arXiv subjects

Himanshu Gupta

Publications and source records attributed to Himanshu Gupta.

At least 55 records · Page 3Linked to original sources

arXiv2023

InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis

We introduce InstructABSA, an instruction learning paradigm for Aspect-Based Sentiment Analysis (ABSA) subtasks. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tune the model (Tk-Instruct) for ABSA subtasks, yielding significant performance improvements. Experimental results on the Sem Eval 2014, 15, and 16 datasets demonstrate that InstructABSA outperforms the previous state-of-the-art (SOTA) approaches on Term Extraction (ATE), Sentiment Classification(ATSC) and Sentiment Pair Extraction (ASPE) subtasks. In particular, InstructABSA outperforms the previous state-of-the-art (SOTA) on the Rest14 ATE subtask by 5.69% points, the Rest15 ATSC subtask by 9.59% points, and the Lapt14 AOPE subtask by 3.37% points, surpassing 7x larger models. We also get competitive results on AOOE, AOPE, and AOSTE subtasks indicating strong generalization ability to all subtasks. Exploring sample efficiency reveals that just 50% train data is required to get competitive results with other instruction tuning approaches. Lastly, we assess the quality of instructions and observe that InstructABSA's performance experiences a decline of ~10% when adding misleading examples.

cs.CL↗

arXiv2023

Automated Assessment of Critical View of Safety in Laparoscopic Cholecystectomy

Cholecystectomy (gallbladder removal) is one of the most common procedures in the US, with more than 1.2M procedures annually. Compared with classical open cholecystectomy, laparoscopic cholecystectomy (LC) is associated with significantly shorter recovery period, and hence is the preferred method. However, LC is also associated with an increase in bile duct injuries (BDIs), resulting in significant morbidity and mortality. The primary cause of BDIs from LCs is misidentification of the cystic duct with the bile duct. Critical view of safety (CVS) is the most effective of safety protocols, which is said to be achieved during the surgery if certain criteria are met. However, due to suboptimal understanding and implementation of CVS, the BDI rates have remained stable over the last three decades. In this paper, we develop deep-learning techniques to automate the assessment of CVS in LCs. An innovative aspect of our research is on developing specialized learning techniques by incorporating domain knowledge to compensate for the limited training data available in practice. In particular, our CVS assessment process involves a fusion of two segmentation maps followed by an estimation of a certain region of interest based on anatomical structures close to the gallbladder, and then finally determination of each of the three CVS criteria via rule-based assessment of structural information. We achieved a gain of over 11.8% in mIoU on relevant classes with our two-stream semantic segmentation approach when compared to a single-model baseline, and 1.84% in mIoU with our proposed Sobel loss function when compared to a Transformer-based baseline model. For CVS criteria, we achieved up to 16% improvement and, for the overall CVS assessment, we achieved 5% improvement in balanced accuracy compared to DeepCVS under the same experiment settings.

cs.CV↗

arXiv2023

Quantum Sensor Network Algorithms for Transmitter Localization

A quantum sensor (QS) is able to measure various physical phenomena with extreme sensitivity. QSs have been used in several applications such as atomic interferometers, but few applications of a quantum sensor network (QSN) have been proposed or developed. We look at a natural application of QSN -- localization of an event (in particular, of a wireless signal transmitter). In this paper, we develop effective quantum-based techniques for the localization of a transmitter using a QSN. Our approaches pose the localization problem as a well-studied quantum state discrimination (QSD) problem and address the challenges in its application to the localization problem. In particular, a quantum state discrimination solution can suffer from a high probability of error, especially when the number of states (i.e., the number of potential transmitter locations in our case) can be high. We address this challenge by developing a two-level localization approach, which localizes the transmitter at a coarser granularity in the first level, and then, in a finer granularity in the second level. We address the additional challenge of the impracticality of general measurements by developing new schemes that replace the QSD's measurement operator with a trained parameterized hybrid quantum-classical circuit. Our evaluation results using a custom-built simulator show that our best scheme is able to achieve meter-level (1-5m) localization accuracy; in the case of discrete locations, it achieves near-perfect (99-100\%) classification accuracy.

quant-ph↗

arXiv2023

Context-NER : Contextual Phrase Generation at Scale

Named Entity Recognition (NER) has seen significant progress in recent years, with numerous state-of-the-art (SOTA) models achieving high performance. However, very few studies have focused on the generation of entities' context. In this paper, we introduce CONTEXT-NER, a task that aims to generate the relevant context for entities in a sentence, where the context is a phrase describing the entity but not necessarily present in the sentence. To facilitate research in this task, we also present the EDGAR10-Q dataset, which consists of annual and quarterly reports from the top 1500 publicly traded companies. The dataset is the largest of its kind, containing 1M sentences, 2.8M entities, and an average of 35 tokens per sentence, making it a challenging dataset. We propose a baseline approach that combines a phrase generation algorithm with inferencing using a 220M language model, achieving a ROUGE-L score of 27% on the test split. Additionally, we perform a one-shot inference with ChatGPT, which obtains a 30% ROUGE-L, highlighting the difficulty of the dataset. We also evaluate models such as T5 and BART, which achieve a maximum ROUGE-L of 49% after supervised finetuning on EDGAR10-Q. We also find that T5-large, when pre-finetuned on EDGAR10-Q, achieve SOTA results on downstream finance tasks such as Headline, FPB, and FiQA SA, outperforming vanilla version by 10.81 points. To our surprise, this 66x smaller pre-finetuned model also surpasses the finance-specific LLM BloombergGPT-50B by 15 points. We hope that our dataset and generated artifacts will encourage further research in this direction, leading to the development of more sophisticated language models for financial text analysis

cs.IR↗

arXiv2023

Distributing Quantum Circuits Using Teleportations

Scalability is currently one of the most sought-after objectives in the field of quantum computing. Distributing a quantum circuit across a quantum network is one way to facilitate large computations using current quantum computers. In this paper, we consider the problem of distributing a quantum circuit across a network of heterogeneous quantum computers, while minimizing the number of teleportations (the communication cost) needed to implement gates spanning multiple computers. We design two algorithms for this problem. The first, called Local- Best, initially distributes the qubits across the network, then tries to teleport qubits only when necessary, with teleportations being influenced by gates in the near future. The second, called Zero- Stitching, divides the given circuit into sub-circuits such that each sub-circuit can be executed using zero teleportations and the teleportation cost incurred at the borders of the sub-circuits is minimal. We evaluate our algorithms over a wide range of randomly-generated circuits as well as known benchmarks, and compare their performance to prior work. We observe that our techniques outperform the prior approach by a significant margin (up to 50%).

quant-ph↗

arXiv2023

Discrete outcome quantum sensor networks

We model a quantum sensor network using techniques from quantum state discrimination. The interaction between a qubit detector and the environment is described by a unitary operator, and we will assume that at most one detector does interact. The task is to determine which one does or if none do. This involves choosing an initial state of the detectors and a measurement. We consider global measurements in which all detectors are measured simultaneously. We find that an entangled initial state can improve the detection probability, but this advantage decreases as the number of detectors increases.

quant-ph↗

arXiv2023

EDM3: Event Detection as Multi-task Text Generation

Event detection refers to identifying event occurrences in a text and comprises of two subtasks; event identification and classification. We present EDM3, a novel approach for Event Detection that formulates three generative tasks: identification, classification, and combined detection. We show that EDM3 helps to learn transferable knowledge that can be leveraged to perform Event Detection and its subtasks concurrently, mitigating the error propagation inherent in pipelined approaches. Unlike previous dataset- or domain-specific approaches, EDM3 utilizes the existing knowledge of language models, allowing it to be trained over any classification schema. We evaluate EDM3 on multiple event detection datasets: RAMS, WikiEvents, MAVEN, and MLEE, showing that EDM3 outperforms 1) single-task performance by 8.4% on average and 2) multi-task performance without instructional prompts by 2.4% on average. We obtain SOTA results on RAMS (71.3% vs. 65.1% F-1) and competitive performance on other datasets. We analyze our approach to demonstrate its efficacy in low-resource and multi-sentence settings. We also show the effectiveness of this approach on non-standard event configurations such as multi-word and multi-class event triggers. Overall, our results show that EDM3 is a promising approach for Event Detection that has the potential for real-world applications.

cs.CL↗

arXiv2023

Instruction Tuned Models are Quick Learners

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream training data for finetuning. Often in real-world situations, there is a scarcity of data available for finetuning, falling somewhere between few shot inference and fully supervised finetuning. In this work, we demonstrate the sample efficiency of instruction tuned models over various tasks by estimating the minimal downstream training data required by them to perform transfer learning and match the performance of state-of-the-art (SOTA) supervised models. We conduct experiments on 119 tasks from Super Natural Instructions (SuperNI) in both the single task learning (STL) and multi task learning (MTL) settings. Our findings reveal that, in the STL setting, instruction tuned models equipped with 25% of the downstream train data surpass the SOTA performance on the downstream tasks. In the MTL setting, an instruction tuned model trained on only 6% of downstream training data achieve SOTA, while using 100% of the training data results in a 3.69% points improvement (ROUGE-L 74.68) over the previous SOTA. We conduct an analysis on T5 vs Tk-Instruct by developing several baselines to demonstrate that instruction tuning aids in increasing both sample efficiency and transfer learning. Additionally, we observe a consistent ~4% performance increase in both settings when pre-finetuning is performed with instructions. Finally, we conduct a categorical study and find that contrary to previous results, tasks in the question rewriting and title generation categories suffer from instruction tuning.

cs.CL↗

arXiv2023

A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution

State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel' instances that do not belong to any known class are often observed. This renders the ability to deal with novelties crucial. To initiate a systematic research in this important area of 'dealing with novelties', we introduce 'NoveltyTask', a multi-stage task to evaluate a system's performance on pipelined novelty 'detection' and 'accommodation' tasks. We provide mathematical formulation of NoveltyTask and instantiate it with the authorship attribution task that pertains to identifying the correct author of a given text. We use Amazon reviews corpus and compile a large dataset (consisting of 250k instances across 200 authors/labels) for NoveltyTask. We conduct comprehensive experiments and explore several baseline methods for the task. Our results show that the methods achieve considerably low performance making the task challenging and leaving sufficient room for improvement. Finally, we believe our work will encourage research in this underexplored area of dealing with novelties, an important step en route to developing robust systems.

cs.CL↗

arXiv2023

"John is 50 years old, can his son be 65?" Evaluating NLP Models' Understanding of Feasibility

In current NLP research, large-scale language models and their abilities are widely being discussed. Some recent works have also found notable failures of these models. Often these failure examples involve complex reasoning abilities. This work focuses on a simple commonsense ability, reasoning about when an action (or its effect) is feasible. To this end, we introduce FeasibilityQA, a question-answering dataset involving binary classification (BCQ) and multi-choice multi-correct questions (MCQ) that test understanding of feasibility. We show that even state-of-the-art models such as GPT-3, GPT-2, and T5 struggle to answer the feasibility questions correctly. Specifically, on MCQ and BCQ questions, GPT-3 achieves an accuracy of just (19%, 62%) and (25%, 64%) in zero-shot and few-shot settings, respectively. We also evaluate models by providing relevant knowledge statements required to answer the question. We find that the additional knowledge leads to a 7% gain in performance, but the overall performance still remains low. These results make one wonder how much commonsense knowledge about action feasibility is encoded in state-of-the-art models and how well they can reason about it.

cs.CL↗

arXiv2022

On the eigenvalues of the graphs $D(5, q)$

Let $q = p^e$, where $p$ is a prime and $e$ is a positive integer. The family of graphs $D(k, q)$, defined for any positive integer $k$ and prime power $q$, were introduced by Lazebnik and Ustimenko in 1995. To this day, the connected components of the graphs $D(k, q)$, provide the best known general lower bound for the size of a graph of given order and given girth. Furthermore, Ustimenko conjectured that the second largest eigenvalue of $D(k, q)$ is always less than or equal to $2\sqrt{q}$. If true, this would imply that for a fixed $q$ and $k$ growing, $D(k, q)$ would define a family of expanders that are nearly Ramanujan. In this paper we prove the smallest open case of the conjecture, showing that for all odd prime powers $q$, the second largest eigenvalue of $D(5, q)$ is less than or equal to $2\sqrt{q}$.

math.CO↗

arXiv2022

Detecting Unintended Social Bias in Toxic Language Datasets

With the rise of online hate speech, automatic detection of Hate Speech, Offensive texts as a natural language processing task is getting popular. However, very little research has been done to detect unintended social bias from these toxic language datasets. This paper introduces a new dataset ToxicBias curated from the existing dataset of Kaggle competition named "Jigsaw Unintended Bias in Toxicity Classification". We aim to detect social biases, their categories, and targeted groups. The dataset contains instances annotated for five different bias categories, viz., gender, race/ethnicity, religion, political, and LGBTQ. We train transformer-based models using our curated datasets and report baseline performance for bias identification, target generation, and bias implications. Model biases and their mitigation are also discussed in detail. Our study motivates a systematic extraction of social bias data from toxic language datasets. All the codes and dataset used for experiments in this work are publicly available

cs.CL↗

arXiv2022

Intention-Aware Navigation in Crowds with Extended-Space POMDP Planning

This paper presents a hybrid online Partially Observable Markov Decision Process (POMDP) planning system that addresses the problem of autonomous navigation in the presence of multi-modal uncertainty introduced by other agents in the environment. As a particular example, we consider the problem of autonomous navigation in dense crowds of pedestrians and among obstacles. Popular approaches to this problem first generate a path using a complete planner (e.g., Hybrid A*) with ad-hoc assumptions about uncertainty, then use online tree-based POMDP solvers to reason about uncertainty with control over a limited aspect of the problem (i.e. speed along the path). We present a more capable and responsive real-time approach enabling the POMDP planner to control more degrees of freedom (e.g., both speed AND heading) to achieve more flexible and efficient solutions. This modification greatly extends the region of the state space that the POMDP planner must reason over, significantly increasing the importance of finding effective roll-out policies within the limited computational budget that real time control affords. Our key insight is to use multi-query motion planning techniques (e.g., Probabilistic Roadmaps or Fast Marching Method) as priors for rapidly generating efficient roll-out policies for every state that the POMDP planning tree might reach during its limited horizon search. Our proposed approach generates trajectories that are safe and significantly more efficient than the previous approach, even in densely crowded dynamic environments with long planning horizons.

cs.RO↗

arXiv2022

Surgical Phase Recognition in Laparoscopic Cholecystectomy

Automatic recognition of surgical phases in surgical videos is a fundamental task in surgical workflow analysis. In this report, we propose a Transformer-based method that utilizes calibrated confidence scores for a 2-stage inference pipeline, which dynamically switches between a baseline model and a separately trained transition model depending on the calibrated confidence level. Our method outperforms the baseline model on the Cholec80 dataset, and can be applied to a variety of action segmentation methods.

cs.CV↗

arXiv2022

Distribution of Quantum Circuits Over General Quantum Networks

Near-term quantum computers can hold only a small number of qubits. One way to facilitate large-scale quantum computations is through a distributed network of quantum computers. In this work, we consider the problem of distributing quantum programs represented as quantum circuits across a quantum network of heterogeneous quantum computers, in a way that minimizes the overall communication cost required to execute the distributed circuit. We consider two ways of communicating: cat-entanglement that creates linked copies of qubits across pairs of computers, and teleportation. The heterogeneous computers impose constraints on cat-entanglement and teleportation operations that can be chosen by an algorithm. We first focus on a special case that only allows cat-entanglements and not teleportations for communication. We provide a two-step heuristic for solving this specialized setting: (i) finding an assignment of qubits to computers using Tabu search, and (ii) using an iterative greedy algorithm designed for a constrained version of the set cover problem to determine cat-entanglement operations required to execute gates locally. For the general case, which allows both forms of communication, we propose two algorithms that subdivide the quantum circuit into several portions and apply the heuristic for the specialized setting on each portion. Teleportations are then used to stitch together the solutions for each portion. Finally, we simulate our algorithms on a wide range of randomly generated quantum networks and circuits, and study the properties of their results with respect to several varying parameters.

cs.ET↗

arXiv2022

Hollywood Identity Bias Dataset: A Context Oriented Bias Analysis of Movie Dialogues

Movies reflect society and also hold power to transform opinions. Social biases and stereotypes present in movies can cause extensive damage due to their reach. These biases are not always found to be the need of storyline but can creep in as the author's bias. Movie production houses would prefer to ascertain that the bias present in a script is the story's demand. Today, when deep learning models can give human-level accuracy in multiple tasks, having an AI solution to identify the biases present in the script at the writing stage can help them avoid the inconvenience of stalled release, lawsuits, etc. Since AI solutions are data intensive and there exists no domain specific data to address the problem of biases in scripts, we introduce a new dataset of movie scripts that are annotated for identity bias. The dataset contains dialogue turns annotated for (i) bias labels for seven categories, viz., gender, race/ethnicity, religion, age, occupation, LGBTQ, and other, which contains biases like body shaming, personality bias, etc. (ii) labels for sensitivity, stereotype, sentiment, emotion, emotion intensity, (iii) all labels annotated with context awareness, (iv) target groups and reason for bias labels and (v) expert-driven group-validation process for high quality annotations. We also report various baseline performances for bias identification and category detection on our dataset.

cs.CL↗

arXiv2022

Pre-Distribution of Entanglements in Quantum Networks

Quantum network communication is challenging, as the No-Cloning theorem in quantum regime makes many classical techniques inapplicable. For long-distance communication, the only viable approach is teleportation of quantum states, which requires a prior distribution of entangled pairs (EPs) of qubits. Establishment of EPs across remote nodes can incur significant latency due to the low probability of success of the underlying physical processes. To reduce EP generation latency, prior works have looked at selection of efficient entanglement-routing paths and simultaneous use of multiple such paths for EP generation. In this paper, we propose and investigate a complementary technique to reduce EP generation latency--to pre-distribute EPs over certain (pre-determined) pairs of network nodes; these pre-distributed EPs can then be used to generate EPs for the requested pairs, when needed, with lower generation latency. For such an pre-distribution approach to be most effective, we need to address an optimization problem of selection of node-pairs where the EPs should be pre-distributed to minimize the generation latency of expected EP requests, under a given cost constraint. In this paper, we appropriately formulate the above optimization problem and design two efficient algorithms, one of which is a greedy approach based on an approximation algorithm for a special case. Via extensive evaluations over the NetSquid simulator, we demonstrate the effectiveness of our approach and developed techniques; we show that our developed algorithms outperform a naive approach by up to an order of magnitude.

quant-ph↗

arXiv2022

Constructions of cospectral graphs with different zero forcing numbers

Several researchers have recently explored various graph parameters that can or cannot be characterized by the spectrum of a matrix associated with a graph. In this paper we show that several NP-hard zero forcing numbers are not characterized by the spectra of several types of associated matrices with a graph. In particular, we consider standard zero forcing, positive semidefinite zero forcing, and skew zero forcing, and provide constructions of infinite families of pairs of cospectral graphs which have different values for these numbers. We explore several methods for obtaining these cospectral graphs including using graph products, graph joins, and graph switching. Among these, we provide a construction involving regular adjacency cospectral graphs; the regularity of this construction also implies cospectrality with respect to several other matrices including the Laplacian, signless Laplacian, and normalized Laplacian. We also provide a construction where pairs of cospectral graphs can have an arbitrarily large difference between their zero forcing numbers.

math.CO↗