arXiv subjects

Pratyay Banerjee

Publications and source records attributed to Pratyay Banerjee.

34 records · Page 2Linked to original sources

arXiv2021

Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling

Decompilation is the procedure of transforming binary programs into a high-level representation, such as source code, for human analysts to examine. While modern decompilers can reconstruct and recover much information that is discarded during compilation, inferring variable names is still extremely difficult. Inspired by recent advances in natural language processing, we propose a novel solution to infer variable names in decompiled code based on Masked Language Modeling, Byte-Pair Encoding, and neural architectures such as Transformers and BERT. Our solution takes \textit{raw} decompiler output, the less semantically meaningful code, as input, and enriches it using our proposed \textit{finetuning} technique, Constrained Masked Language Modeling. Using Constrained Masked Language Modeling introduces the challenge of predicting the number of masked tokens for the original variable name. We address this \textit{count of token prediction} challenge with our post-processing algorithm. Compared to the state-of-the-art approaches, our trained VarBERT model is simpler and of much better performance. We evaluated our model on an existing large-scale data set with 164,632 binaries and showed that it can predict variable names identical to the ones present in the original source code up to 84.15\% of the time.

cs.LG↗

arXiv2021

Self-Supervised Test-Time Learning for Reading Comprehension

Recent work on unsupervised question answering has shown that models can be trained with procedurally generated question-answer pairs and can achieve performance competitive with supervised methods. In this work, we consider the task of unsupervised reading comprehension and present a method that performs "test-time learning" (TTL) on a given context (text passage), without requiring training on large-scale human-authored datasets containing \textit{context-question-answer} triplets. This method operates directly on a single test context, uses self-supervision to train models on synthetically generated question-answer pairs, and then infers answers to unseen human-authored questions for this context. Our method achieves accuracies competitive with fully supervised methods and significantly outperforms current unsupervised methods. TTL methods with a smaller model are also competitive with the current state-of-the-art in unsupervised reading comprehension.

cs.CL↗

arXiv2020

Can Transformers Reason About Effects of Actions?

A recent work has shown that transformers are able to "reason" with facts and rules in a limited setting where the rules are natural language expressions of conjunctions of conditions implying a conclusion. Since this suggests that transformers may be used for reasoning with knowledge given in natural language, we do a rigorous evaluation of this with respect to a common form of knowledge and its corresponding reasoning -- the reasoning about effects of actions. Reasoning about action and change has been a top focus in the knowledge representation subfield of AI from the early days of AI and more recently it has been a highlight aspect in common sense question answering. We consider four action domains (Blocks World, Logistics, Dock-Worker-Robots and a Generic Domain) in natural language and create QA datasets that involve reasoning about the effects of actions in these domains. We investigate the ability of transformers to (a) learn to reason in these domains and (b) transfer that learning from the generic domains to the other domains.

cs.CL↗

arXiv2020

MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering

While progress has been made on the visual question answering leaderboards, models often utilize spurious correlations and priors in datasets under the i.i.d. setting. As such, evaluation on out-of-distribution (OOD) test samples has emerged as a proxy for generalization. In this paper, we present MUTANT, a training paradigm that exposes the model to perceptually similar, yet semantically distinct mutations of the input, to improve OOD generalization, such as the VQA-CP challenge. Under this paradigm, models utilize a consistency-constrained training objective to understand the effect of semantic changes in input (question-image pair) on the output (answer). Unlike existing methods on VQA-CP, MUTANT does not rely on the knowledge about the nature of train and test answer distributions. MUTANT establishes a new state-of-the-art accuracy on VQA-CP with a $10.57\%$ improvement. Our work opens up avenues for the use of semantic input mutations for OOD generalization in question answering.

cs.CV↗

arXiv2020

Knowledge Guided Named Entity Recognition for BioMedical Text

In this work, we formulate the NER task as a multi-answer knowledge guided QA task (KGQA) which helps to predict entities only by assigning B, I and O tags without associating entity types with the tags. We provide different knowledge contexts, such as, entity types, questions, definitions and examples along with the text and train on a combined dataset of 18 biomedical corpora. This formulation (a) enables systems to jointly learn NER specific features from varied NER datasets, (b) can use knowledge-text attention to identify words having higher similarity to provided knowledge, improving performance, (c) reduces system confusion by reducing the prediction classes to B, I, O only, and (d) makes detection of nested entities easier. We perform extensive experiments of this KGQA formulation on 18 biomedical NER datasets, and through experiments we note that knowledge helps in achieving better performance. Our problem formulation is able to achieve state-of-the-art results in 12 datasets.

cs.CL↗

arXiv2020

Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering

The aim of all Question Answering (QA) systems is to be able to generalize to unseen questions. Current supervised methods are reliant on expensive data annotation. Moreover, such annotations can introduce unintended annotator bias which makes systems focus more on the bias than the actual task. In this work, we propose Knowledge Triplet Learning (KTL), a self-supervised task over knowledge graphs. We propose heuristics to create synthetic graphs for commonsense and scientific knowledge. We propose methods of how to use KTL to perform zero-shot QA and our experiments show considerable improvements over large pre-trained transformer models.

cs.CL↗

arXiv2020

VQA-LOL: Visual Question Answering under the Lens of Logic

Logical connectives and their implications on the meaning of a natural language sentence are a fundamental aspect of understanding. In this paper, we investigate whether visual question answering (VQA) systems trained to answer a question about an image, are able to answer the logical composition of multiple such questions. When put under this \textit{Lens of Logic}, state-of-the-art VQA models have difficulty in correctly answering these logically composed questions. We construct an augmentation of the VQA dataset as a benchmark, with questions containing logical compositions and linguistic transformations (negation, disjunction, conjunction, and antonyms). We propose our {Lens of Logic (LOL)} model which uses question-attention and logic-attention to understand logical connectives in the question, and a novel Fréchet-Compatibility Loss, which ensures that the answers of the component questions and the composed question are consistent with the inferred logical operation. Our model shows substantial improvement in learning logical compositions while retaining performance on VQA. We suggest this work as a move towards robustness by embedding logical connectives in visual understanding.

cs.CV↗

arXiv2020

How Additional Knowledge can Improve Natural Language Commonsense Question Answering?

Recently several datasets have been proposed to encourage research in Question Answering domains where commonsense knowledge is expected to play an important role. Recent language models such as ROBERTA, BERT and GPT that have been pre-trained on Wikipedia articles and books have shown reasonable performance with little fine-tuning on several such Multiple Choice Question-Answering (MCQ) datasets. Our goal in this work is to develop methods to incorporate additional (commonsense) knowledge into language model-based approaches for better question-answering in such domains. In this work, we first categorize external knowledge sources, and show performance does improve on using such sources. We then explore three different strategies for knowledge incorporation and four different models for question-answering using external commonsense knowledge. We analyze our predictions to explore the scope of further improvements.

cs.CL↗

arXiv2020

Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering

Open Domain Question Answering requires systems to retrieve external knowledge and perform multi-hop reasoning by composing knowledge spread over multiple sentences. In the recently introduced open domain question answering challenge datasets, QASC and OpenBookQA, we need to perform retrieval of facts and compose facts to correctly answer questions. In our work, we learn a semantic knowledge ranking model to re-rank knowledge retrieved through Lucene based information retrieval systems. We further propose a "knowledge fusion model" which leverages knowledge in BERT-based language models with externally retrieved knowledge and improves the knowledge understanding of the BERT-based language models. On both OpenBookQA and QASC datasets, the knowledge fusion model with semantically re-ranked knowledge outperforms previous attempts.

cs.CL↗

arXiv2020

Natural Language QA Approaches using Reasoning with External Knowledge

Question answering (QA) in natural language (NL) has been an important aspect of AI from its early days. Winograd's ``councilmen'' example in his 1972 paper and McCarthy's Mr. Hug example of 1976 highlights the role of external knowledge in NL understanding. While Machine Learning has been the go-to approach in NL processing as well as NL question answering (NLQA) for the last 30 years, recently there has been an increasingly emphasized thread on NLQA where external knowledge plays an important role. The challenges inspired by Winograd's councilmen example, and recent developments such as the Rebooting AI book, various NLQA datasets, research on knowledge acquisition in the NLQA context, and their use in various NLQA models have brought the issue of NLQA using ``reasoning'' with external knowledge to the forefront. In this paper, we present a survey of the recent work on them. We believe our survey will help establish a bridge between multiple fields of AI, especially between (a) the traditional fields of knowledge representation and reasoning and (b) the field of NL understanding and NLQA.

cs.CL↗

arXiv2019

ASU at TextGraphs 2019 Shared Task: Explanation ReGeneration using Language Models and Iterative Re-Ranking

In this work we describe the system from Natural Language Processing group at Arizona State University for the TextGraphs 2019 Shared Task. The task focuses on Explanation Regeneration, an intermediate step towards general multi-hop inference on large graphs. Our approach consists of modeling the explanation regeneration task as a \textit{learning to rank} problem, for which we use state-of-the-art language models and explore dataset preparation techniques. We utilize an iterative re-ranking based approach to further improve the rankings. Our system secured 2nd rank in the task with a mean average precision (MAP) of 41.3\% on the test set.

cs.CL↗

arXiv2019

Careful Selection of Knowledge to solve Open Book Question Answering

Open book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such QA, OpenBookQA, has been proposed. Unlike most other NLQA tasks that focus on linguistic understanding, OpenBookQA requires deeper reasoning involving linguistic understanding as well as reasoning with common knowledge. In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.

cs.CL↗

arXiv2019

Construction of a few Quantum mechanical Hamiltonians via L$\acute{e}$vi-Leblond type Linearization:Spinor states and Supersymmetry

A number of new L$\acute{e}$vi-Leblond type equations admitting four component spinor solutions have been proposed. The pair of linearized equations thus obtained in each case lead to Hamiltonians with characteristic features like L-S coupling and supersymmetry. The relevant momentum operators have often been understood in terms of Clifford algebraic bases producing Schr$\ddot{o}$dinger Hamiltonians with L-S coupling. As for example Hamiltonians representing Rashba effect or three dimensional harmonic oscillator have been constructed. The supersymmetric nature of one dimensional oscillator has also been appreciated.

quant-ph↗

arXiv2014

Partition functions of Polychronakos like spin chains associated with polarized spin reversal operators

We construct polarized spin reversal operator (PSRO) which yields a class of representations for the $BC_N$ type of Weyl algebra, and subsequently use this PSRO to find out novel exactly solvable variants of the $BC_N$ type of spin Calogero model. The strong coupling limit of such spin Calogero models generates the $BC_N$ type of Polychronakos spin chains with PSRO. We derive the exact spectra of the $BC_N$ type of spin Calogero models with PSRO and compute the partition functions of the related spin chains by using the freezing trick. We also find out an interesting relation between the partition functions of the $BC_N$ type and $A_{N-1}$ type of Polychronakos spin chains. Finally, we study spectral properties like level density and distribution of spacing between consecutive energy levels for $BC_N$ type of Polychronakos spin chains with PSRO.

cond-mat.stat-mech↗

arXiv2011

Level density distribution for one-dimensional vertex models related to Haldane-Shastry like spin chains

The energy level density distributions of some Haldane-Shastry like spin chains associated with the $A_{N-1}$ root system have been computed recently by Enciso et al., exploiting the connection of these spin systems with inhomogeneous one-dimensional vertex models whose energy functions depend on the vertices through specific polynomials of first or second degree. Here we consider a much broader class of one-dimensional vertex models whose energy functions depend on the vertices through arbitrary polynomials of any possible degree. We estimate the order of mean and variance for such energy functions and show that the level density distribution of all vertex models belonging to this class asymptotically follow the Gaussian pattern for large number of vertices. We also present some numerical evidence in support of this analytical result.

cond-mat.stat-mech↗

arXiv2010

Exact solution of $D_N$ type quantum Calogero model through a mapping to free harmonic oscillators

We solve the eigenvalue problem of the $D_N$ type of Calogero model by mapping it to a set of decoupled quantum harmonic oscillators through a similarity transformation. In particular, we construct the eigenfunctions of this Calogero model from those of bosonic harmonic oscillators having either all even parity or all odd parity. It turns out that the eigenfunctions of this model are orthogonal with respect to a nontrivial inner product, which can be derived from the quasi-Hermiticity property of the corresponding conserved quantities.

nlin.SI↗