Papers by Francesco Piccinno

11 papers
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering (2023.acl-long)

Copied to clipboard

Challenge: Visual language models that are pretraining on natural images or image-text pairs crawled from the web perform poorly on visual language tasks such as ChartQA and ChartQA.
Approach: They propose to perform several pretraining tasks that cover plot deconstruction and numerical reasoning which are key capabilities in visual language modeling.
Outcome: The proposed model outperforms state-of-the-art methods on benchmarks such as PlotQA and ChartQA by as much as 20%.
Table-To-Text generation and pre-training with TabT5 (2022.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are limited when it comes to structured or semi-structured domains like tables.
Approach: They propose an encoder-decoder model that generates natural language text based on tables and textual inputs.
Outcome: TabT5 achieves 15% increase in sequence accuracy on spreadsheet formula prediction and data-to-text generation domains.
STRUCTSUM Generation for Faster Text Comprehension (2024.acl-long)

Copied to clipboard

Challenge: Current large language models (LLMs) fail to adequately structure and organize information in a way that facilitates comprehension.
Approach: They propose a taxonomy of problems around factuality, global and local structure common to both modalities and propose 'auto-QA' to improve the accuracy of generated structured representations.
Outcome: The proposed models improve accuracy and speed without loss of accuracy.
DePlot: One-shot visual language reasoning by plot-to-table translation (2023.findings-acl)

Copied to clipboard

Challenge: Existing models for visual language reasoning require tens of thousands of training examples and their reasoning capabilities are limited.
Approach: They propose a one-shot solution to visual language reasoning by combining plot-to-text translation and reasoning over the translated text into a modality conversion module.
Outcome: The proposed method improves on human-written queries on plots and charts compared with a fine-tuned SOTA model on human queries.
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs (2021.emnlp-main)

Copied to clipboard

Challenge: We present a new approach for weakly-supervised conversational Question Answering over Knowledge Graphs .
Approach: They propose a Logical Form grammar that can model a wide range of queries on a Knowledge Graph while remaining sufficiently simple to generate supervision data efficiently.
Outcome: The proposed grammar can model a wide range of queries while remaining simple to generate supervision data efficiently.
mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent large language models display surprising multilingual capabilities despite being pre-trained on English data.
Approach: They propose a multilingual sequence-to-sequence model that disentangles language-specific information from language-agnostic information.
Outcome: The proposed model outperforms existing models on representative natural language understanding and generation tasks in 40+ languages.
Multimodal Chart Retrieval: A Comparison of Text, Table and Image Based Approaches (2024.naacl-long)

Copied to clipboard

Challenge: Multimodal chart retrieval is a task of retrieving information from a multimodal dataset, given a query.
Approach: They compare four different approaches to multimodal chart retrieval . they use chart derendering, chart derending, table retrieval and Tab-GTR .
Outcome: The proposed model outperforms the previous methods on the NQ-Tables benchmark and is significantly more efficient on in-distribution data.
Answering Conversational Questions on Structured Data without Logical Forms (D19-1)

Copied to clipboard

Challenge: Existing approaches to answering sequential questions based on structured objects do not use a logical form as an intermediate representation.
Approach: They propose a novel approach to answering sequential questions based on structured objects without using a logical form as an intermediate representation.
Outcome: The proposed approach is competitively tested on the Sequential Question Answering (SQA) task.
Generating Logical Forms from Graph Representations of Text and Entities (P19-1)

Copied to clipboard

Challenge: Recent approaches to semantic parsing have cast it as a sequence-to-sequence task, with strong results.
Approach: They propose a Graph Neural Network architecture to incorporate information about relevant entities and their relations during parsing.
Outcome: The proposed approach outperforms the state-of-the-art in several tasks without pre-training and outperformed existing approaches when combined with BERT pre-trainment.
TaPas: Weakly Supervised Table Parsing via Pre-training (2020.acl-main)

Copied to clipboard

Challenge: Answering natural language questions over tables is often seen as a semantic parsing task.
Approach: They propose an approach to question answering over tables without generating logical forms by selecting table cells and optionally applying a corresponding aggregation operator.
Outcome: The proposed approach outperforms or rivals existing models on three different datasets and performs on par with the state-of-the-art on WikiSQL and WikiTQ.
Faithful Chart Summarization with ChaTS-Pi (2024.acl-long)

Copied to clipboard

Challenge: Chart-to-summary generation can help explore data, communicate insights, and help the visually impaired.
Approach: They propose a reference-free chart summarization metric for scoring faithfulness . they use human raters to fix and rank candidate summaries from any chart-summarization model .
Outcome: The proposed metric scores the summarization faithfulness according to human ratings better than reference-based metrics, either learned or n-gram based.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations