Search Results for author:
Found 53 papers, 18 papers with code
Building Goal-oriented Document-grounded Dialogue Systems
In this paper, we describe our systems for solving the two Doc2Dial shared task: knowledge identification and response generation.
R3 : Refined Retriever-Reader pipeline for Multidoc2dial
In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset.
Semantic Augmentation in Images using Language
Deep Learning models are incredibly data-hungry and require very large labeled datasets for supervised learning.
Attribution Regularization for Multimodal Paradigms
This research project aims to address these challenges by proposing a novel regularization term that encourages multimodal models to effectively utilize information from all modalities when making decisions.
VISREAS: Complex Visual Reasoning with Unanswerable Questions
The unique feature of this task, validating question answerability with respect to an image before answering, and the poor performance of state-of-the-art models inspired the design of a new modular baseline, LOGIC2VISION that reasons by producing and executing pseudocode without any external modules to generate the answer.
Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-Imagination
The potential of Vision-Language Models (VLMs) often remains underutilized in handling complex text-based problems, particularly when these problems could benefit from visual representation.
Difference-Masking: Choosing What to Mask in Continued Pretraining
The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks.
Chain-of-Skills: A Configurable Model for Open-domain Question Answering
Our approach outperforms recent self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.
Ranked #4 on
Question Answering
on HotpotQA
Using Implicit Feedback to Improve Question Generation
Each generated question, after being corrected by the user, is used as a new seed in the next iteration, so more patterns are created each time.
InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers
Unlike InPars, InPars-light uses 7x-100x smaller ranking models and only a freely available language model BLOOM, which -- as we found out -- produced more accurate rankers compared to a proprietary GPT-3 model.
Knowledge-driven Scene Priors for Semantic Audio-Visual Embodied Navigation
We also define a new audio-visual navigation sub-task, where agents are evaluated on novel sounding objects, as opposed to unheard clips of known objects.
Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving
The feasibility of collecting a large amount of expert demonstrations has inspired growing research interests in learning-to-drive settings, where models learn by imitating the driving behaviour from experts.
Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge
We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources.
Coalescing Global and Local Information for Procedural Text Understanding
In this paper, we propose Coalescing Global and Local Information (CGLI), a new model that builds entity- and timestep-aware input representations (local input) considering the whole context (global input), and we jointly model the entity states with a structured prediction objective (global output).
Understanding Performance of Long-Document Ranking Models through Comprehensive Evaluation and Leaderboarding
Most other models had poor zero-shot performance (sometimes at a random baseline level) but outstripped MaxP by as much 13-28\% after finetuning.
Table Retrieval May Not Necessitate Table-specific Model Design
In this work, we focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval, or can a simpler text-based model be effectively used to achieve a similar result?"
Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing
In the first stage of the challenge, we evaluate an autonomous agent's ability to drive as fast as possible, while adhering to safety constraints.
Open Domain Question Answering with A Unified Knowledge Interface
The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge.
Safe Autonomous Racing via Approximate Reachability on Ego-vision
Given the nature of the task, autonomous agents need to be able to 1) identify and avoid unsafe scenarios under the complex vehicle dynamics, and 2) make sub-second decision in a fast-changing environment.
Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models
In this paper, we investigate what models learn from commonsense reasoning datasets.
Learn-to-Race: A Multimodal Control Environment for Autonomous Racing
Existing research on autonomous driving primarily focuses on urban driving, which is insufficient for characterising the complex driving behaviour underlying high-speed racing.
Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection
Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models.
Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering
Guided by a set of hypotheses, the framework studies how to transform various pre-existing knowledge resources into a form that is most effective for pre-training models.
Flexible retrieval with NMSLIB and FlexNeuART
Our objective is to introduce to the NLP community an existing k-NN search library NMSLIB, a new retrieval toolkit FlexNeuART, as well as their integration capabilities.
Bend but Don't Break? Multi-Challenge Stress Test for QA Models
The field of question answering (QA) has seen rapid growth in new tasks and modeling approaches in recent years.
Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
Non-extractive commonsense QA remains a challenging AI task, as it requires systems to reason about, synthesize, and gather disparate pieces of information, in order to generate responses to queries.
Ranked #15 on
Common Sense Reasoning
on CommonsenseQA
Pruning Algorithms for Low-Dimensional Non-metric k-NN Search: A Case Study
We consider two known data-driven approaches to extend these rules to non-metric spaces: TriGen and a piece-wise linear approximation of the pruning rule.
Accurate and Fast Retrieval for Complex Non-metric Data via Neighborhood Graphs
We demonstrate that a graph-based search algorithm-relying on the construction of an approximate neighborhood graph-can directly work with challenging non-metric and/or non-symmetric distances without resorting to metric-space mapping and/or distance symmetrization, which, in turn, lead to substantial performance degradation.
Sieg at MEDIQA 2019: Multi-task Neural Ensemble for Biomedical Inference and Entailment
This paper presents a multi-task learning approach to natural language inference (NLI) and question entailment (RQE) in the biomedical domain.
Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations
This paper presents the submissions by Team Dr. Quad to the ACL-BioNLP 2019 shared task on Textual Inference and Question Entailment in the Medical Domain.
Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment
Parallel deep learning architectures like fine-tuned BERT and MT-DNN, have quickly become the state of the art, bypassing previous deep and shallow learning methods by a large margin.
Storyboarding of Recipes: Grounded Contextual Generation
We introduce a dataset for sequential procedural (how-to) text generation from images in cooking domain.
Ontology-Based Retrieval \& Neural Approaches for BioASQ Ideal Answer Generation
The ever-increasing magnitude of biomedical information sources makes it difficult and time-consuming for a human researcher to find the most relevant documents and pinpointed answers for a specific question or topic when using only a traditional search engine.
Extraction Meets Abstraction: Ideal Answer Generation for Biomedical Questions
The growing number of biomedical publications is a challenge for human researchers, who invest considerable effort to search for relevant documents and pinpointed answers.
BioAMA: Towards an End to End BioMedical Question Answering System
In this paper, we present a novel Biomedical Question Answering system, BioAMA: {``}Biomedical Ask Me Anything{''} on task 5b of the annual BioASQ challenge.
Code-Mixed Question Answering Challenge: Crowd-sourcing Data and Techniques
As a first step towards fostering research which supports CM in NLP applications, we systematically crowd-sourced and curated an evaluation dataset for factoid question answering in three CM languages - Hinglish (Hindi+English), Tenglish (Telugu+English) and Tamlish (Tamil+English) which belong to two language families (Indo-Aryan and Dravidian).
Comparative Analysis of Neural QA models on SQuAD
The task of Question Answering has gained prominence in the past few decades for testing the ability of machines to understand natural language.
Towards Inference-Oriented Reading Comprehension: ParallelQA
In this paper, we investigate the tendency of end-to-end neural Machine Reading Comprehension (MRC) models to match shallow patterns rather than perform inference-oriented reasoning on RC benchmarks.
CMU LiveMedQA at TREC 2017 LiveQA: A Consumer Health Question Answering System
In this paper, we present LiveMedQA, a question answering system that is optimized for consumer health question.
Steering Output Style and Topic in Neural Response Generation
We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation.
Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models
Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose.
How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing
Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording.
Tackling Biomedical Text Summarization: OAQA at BioASQ 5B
In this paper, we describe our participation in phase B of task 5b of the fifth edition of the annual BioASQ challenge, which includes answering factoid, list, yes-no and summary questions from biomedical data.
Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models
Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose.
CharManteau: Character Embedding Models For Portmanteau Creation
Portmanteaus are a word formation phenomenon where two words are combined to form a new word.
Structural Embedding of Syntactic Trees for Machine Comprehension
Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees.
Ranked #40 on
Question Answering
on SQuAD1.1 dev
LAPPS/Galaxy: Current State and Next Steps
The US National Science Foundation (NSF) SI2-funded LAPPS/Galaxy project has developed an open-source platform for enabling complex analyses while hiding complexities associated with underlying infrastructure, that can be accessed through a web interface, deployed on any Unix system, or run from the cloud.
Permutation Search Methods are Efficient, Yet Faster Search is Possible
The underpinning assumption is that, for both metric and non-metric spaces, the distance between permutations is a good proxy for the distance between original points.
The Language Application Grid
The Language Application (LAPPS) Grid project is establishing a framework that enables language service discovery, composition, and reuse and promotes sustainability, manageability, usability, and interoperability of natural language Processing (NLP) components.
