Search Results for author:
Found 61 papers, 35 papers with code
RETINAQA : A Knowledge Base Question Answering Model Robust to both Answerable and Unanswerable Questions
We propose a new model for KBQA named RetinaQA that is robust against unaswerability.
PuzzleBench: Can LLMs Solve Challenging First-Order Combinatorial Reasoning Problems?
Recent works show that the largest of the large language models (LLMs) can solve many simple reasoning tasks expressed in natural language, without any/much supervision.
Guided Prompting in SAM for Weakly Supervised Cell Segmentation in Histopathological Images
In response, we investigate guiding the prompting procedure in SAM for weakly supervised cell segmentation when only bounding box supervision is available.
Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning
Additional experiments in the in-domain setting show that FuSIC-KBQA also outperforms SoTA KBQA models when training data is limited.
CoRE-CoG: Conversational Recommendation of Entities using Constrained Generation
End-to-end conversational recommendation systems (CRS) generate responses by leveraging both dialog history and a knowledge base (KB).
Ensembling Textual and Structure-Based Models for Knowledge Graph Completion
We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connectivity structure of the Knowledge Graph (KG).
ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters
We posit that for more effective cross-lingual transfer, instead of just one source LA, we need to leverage LAs of multiple (linguistically or geographically related) source languages, both at train and test-time - which we investigate via our novel neural architecture, ZGUL.
AutoMix: Automatically Mixing Language Models
Large language models (LLMs) are now available from cloud API providers in various sizes and configurations.
Towards Fair and Calibrated Models
Further, we show that ensuring group-wise calibration with respect to the sensitive attributes automatically results in a fair model under our definition.
Reconstructing Materials Tetrahedron: Challenges in Materials Information Extraction
Discovery of new materials has a documented history of propelling human progress for centuries and more.
MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models
Further, we evaluate the performance of GPT-3. 5 and GPT-4 models on solving these questions via zero-shot and chain of thought prompting.
DKAF: KB Arbitration for Learning Task-Oriented Dialog Systems with Dialog-KB Inconsistencies
In this work, we define the novel problem of learning a TOD agent with dialog-KB inconsistencies in the training data.
Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models
In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs.
Ranked #1 on
Overall - Test
on JEEBench
Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs
A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution.
NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs
While Knowledge Graph Completion (KGC) on static facts is a matured field, Temporal Knowledge Graph Completion (TKGC), that incorporates validity time into static facts is still in its nascent stage.
DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting
While there exist multiple, general-purpose, deep learning-based object detection and counting methods, they may not readily transfer to detecting and counting cells in medical images, due to the limited data, presence of tiny overlapping objects, multiple cell types, severe class-imbalance, minute differences in size/shape of cells, etc.
Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions
When answering natural language questions over knowledge bases, missing facts, incomplete schema and limited scope naturally lead to many questions being unanswerable.
mOKB6: A Multilingual Open Knowledge Base Completion Benchmark
Automated completion of open knowledge bases (Open KBs), which are constructed from triples of the form (subject phrase, relation phrase, object phrase), obtained via open information extraction (Open IE) system, are useful for discovering novel facts that may not be directly present in the text.
"Covid vaccine is against Covid but Oxford vaccine is made at Oxford!" Semantic Interpretation of Proper Noun Compounds
Proper noun compounds, e. g., "Covid vaccine", convey information in a succinct manner (a "Covid vaccine" is a "vaccine that immunizes against the Covid disease").
A Solver-Free Framework for Scalable Learning in Neural ILP Architectures
Experiments on several problems, both perceptual as well as symbolic, which require learning the constraints of an ILP, show that our approach has superior performance and scales much better compared to purely neural baselines and other state-of-the-art models that require solver-based training.
DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles
A crucial component in the curation of KB for a scientific domain (e. g., materials science, foods & nutrition, fuels) is information extraction from tables in the domain's published research articles.
GoalNet: Inferring Conjunctive Goal Predicates from Human Plan Demonstrations for Robot Instruction Following
Our goal is to enable a robot to learn how to sequence its actions to perform tasks specified as natural language instructions, given successful demonstrations from a human partner.
Matching Papers and Reviewers at Large Conferences
Peer-reviewed conferences, the main publication venues in CS, rely critically on matching highly qualified reviewers for each paper.
Neural Models for Output-Space Invariance in Combinatorial Problems
One drawback of the proposed architectures, which are often based on Graph Neural Networks (GNN), is that they cannot generalize across the size of the output space from which variables are assigned a value, for example, set of colors in a GCP, or board-size in sudoku.
PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction
The contextual embeddings of tokens are aggregated using attention with the candidate relation as query -- this summary of whole passage predicts the candidate relation.
MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction
Here, we present a materials-aware language model, namely, MatSciBERT, which is trained on a large corpus of scientific literature published in the materials domain.
End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs
We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e. g., car not starting).
Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record.
Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation
We evaluate our method on four public medical segmentation datasets and a novel histopathology dataset that we introduce.
End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks
A key limitation is that such neural-to-symbolic models can only be trained end-to-end for tasks where the output space is symbolic.
TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators
We introduce a novel neural model, termed TANGO, for predicting task-specific tool interactions, trained using demonstrations from human teachers instructing a virtual robot.
Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment
Almost all of existing KGC research is applicable to only one KG at a time, and in one language only.
Ranked #2 on
Knowledge Graph Completion
on DBP-5L (Greek)
CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion
Pre-trained language models (LMs) like BERT have shown to store factual knowledge about the world.
DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction
We show that these characteristics lead to a gross overestimation of the model performance.
OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction
This IGL based coordination analyzer helps our OpenIE system handle complicated coordination structures, while also establishing a new state of the art on the task of coordination analysis, with a 12. 3 pts improvement in F1 over previous analyzers.
Ranked #1 on
Open Information Extraction
on WiRe57
Joint Spatio-Textual Reasoning for Answering Tourism Questions
In response, we develop the first joint spatio-textual reasoning model, which combines geo-spatial knowledge with information in textual corpora to answer questions.
Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces
Our framework uses a selection module, whose goal is to dynamically determine, for every input, the solution that is most effective for training the network parameters in any given learning iteration.
ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis
When compared to a graph neural network baseline, it achieves 14-27% accuracy improvement for predicting known tools from new world scenes, and 44-67% improvement in generalization for novel objects not encountered during training.
Robotics
IMoJIE: Iterative Memory-Based Joint Open Information Extraction
While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task.
Knowledge Base Completion: Baseline strikes back (Again)
Most existing methods train with a small number of negative samples for each positive instance in these datasets to save computational costs.
Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols
Temporal knowledge bases associate relational (s, r, o) triples with a set of times (or a single time instant) when the relation is valid.
Ranked #1 on
Link Prediction
on Wikidata12k
Why and when should you pool? Analyzing Pooling in Recurrent Architectures
We find that pooling-based architectures substantially differ from their non-pooling equivalents in their learning ability and positional biases--which elucidate their performance benefits.
Regex Queries over Incomplete Knowledge Bases
In response, we develop RotatE-Box -- a novel combination of RotatE and box embeddings.
Unsupervised Learning of KB Queries in Task-Oriented Dialogs
Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses.
A Simple Yet Strong Pipeline for HotpotQA
State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition.
Ranked #37 on
Question Answering
on HotpotQA
Symbolic Network: Generalized Neural Policies for Relational MDPs
We present SymNet, the first neural approach for solving RMDPs that are expressed in the probabilistic planning language of RDDL.
OxKBC: Outcome Explanation for Factorization Based Knowledge Base Completion
State-of-the-art models for Knowledge Base Completion (KBC) are based on tensor factorization (TF), e. g, DistMult, ComplEx.
A Primal Dual Formulation For Deep Learning With Constraints
In this paper, we present a constrained optimization formulation for training a deep network with a given set of hard constraints on output labels.
Large Scale Question Answering using Tourism Data
We introduce the novel task of answering entity-seeking recommendation questions using a collection of reviews that describe candidate answer entities.
Size Independent Neural Transfer for RDDL Planning
To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on other problems of the same domain can rapidly transfer to a new problem.
Transfer of Deep Reactive Policies for MDP Planning
We then learn an RL agent in the embedding space, making a near zero-shot transfer possible, i. e., without much training on the new instance, and without using the domain simulator at all.
Block-Value Symmetries in Probabilistic Graphical Models
These orbits are represented compactly using permutations over variables, and variable-value (VV) pairs, but they can miss several state symmetries in a domain.
Disentangling Language and Knowledge in Task-Oriented Dialogs
We also systematically modify existing datasets to measure disentanglement and show BoSsNet to be robust to KB modifications.
Non-Count Symmetries in Boolean & Multi-Valued Prob. Graphical Models
Moreover, algorithms for lifted inference in multi-valued domains also compute a multi-valued extension of count symmetries only.
Coarse-to-Fine Lifted MAP Inference in Computer Vision
We demonstrate the performance of C2F inference by developing lifted versions of two near state-of-the-art CV algorithms for stereo vision and interactive image segmentation.
Joint Matrix-Tensor Factorization for Knowledge Base Inference
If not, what characteristics of a dataset determine the performance of MF and TF models?
Octopus: A Framework for Cost-Quality-Time Optimization in Crowdsourcing
We present Octopus, an AI agent to jointly balance three conflicting task objectives on a micro-crowdsourcing marketplace - the quality of work, total cost incurred, and time to completion.
A Programming Language With a POMDP Inside
We present POAPS, a novel planning system for defining Partially Observable Markov Decision Processes (POMDPs) that abstracts away from POMDP details for the benefit of non-expert practitioners.
Contextual Symmetries in Probabilistic Graphical Models
We extend previous work on exploiting symmetries in the MCMC framework to the case of contextual symmetries.
Topological Value Iteration Algorithms
Value iteration is a powerful yet inefficient algorithm for Markov decision processes (MDPs) because it puts the majority of its effort into backing up the entire state space, which turns out to be unnecessary in many cases.
A Heuristic Search Approach to Planning with Continuous Resources in Stochastic Domains
We consider the problem of optimal planning in stochastic domains with resource constraints, where the resources are continuous and the choice of action at each step depends on resource availability.
