Francesco Piccinno
Research Areas
Authored Publications
Sort By
DePlot: One-shot visual language understanding by plot-to-text translation
Chenxi Pang
Mandar Joshi
Nigel Collier
Under review (2022)
Preview abstract
Visual language such as charts and plots are ubiquitous in the human world. Comprehending plots and charts requires strong reasoning skills. Prior state-of-the-art models are end-to-end multimodal Transformers pretrained with dedicated plot derendering and numerical reasoning objectives. However, the models reasoning capabilities still fall short and will generally fail on complex queries.
In this paper, we decompose the multimodal reasoning problem into first, a modality conversion problem from image to text, then a purely textual reasoning problem. Through combining a pretrained image-to-text model and an LLM for the task of chart/figure reasoning. Compared with a SOTA model finetuned on >10k data points, our plug-and-play model DePlot-LLM achieves >20% improvement over finetuned SOTA with just one-shot prompting.
View details
Evaluating Byte and Wordpiece Level Models for Massively Multilingual Semantic Parsing
Massively Multilingual NLU 2022, colocated with EMNLP 2022, The 2022 Conference on Empirical Methods in Natural Language Processing (2022)
Preview abstract
Token free approaches have been successfully applied to a series of word and span level tasks. In this work, we compare a byte-level (ByT5) and a wordpiece based (mT5) sequence to sequence model on the 51 languages of the MASSIVE multilingual semantic parsing dataset. We examine multiple experimental settings: (i) zero-shot, (ii) full gold data and (iii) zero-shot with synthetic data. By leveraging a state-of-the-art label projection method for machine translated examples, we are able to reduce the gap in exact match accuracy to only 5 points with respect to a model trained on gold data from all the languages.
We additionally provide insights on the cross-lingual transfer of ByT5 and show how the model compares with respect to mT5 across all parameter sizes.
View details
Table-To-Text generation and pre-training with TabT5
Ewa Andrejczuk
Findings of EMNLP (2022)
Preview abstract
Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks such as cell selection or entailment detection. We present TABT5, an encoder-decoder model that generates natural language text based on tables and textual inputs. TABT5, overcomes the encoder-only limitation by incorporating a decoder component and leverages the input structure with table specific embeddings as well as pre-training. TABT5 achieves new state-of-the-art results on several domains, including spreadsheet formula prediction (15% increase in sequence accuracy), question answering (10% increase in sequence accuracy) and data-to-text generation (2% increas in BLEU).
View details
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
Chenxi Pang
Mandar Joshi
Nigel Collier
Under review (2022)
Preview abstract
Visual language data such as plots, charts, and infographics are ubiquitous in the human world. However, state-of-the-art vision-language models do not perform well on these data. We propose a set of pretraining tasks to enhance visual language models' capabilities in jointly modeling charts/plots and language data. We initialize with Pix2Struct, a recently proposed image-to-text visual language model and continue pretraining with our proposed objectives. We argue that numerical reasoning and plot deconstruction enable a model with the key capabilities of (1) extracting key information and (2) reasoning on the extracted information. On standard benchmarks such as PlotQA and ChartQA, our continually pretrained MatCha model outperforms state-of-the-art methods by as much as ~20%. We also examine how well does MatCha pretraining transfer to domains such as screenshot, textbook, and poster figures. We observe improvement over the base Pix2Struct checkpoint by 1.2% on average, verifying the usefulness of MatCha pretraining on broader visual language tasks.
View details
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs
Pierre Marion
Empirical Methods in Natural Language Processing (2021) (to appear)
Preview abstract
We tackle the problem of weakly-supervised conversational Question Answering over large Knowledge Graphs using a neural semantic parsing approach.
We introduce a new Logical Form (LF) grammar that can model a wide range of queries on the graph while remaining sufficiently simple to generate supervision data efficiently.
Our Transformer-based model takes a JSON-like structure as input, allowing us to easily incorporate both Knowledge Graph and conversational contexts. This structured input is transformed to lists of embeddings and then fed to standard attention layers.
We validate our approach, both in terms of grammar coverage and LF execution accuracy, on two publicly available datasets, CSQA and ConvQuestions, both grounded in Wikidata. On CSQA, our approach increases the coverage from 80% to 96.2%, and the LF execution accuracy from 70.6% to 75.6%, with respect to previous state-of-the-art results. On ConvQuestions, we achieve competitive results with respect to the state-of-the-art.
View details
Tapas: Weakly Supervised Table Parsing via Pre-training
Thomas Müller
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Seattle, Washington, United States (2020)
Preview abstract
Answering natural language questions over tables is usually seen as a semantic parsing task. To alleviate the collection cost of full logical forms, one popular approach focuses on weak supervision consisting of denotations instead of logical forms. However, training semantic parsers from weak supervision poses difficulties, and in addition, the generated logical forms are only used as an intermediate step prior to retrieving the denotation. In this paper, we present TAPAS, an approach to question answering over tables without generating logical forms. TAPAS trains from weak supervision, and predicts the denotation by selecting table cells and optionally applying a corresponding aggregation operator to such selection. TAPAS extends BERT's architecture to encode tables as input, initializes from an effective joint pre-training of text segments and tables crawled from Wikipedia, and is trained end-to-end. We experiment with three different semantic parsing datasets, and find that TAPAS outperforms or rivals semantic parsing models by improving state-of-the-art accuracy on SQA from 55.1 to 67.2 and performing on par with the state-of-the-art on WIKISQL and WIKITQ, but with a simpler model architecture. We additionally find that transfer learning, which is trivial in our setting, from WIKISQL to WIKITQ, yields 48.7 accuracy, 4.2 points above the state-of-the-art.
View details
Preview abstract
Semantic parsing maps natural language utterances into structured meaning representations. We present an approach that uses a Graph Neural Network (GNN) architecture to incorporate information about relevant entities and their relations during parsing. Combined with a decoder copy mechanism, this approach also provides a conceptually simple mechanism to generate logical forms with entities. We demonstrate that this approach is competitive with state-of-the-art across several tasks without pre-training, and outperforms existing approaches when combined with BERT pre-training.
View details
Answering Conversational Questions on Structured Data without Logical Forms
Thomas Müller
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics (2019)
Preview abstract
We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. We encode tables as graphs using a graph neural network model based on the Transformer architecture. The answers are then selected from the encoded graph using a pointer network. This model is appropriate for processing conversations around structured data, where the attention mechanism that selects the answer to a question can also be used to resolve conversational references. We demonstrate the validity of this approach with competitive results on the Sequential Question Answering task (SQA) (Iyyer et al., 2017).
View details
