Dinesh Garg


2024

pdf bib
Read between the lines - Functionality Extraction From READMEs
Prince Kumar | Srikanth Tamilselvam | Dinesh Garg
Findings of the Association for Computational Linguistics: NAACL 2024

While text summarization is a well-known NLP task, in this paper, we introduce a novel and useful variant of it called functionality extraction from Git README files. Though this task is a text2text generation at an abstract level, it involves its own peculiarities and challenges making existing text2text generation systems not very useful. The motivation behind this task stems from a recent surge in research and development activities around the use of large language models for code-related tasks, such as code refactoring, code summarization, etc. We also release a human-annotated dataset called FuncRead, and develop a battery of models for the task. Our exhaustive experimentation shows that small size fine-tuned models beat any baseline models that can be designed using popular black-box or white-box large language models (LLMs) such as ChatGPT and Bard. Our best fine-tuned 7 Billion CodeLlama model exhibit 70% and 20% gain on the F1 score against ChatGPT and Bard respectively.

2023

pdf bib
Image Manipulation via Multi-Hop Instructions - A New Dataset and Weakly-Supervised Neuro-Symbolic Approach
Harman Singh | Poorva Garg | Mohit Gupta | Kevin Shah | Ashish Goswami | Satyam Modi | Arnab Mondal | Dinesh Khandelwal | Dinesh Garg | Parag Singla
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

We are interested in image manipulation via natural language text – a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We extend recently proposed Neuro Symbolic Concept Learning (NSCL), which has been quite effective for the task of Visual Question Answering (VQA), for the task of image manipulation. Our system referred to as NeuroSIM can perform complex multi-hop reasoning over multi-object scenes and only requires weak supervision in the form of annotated data for VQA. NeuroSIM parses an instruction into a symbolic program, based on a Domain Specific Language (DSL) comprising of object attributes and manipulation operations, that guides its execution. We create a new dataset for the task, and extensive experiments demonstrate that NeuroSIM is highly competitive with or beats SOTA baselines that make use of supervised data for manipulation.

2022

pdf bib
Zero-shot Entity Linking with Less Data
G P Shrivatsa Bhargav | Dinesh Khandelwal | Saswati Dana | Dinesh Garg | Pavan Kapanipathi | Salim Roukos | Alexander Gray | L Venkata Subramaniam
Findings of the Association for Computational Linguistics: NAACL 2022

Entity Linking (EL) maps an entity mention in a natural language sentence to an entity in a knowledge base (KB). The Zero-shot Entity Linking (ZEL) extends the scope of EL to unseen entities at the test time without requiring new labeled data. BLINK (BERT-based) is one of the SOTA models for ZEL. Interestingly, we discovered that BLINK exhibits diminishing returns, i.e., it reaches 98% of its performance with just 1% of the training data and the remaining 99% of the data yields only a marginal increase of 2% in the performance. While this extra 2% gain makes a huge difference for downstream tasks, training BLINK on large amounts of data is very resource-intensive and impractical. In this paper, we propose a neuro-symbolic, multi-task learning approach to bridge this gap. Our approach boosts the BLINK’s performance with much less data by exploiting an auxiliary information about entity types. Specifically, we train our model on two tasks simultaneously - entity linking (primary task) and hierarchical entity type prediction (auxiliary task). The auxiliary task exploits the hierarchical structure of entity types. Our approach achieves superior performance on ZEL task with significantly less training data. On four different benchmark datasets, we show that our approach achieves significantly higher performance than SOTA models when they are trained with just 0.01%, 0.1%, or 1% of the original training data. Our code is available at https://github.com/IBM/NeSLET.

pdf bib
SYGMA: A System for Generalizable and Modular Question Answering Over Knowledge Bases
Sumit Neelam | Udit Sharma | Hima Karanam | Shajith Ikbal | Pavan Kapanipathi | Ibrahim Abdelaziz | Nandana Mihindukulasooriya | Young-Suk Lee | Santosh Srivastava | Cezar Pendus | Saswati Dana | Dinesh Garg | Achille Fokoue | G P Shrivatsa Bhargav | Dinesh Khandelwal | Srinivas Ravishankar | Sairam Gurajada | Maria Chang | Rosario Uceda-Sosa | Salim Roukos | Alexander Gray | Guilherme Lima | Ryan Riegel | Francois Luus | L V Subramaniam
Findings of the Association for Computational Linguistics: EMNLP 2022

Knowledge Base Question Answering (KBQA) involving complex reasoning is emerging as an important research direction. However, most KBQA systems struggle with generalizability, particularly on two dimensions: (a) across multiple knowledge bases, where existing KBQA approaches are typically tuned to a single knowledge base, and (b) across multiple reasoning types, where majority of datasets and systems have primarily focused on multi-hop reasoning. In this paper, we present SYGMA, a modular KBQA approach developed with goal of generalization across multiple knowledge bases and multiple reasoning types. To facilitate this, SYGMA is designed as two high level modules: 1) KB-agnostic question understanding module that remain common across KBs, and generates logic representation of the question with high level reasoning constructs that are extensible, and 2) KB-specific question mapping and answering module to address the KB-specific aspects of the answer extraction. We evaluated SYGMA on multiple datasets belonging to distinct knowledge bases (DBpedia and Wikidata) and distinct reasoning types (multi-hop and temporal). State-of-the-art or competitive performances achieved on those datasets demonstrate its generalization capability.

2021

pdf bib
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Pavan Kapanipathi | Ibrahim Abdelaziz | Srinivas Ravishankar | Salim Roukos | Alexander Gray | Ramón Fernandez Astudillo | Maria Chang | Cristina Cornelio | Saswati Dana | Achille Fokoue | Dinesh Garg | Alfio Gliozzo | Sairam Gurajada | Hima Karanam | Naweed Khan | Dinesh Khandelwal | Young-Suk Lee | Yunyao Li | Francois Luus | Ndivhuwo Makondo | Nandana Mihindukulasooriya | Tahira Naseem | Sumit Neelam | Lucian Popa | Revanth Gangi Reddy | Ryan Riegel | Gaetano Rossiello | Udit Sharma | G P Shrivatsa Bhargav | Mo Yu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Explanations for CommonsenseQA: New Dataset and Models
Shourya Aggarwal | Divyanshu Mandowara | Vishwajeet Agrawal | Dinesh Khandelwal | Parag Singla | Dinesh Garg
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

CommonsenseQA (CQA) (Talmor et al., 2019) dataset was recently released to advance the research on common-sense question answering (QA) task. Whereas the prior work has mostly focused on proposing QA models for this dataset, our aim is to retrieve as well as generate explanation for a given (question, correct answer choice, incorrect answer choices) tuple from this dataset. Our explanation definition is based on certain desiderata, and translates an explanation into a set of positive and negative common-sense properties (aka facts) which not only explain the correct answer choice but also refute the incorrect ones. We human-annotate a first-of-its-kind dataset (called ECQA) of positive and negative properties, as well as free-flow explanations, for 11K QA pairs taken from the CQA dataset. We propose a latent representation based property retrieval model as well as a GPT-2 based property generation model with a novel two step fine-tuning procedure. We also propose a free-flow explanation generation model. Extensive experiments show that our retrieval model beats BM25 baseline by a relative gain of 100% in F1 score, property generation model achieves a respectable F1 score of 36.4, and free-flow generation model achieves a similarity score of 61.9, where last two scores are based on a human correlated semantic similarity metric.

2020

pdf bib
The TechQA Dataset
Vittorio Castelli | Rishav Chakravarti | Saswati Dana | Anthony Ferritto | Radu Florian | Martin Franz | Dinesh Garg | Dinesh Khandelwal | Scott McCarley | Michael McCawley | Mohamed Nasr | Lin Pan | Cezar Pendus | John Pitrelli | Saurabh Pujar | Salim Roukos | Andrzej Sakrajda | Avi Sil | Rosario Uceda-Sosa | Todd Ward | Rong Zhang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We introduce TECHQA, a domain-adaptation question answering dataset for the technical support domain. The TECHQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on a technical forum, rather than questions generated specifically for a competition or a task. Second, it has a real-world size – 600 training, 310 dev, and 490 evaluation question/answer pairs – thus reflecting the cost of creating large labeled datasets with actual data. Hence, TECHQA is meant to stimulate research in domain adaptation rather than as a resource to build QA systems from scratch. TECHQA was obtained by crawling the IBMDeveloper and DeveloperWorks forums for questions with accepted answers provided in an IBM Technote—a technical document that addresses a specific technical issue. We also release a collection of the 801,998 Technotes available on the web as of April 4, 2019 as a companion resource that can be used to learn representations of the IT domain language.

pdf bib
Span Selection Pre-training for Question Answering
Michael Glass | Alfio Gliozzo | Rishav Chakravarti | Anthony Ferritto | Lin Pan | G P Shrivatsa Bhargav | Dinesh Garg | Avi Sil
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). BERT is pretrained on two auxiliary tasks: Masked Language Model and Next Sentence Prediction. In this paper we introduce a new pre-training task inspired by reading comprehension to better align the pre-training from memorization to understanding. Span Selection PreTraining (SSPT) poses cloze-like training instances, but rather than draw the answer from the model’s parameters, it is selected from a relevant passage. We find significant and consistent improvements over both BERT-BASE and BERT-LARGE on multiple Machine Reading Comprehension (MRC) datasets. Specifically, our proposed model has strong empirical evidence as it obtains SOTA results on Natural Questions, a new benchmark MRC dataset, outperforming BERT-LARGE by 3 F1 points on short answer prediction. We also show significant impact in HotpotQA, improving answer prediction F1 by 4 points and supporting fact prediction F1 by 1 point and outperforming the previous best system. Moreover, we show that our pre-training approach is particularly effective when training data is limited, improving the learning curve by a large amount.

2017

pdf bib
Latent Space Embedding for Retrieval in Question-Answer Archives
Deepak P | Dinesh Garg | Shirish Shevade
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Community-driven Question Answering (CQA) systems such as Yahoo! Answers have become valuable sources of reusable information. CQA retrieval enables usage of historical CQA archives to solve new questions posed by users. This task has received much recent attention, with methods building upon literature from translation models, topic models, and deep learning. In this paper, we devise a CQA retrieval technique, LASER-QA, that embeds question-answer pairs within a unified latent space preserving the local neighborhood structure of question and answer spaces. The idea is that such a space mirrors semantic similarity among questions as well as answers, thereby enabling high quality retrieval. Through an empirical analysis on various real-world QA datasets, we illustrate the improved effectiveness of LASER-QA over state-of-the-art methods.