAL 2024 study on grounding dialogue exchanges using knowledge graphs.Investigating Conversational Search Behavior For Domain Explorationhttps://philotron.github.io/datasets/conversational_domain_exploration_data/Sun, 01 Jan 2023 00:00:00 +0000https://philotron.github.io/datasets/conversational_domain_exploration_data/This repository offers an annotated dialogue corpus of text-based information-seeking conversations and five domain datasets to study exploratory search behavior from ECIR 2023.A Decade of Knowledge Graphs in Natural Language Processing: A Surveyhttps://philotron.github.io/datasets/kg_in_nlp_survey/Tue, 01 Nov 2022 00:00:00 +0000https://philotron.github.io/datasets/kg_in_nlp_survey/This repository contains the annotated collection of 507 papers and data included in the AACL-IJCNLP 2022 study on knowledge graphs in NLP.