[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models

Code and Data for EMNLP2020 Paper "KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation"

SPRING is a seq2seq model for Text-to-AMR and AMR-to-Text (AAAI2021).

This repository is the official implementation of our paper MVP: Multi-task Supervised Pre-training for Natural Language Generation.

Implementation of NeurIPS 20 paper: Latent Template Induction with Gumbel-CRFs

Code for Describing a Knowledge Base

Biomedical Data-to-Text Generation via Fine-Tuning Transformers

Code for Stage-wise Fine-tuning for Graph-to-Text Generation

:monocle_face: Code & Data for Fact-based Text Editing (Iso et al; ACL 2020)

Code for Controlling Hallucinations at Word Level in Data-to-Text Generation (C. Rebuffel, M. Roberti, L. Soulier, G. Scoutheeten, R. Cancelliere, P. Gallinari)

TCube generates rich and fluent narratives that describes the characteristics, trends, and anomalies of any time-series data (domain-agnostic) using the transfer learning capabilities of PLMs.

⛹️Code for Learning to Select, Track, and Generate for Data-to-Text (Iso et al; ACL 2019).

:basketball: Script for generating the rotowire-modified dataset (Iso et al; ACL 2019)

[COLING22] Text-to-Text Extraction and Verbalization of Biomedical Event Graphs

Data-to-Text generation with loosely aligned WikiBio dataset from (Lebret et al. 2016). Explicit content selection step with Multi-Instance Learning.

Data-to-text generation papers

LREC-COLING 24: Retrieval-Augmented Modular Prompt Tuning for Low-Resource Data-to-Text Generation

Code for my Master Thesis project on "Prompting Techniques for Natural Language Generation in the Medical Domain" at the University of Bologna

data-to-text system based on change point detection and fuzzy set theory.

Codebase for the journal paper "The Rare Word Issue in Natural Language Generation: a Character-Based Solution" (Giovanni Bonetta, Marco Roberti, Rossella Cancelliere, Patrick Gallinari)

Bidirectional fine-tuning of Microsoft's Phi-3-Mini model for payment transaction processing using LoRA. Includes forward (structured→NL) and reverse (NL→structured) models. Optimized for NVIDIA RTX 3060 (12GB VRAM). 500 synthetic examples, ~95% accuracy, 30-60min training time.

Code for IJCoL 7 Special Issue Paper - Improving Data-to-Text Generation via Preserving High-Frequency Phrases and Fact-Checking

InsightX transforms complex data analysis into simple conversations. Upload your CSV files and ask questions in plain English to get instant, data-backed insights with visualizations and statistical analysis. Built with a sophisticated multi-agent AI system that intelligently routes queries between SQL and Python for 10-50x performance improvements

Data To Text! Your ultimate open source solution to build NLG systems.

An LLM based tool for generation of cheese advirtisements

CURED4NLG: A Dataset for Table-to-Text Generation

This repository provides the official implementation for the EMNLP 2025 Findings paper: KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration

Annotation tool for adding text labels to CSV data. Useful for data-to-text NLP tasks.

Data-to-Text Generation with Case-Based Reasoning

Edge-AI powered Data-to-Text system that analyzes global fishery trends (Capture, Aquaculture, Stocks) and generates automated status reports offline using LSTM & TensorFlow Lite.