Probabilistic Graph Reasoning for Natural Proof Generation
- URL: http://arxiv.org/abs/2107.02418v1
- Date: Tue, 6 Jul 2021 06:34:41 GMT
- Title: Probabilistic Graph Reasoning for Natural Proof Generation
- Authors: Changzhi Sun, Xinbo Zhang, Jiangjie Chen, Chun Gan, Yuanbin Wu, Jiaze
Chen, Hao Zhou, Lei Li
- Abstract summary: We propose PRobr, a novel approach for joint answer prediction and proof generation.
PRobr defines a joint probabilistic distribution over all possible proof graphs and answers.
Experiments on multiple datasets verify the effectiveness of PRobr.
- Score: 22.1374469158861
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we investigate the problem of reasoning over natural language
statements. Prior neural based approaches do not explicitly consider the
inter-dependency among answers and their proofs. In this paper, we propose
PRobr, a novel approach for joint answer prediction and proof generation. PRobr
defines a joint probabilistic distribution over all possible proof graphs and
answers via an induced graphical model. We then optimize the model using
variational approximation on top of neural textual representation. Experiments
on multiple datasets under diverse settings (fully supervised, few-shot and
zero-shot evaluation) verify the effectiveness of PRobr, e.g., achieving
10%-30% improvement on QA accuracy in few/zero-shot evaluation. Our codes and
models can be found at https://github.com/changzhisun/PRobr/.
Related papers
- Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs [49.547988001231424]
We propose the one-shot-subgraph link prediction to achieve efficient and adaptive prediction.
Design principle is that, instead of directly acting on the whole KG, the prediction procedure is decoupled into two steps.
We achieve promoted efficiency and leading performances on five large-scale benchmarks.
arXiv Detail & Related papers (2024-03-15T12:00:12Z) - Evidence Networks: simple losses for fast, amortized, neural Bayesian
model comparison [0.0]
Evidence Networks can enable Bayesian model comparison when state-of-the-art methods fail.
We introduce the leaky parity-odd power transform, leading to the novel l-POP-Exponential'' loss function.
We show that Evidence Networks are explicitly independent of dimensionality of the parameter space and scale mildly with the complexity of the posterior probability density function.
arXiv Detail & Related papers (2023-05-18T18:14:53Z) - Enhancing Self-Consistency and Performance of Pre-Trained Language
Models through Natural Language Inference [72.61732440246954]
Large pre-trained language models often lack logical consistency across test inputs.
We propose a framework, ConCoRD, for boosting the consistency and accuracy of pre-trained NLP models.
We show that ConCoRD consistently boosts accuracy and consistency of off-the-shelf closed-book QA and VQA models.
arXiv Detail & Related papers (2022-11-21T21:58:30Z) - Embarrassingly Simple Performance Prediction for Abductive Natural
Language Inference [10.536415845097661]
We propose a method for predicting the performance of NLI models without fine-tuning them.
We show that the accuracy of the cosine similarity approach correlates strongly with the accuracy of the classification approach with a Pearson correlation coefficient of 0.65.
Our method can lead to significant time savings in the process of model selection.
arXiv Detail & Related papers (2022-02-21T18:10:24Z) - How Can We Know When Language Models Know? On the Calibration of
Language Models for Question Answering [80.82194311274694]
We examine the question "how can we know when language models know, with confidence, the answer to a particular query?"
We examine three strong generative models -- T5, BART, and GPT-2 -- and study whether their probabilities on QA tasks are well calibrated.
We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness.
arXiv Detail & Related papers (2020-12-02T03:53:13Z) - PRover: Proof Generation for Interpretable Reasoning over Rules [81.40404921232192]
We propose a transformer-based model that answers binary questions over rule-bases and generates the corresponding proofs.
Our model learns to predict nodes and edges corresponding to proof graphs in an efficient constrained training paradigm.
We conduct experiments on synthetic, hand-authored, and human-paraphrased rule-bases to show promising results for QA and proof generation.
arXiv Detail & Related papers (2020-10-06T15:47:53Z) - PushNet: Efficient and Adaptive Neural Message Passing [1.9121961872220468]
Message passing neural networks have recently evolved into a state-of-the-art approach to representation learning on graphs.
Existing methods perform synchronous message passing along all edges in multiple subsequent rounds.
We consider a novel asynchronous message passing approach where information is pushed only along the most relevant edges until convergence.
arXiv Detail & Related papers (2020-03-04T18:15:30Z) - Neural Enhanced Belief Propagation on Factor Graphs [85.61562052281688]
A graphical model is a structured representation of locally dependent random variables.
We first extend graph neural networks to factor graphs (FG-GNN)
We then propose a new hybrid model that runs conjointly a FG-GNN with belief propagation.
arXiv Detail & Related papers (2020-03-04T11:03:07Z) - Parameter Space Factorization for Zero-Shot Learning across Tasks and
Languages [112.65994041398481]
We propose a Bayesian generative model for the space of neural parameters.
We infer the posteriors over such latent variables based on data from seen task-language combinations.
Our model yields comparable or better results than state-of-the-art, zero-shot cross-lingual transfer methods.
arXiv Detail & Related papers (2020-01-30T16:58:56Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.