Aditya Srikanth Veerubhotla


2023

pdf bib
Few Shot Rationale Generation using Self-Training with Dual Teachers
Aditya Srikanth Veerubhotla | Lahari Poddar | Jun Yin | György Szarvas | Sharanya Eswaran
Findings of the Association for Computational Linguistics: ACL 2023

Self-rationalizing models that also generate a free-text explanation for their predicted labels are an important tool to build trustworthy AI applications. Since generating explanations for annotated labels is a laborious and costly process, recent models rely on large pretrained language models (PLMs) as their backbone and few-shot learning. In this work we explore a self-training approach leveraging both labeled and unlabeled data to further improve few-shot models, under the assumption that neither human written rationales nor annotated task labels are available at scale. We introduce a novel dual-teacher learning framework, which learns two specialized teacher models for task prediction and rationalization using self-training and distills their knowledge into a multi-tasking student model that can jointly generate the task label and rationale. Furthermore, we formulate a new loss function, Masked Label Regularization(MLR) which promotes explanations to be strongly conditioned on predicted labels. Evaluation on three public datasets demonstrate that the proposed methods are effective in modeling task labels and generating faithful rationales.

2022

pdf bib
R3 : Refined Retriever-Reader pipeline for Multidoc2dial
Srijan Bansal | Suraj Tripathi | Sumit Agarwal | Sireesh Gururaja | Aditya Srikanth Veerubhotla | Ritam Dutt | Teruko Mitamura | Eric Nyberg
Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering

In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset. MultiDoc2Dial is a conversational question answering dataset that grounds dialogues in multiple documents. The task involves grounding a user’s query in a document followed by generating an appropriate response. We propose several improvements over the baseline’s retriever-reader architecture to aid in modeling goal-oriented dialogues grounded in multiple documents. Our proposed approach employs sparse representations for passage retrieval, a passage re-ranker, the fusion-in-decoder architecture for generation, and a curriculum learning training paradigm. Our approach shows a 12 point improvement in BLEU score compared to the baseline RAG model.