Search Results for author:
Found 9 papers, 6 papers with code
DePlot: One-shot visual language reasoning by plot-to-table translation
Compared with a SOTA model finetuned on more than >28k data points, DePlot+LLM with just one-shot prompting achieves a 24. 0% improvement over finetuned SOTA on human-written queries from the task of chart QA.
Chart Question Answering
Factual Inconsistency Detection in Chart Captioning
+3
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
Visual language data such as plots, charts, and infographics are ubiquitous in the human world.
Ranked #1 on
Visual Question Answering
on PlotQA-D2
Table-To-Text generation and pre-training with TabT5
Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020).
DoT: An efficient Double Transformer for NLP tasks with tables
To improve efficiency while maintaining a high accuracy, we propose a new architecture, DoT, a double transformer model, that decomposes the problem into two sub-tasks: A shallow pruning transformer that selects the top-K tokens, followed by a deep task-specific transformer that takes as input those K tokens.
TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training
We adopt the binary TAPAS model of Eisenschlos et al. (2020) to this task.
Open Domain Question Answering over Tables via Dense Retrieval
Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages.
Understanding tables with intermediate pre-training
To be able to use long examples as input of BERT models, we evaluate table pruning techniques as a pre-processing step to drastically improve the training and prediction efficiency at a moderate drop in accuracy.
Ranked #9 on
Table-based Fact Verification
on TabFact
Embedding models for recommendation under contextual constraints
For example, applying constraints a posteriori can result in incomplete recommendations or low-quality results for the tail of the distribution (i. e., less popular items).
Learning Nonsymmetric Determinantal Point Processes
Our method imposes a particular decomposition of the nonsymmetric kernel that enables such tractable learning algorithms, which we analyze both theoretically and experimentally.
