arXiv subjects

Prateek Yadav

Publications and source records attributed to Prateek Yadav.

24 records · Page 2Linked to original sources

arXiv2021

multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning

We focus on a type of linguistic formal reasoning where the goal is to reason over explicit knowledge in the form of natural language facts and rules (Clark et al., 2020). A recent work, named PRover (Saha et al., 2020), performs such reasoning by answering a question and also generating a proof graph that explains the answer. However, compositional reasoning is not always unique and there may be multiple ways of reaching the correct answer. Thus, in our work, we address a new and challenging problem of generating multiple proof graphs for reasoning over natural language rule-bases. Each proof provides a different rationale for the answer, thereby improving the interpretability of such reasoning systems. In order to jointly learn from all proof graphs and exploit the correlations between multiple proofs for a question, we pose this task as a set generation problem over structured output spaces where each proof is represented as a directed graph. We propose two variants of a proof-set generation model, multiPRover. Our first model, Multilabel-multiPRover, generates a set of proofs via multi-label classification and implicit conditioning between the proofs; while the second model, Iterative-multiPRover, generates proofs iteratively by explicitly conditioning on the previously generated proofs. Experiments on multiple synthetic, zero-shot, and human-paraphrased datasets reveal that both multiPRover models significantly outperform PRover on datasets containing multiple gold proofs. Iterative-multiPRover obtains state-of-the-art proof F1 in zero-shot scenarios where all examples have single correct proofs. It also generalizes better to questions requiring higher depths of reasoning where multiple proofs are more frequent. Our code and models are publicly available at https://github.com/swarnaHub/multiPRover

cs.CL↗

arXiv2019

Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks

Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing syntactic context of a word, such methods result in an explosion of the vocabulary size. In this paper, we overcome this problem by proposing SynGCN, a flexible Graph Convolution based method for learning word embeddings. SynGCN utilizes the dependency context of a word without increasing the vocabulary size. Word embeddings learned by SynGCN outperform existing methods on various intrinsic and extrinsic tasks and provide an advantage when used with ELMo. We also propose SemGCN, an effective framework for incorporating diverse semantic knowledge for further enhancing learned word representations. We make the source code of both models available to encourage reproducible research.

cs.CL↗

arXiv2019

HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs

In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise. Hypergraphs provide a flexible and natural modeling tool to model such complex relationships. The obvious existence of such complex relationships in many real-world networks naturaly motivates the problem of learning with hypergraphs. A popular learning paradigm is hypergraph-based semi-supervised learning (SSL) where the goal is to assign labels to initially unlabeled vertices in a hypergraph. Motivated by the fact that a graph convolutional network (GCN) has been effective for graph-based SSL, we propose HyperGCN, a novel GCN for SSL on attributed hypergraphs. Additionally, we show how HyperGCN can be used as a learning-based approach for combinatorial optimisation on NP-hard hypergraph problems. We demonstrate HyperGCN's effectiveness through detailed experimentation on real-world hypergraphs.

cs.LG↗

arXiv2019

Confidence-based Graph Convolutional Networks for Semi-Supervised Learning

Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi-Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds and then utilizing the graph structure to predict label scores for the rest of the nodes in the graph. Recently, Graph Convolutional Networks (GCNs) have achieved impressive performance on the graph-based SSL task. In addition to label scores, it is also desirable to have confidence scores associated with them. Unfortunately, confidence estimation in the context of GCN has not been previously explored. We fill this important gap in this paper and propose ConfGCN, which estimates labels scores along with their confidences jointly in GCN-based setting. ConfGCN uses these estimated confidences to determine the influence of one node on another during neighborhood aggregation, thereby acquiring anisotropic capabilities. Through extensive analysis and experiments on standard benchmarks, we find that ConfGCN is able to outperform state-of-the-art baselines. We have made ConfGCN's source code available to encourage reproducible research.

cs.LG↗

arXiv2019

Observations of Fast Radio Bursts at Frequencies down to 400 Megahertz

Fast radio bursts (FRBs) are highly dispersed millisecond-duration radio flashes likely arriving from far outside the Milky Way galaxy. This phenomenon was discovered at radio frequencies near 1.4 GHz and to date has been observed in one case at as high as 8 GHz, but not below 700 MHz in spite of significant searches at low frequencies. Here we report detections of FRBs at radio frequencies as low as 400 MHz, on the Canadian Hydrogen Intensity Mapping Experiment (CHIME) using the CHIME/FRB instrument. We present 13 FRBs detected during a telescope pre-commissioning phase, when our sensitivity and field-of-view were not yet at design specifications. Emission in multiple events is seen down to 400 MHz, the lowest radio frequency to which we are sensitive. The FRBs show a variety of temporal scattering behaviours, with the majority significantly scattered, and some apparently unscattered to within measurement uncertainty even at our lowest frequencies. Of the 13 reported here, one event has the lowest dispersion measure yet reported, implying it is among the closest yet known, and another has shown multiple repeat bursts, as described in a companion paper. Our low-scattering events suggest that efforts to detect FRBs at radio frequencies below 400 MHz will eventually be successful. The overall scattering properties of our sample suggest that FRBs as a class are preferentially located in environments that scatter radio waves more strongly than the diffuse interstellar medium (ISM) in the Milky Way.

astro-ph.HE↗

arXiv2019

Lovasz Convolutional Networks

Semi-supervised learning on graph structured data has received significant attention with the recent introduction of Graph Convolution Networks (GCN). While traditional methods have focused on optimizing a loss augmented with Laplacian regularization framework, GCNs perform an implicit Laplacian type regularization to capture local graph structure. In this work, we propose Lovasz Convolutional Network (LCNs) which are capable of incorporating global graph properties. LCNs achieve this by utilizing Lovasz's orthonormal embeddings of the nodes. We analyse local and global properties of graphs and demonstrate settings where LCNs tend to work better than GCNs. We validate the proposed method on standard random graph models such as stochastic block models (SBM) and certain community structure based graphs where LCNs outperform GCNs and learn more intuitive embeddings. We also perform extensive binary and multi-class classification experiments on real world datasets to demonstrate LCN's effectiveness. In addition to simple graphs, we also demonstrate the use of LCNs on hyper-graphs by identifying settings where they are expected to work better than GCNs.

cs.LG↗