Temporal question answering (QA) is a special category of complex question answering task that requires reasoning over facts asserting time intervals of events.Previous works have predominately relied on Knowledge Base Question Answering (KBQA) for temporal QA.One of the major challenges faced by these systems is their inability to retrieve all relevant facts due to factors such as incomplete KB and entity/relation linking errors (Patidar et al., 2022).A failure to fetch even a single fact will block KBQA from computing the answer.Such cases of KB incompleteness are even more profound in the temporal context.To address this issue, we explore an interesting direction where a targeted temporal fact extraction technique is used to assist KBQA whenever it fails to retrieve temporal facts from the KB.We model the extraction problem as an open-domain question answering task using offthe-shelf language models.This way, we target to extract from textual resources those facts that failed to get retrieved from the KB.Experimental results on two temporal QA benchmarks show promising ~30% & ~10% relative improvements in answer accuracies without any additional training cost.

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. 2023.

Knowledge Graph Question Answering (KGQA) has become a prominent area in natural language processing due to the emergence of large scale Knowledge Graphs (KGs). Semantic parsing based approach is the predominant direction to solve the KGQA task where natural language question is translated into a logic form such as SPARQL query. Recently Neural Machine Translation (NMT) based approaches are gaining momentum in order to translate natural language query to structured query languages thereby solving the KGQA task. However, most of these methods struggle with out-of-vocabulary words where test entities and relations are not seen during training time. In this work, we propose a modular two stage neural architecture to solve the KGQA task. Stage-I of our approach comprises a NMT-based seq2seq module that translates a question into a sketch of the desired SPARQL query called a SPARQL silhouette. Stage-II of our approach comprises a Neural Graph Search (NGS) module which aims to improve the quality of the SPARQL silhouette by detecting the right relations in the underlying knowledge graph. Experimental results show that we achieve substantial improvements and obtain state-of-the-art performance or comparable results to the best performing systems on two benchmark datasets. We believe, our proposed approach is novel and will lead to dynamic KGQA solutions that are well-suited for practical applications.

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). 2021.

Research on the task of Reading Comprehension style Question Answering (RCQA) has gained momentum in recent years due to the emergence of human annotated datasets and associated leaderboards, for example CoQA, HotpotQA, SQuAD, TriviaQA, etc. While state-of-the-art has advanced considerably, there is still ample opportunity to advance it further on some important variants of the RCQA task. In this paper, we propose a novel deep neural architecture, called TAP (Translucent Answer Prediction), to identify answers and evidence (in the form of supporting facts) in an RCQA task requiring multi-hop reasoning. TAP comprises two loosely coupled networks – Local and Global Interaction eXtractor (LoGIX) and Answer Predictor (AP). LoGIX predicts supporting facts, whereas AP consumes these predicted supporting facts to predict the answer span. The novel design of LoGIX is inspired by two key design desiderata – local context and global interaction– that we identified by analyzing examples of multi-hop RCQA task. The loose coupling between LoGIX and the AP reveals the set of sentences used by the AP in predicting an answer. Therefore, answer predictions of TAP can be interpreted in a translucent manner. TAP offers state-of-the-art performance on the HotpotQA (Yang et al. 2018) dataset – an apt dataset for multi-hop RCQA task – as it occupies Rank-1 on its leaderboard (https://hotpotqa.github.io/) at the time of submission.

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. 2020.

Quantum logic inspired embedding (aka Quantum Embedding (QE)) of a Knowledge-Base (KB) was proposed recently by Garg:2019. It is claimed that the QE preserves the logical structure of the input KB given in the form of unary and binary predicates hierarchy. Such structure preservation allows one to perform Boolean logic style deductive reasoning directly over these embedding vectors. The original QE idea, however, is limited to the transductive (not inductive) setting. Moreover, the original QE scheme runs quite slow on real applications involving millions of entities. This paper alleviates both of these key limitations. We start by reformulating the original QE problem to allow for the induction. On the way, we also underscore some interesting analytic and geometric properties of the solution and leverage them to design a faster training scheme. As an application, we show that one can achieve state-of-the-art performance on the well-known NLP task of fine-grained entity type classification by using the inductive QE approach. Our training runs 9-times faster than the original QE scheme on this task.

Higher order MRF-MAP formulation has been shown to improve solutions in many popular computer vision problems. Most of these approaches have considered hand tuned clique potentials only. Over the last few years, while there has been steady improvement in inference techniques making it possible to perform tractable inference for clique sizes even up to few hundreds, the learning techniques for such clique potentials have been limited to clique size of merely 3 or 4. In this paper, we investigate learning of higher order clique potentials up to clique size of 16. We use structural support vector machine (SSVM), a large-margin learning framework, to learn higher order potential functions from data. It formulates the training problem as a quadratic programming problem (QP) that requires solving MAP inference problems in the inner iteration. We introduce multiple innovations in the formulation by introducing soft submodularity constraints which keep QP constraints manageable and at the same time makes MAP inference tractable. Unlike contemporary approaches to solving the original problem using the cutting plane technique, we propose to solve the problem using subgradient descent. This allows us to scale for problems with clique size even up to 16. We give indicative experiments to show the improvement gained in real applications using learned potentials instead of hand tuned ones.