Stalin Varanasi


2023

pdf
Auto-Encoding Questions with Retrieval Augmented Decoding for Unsupervised Passage Retrieval and Zero-Shot Question Generation
Stalin Varanasi | Muhammad Umer Tariq Butt | Guenter Neumann
Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing

Dense passage retrieval models have become state-of-the-art for information retrieval on many Open-domain Question Answering (ODQA) datasets. However, most of these models rely on supervision obtained from the ODQA datasets, which hinders their performance in a low-resource setting. Recently, retrieval-augmented language models have been proposed to improve both zero-shot and supervised information retrieval. However, these models have pre-training tasks that are agnostic to the target task of passage retrieval. In this work, we propose Retrieval Augmented Auto-encoding of Questions for zero-shot dense information retrieval. Unlike other pre-training methods, our pre-training method is built for target information retrieval, thereby making the pre-training more efficient. Our method consists of a dense IR model for encoding questions and retrieving documents during training and a conditional language model that maximizes the question’s likelihood by marginalizing over retrieved documents. As a by-product, we can use this conditional language model for zero-shot question generation from documents. We show that the IR model obtained through our method improves the current state-of-the-art of zero-shot dense information retrieval, and we improve the results even further by training on a synthetic corpus created by zero-shot question generation.

2021

pdf
AutoEQA: Auto-Encoding Questions for Extractive Question Answering
Stalin Varanasi | Saadullah Amin | Guenter Neumann
Findings of the Association for Computational Linguistics: EMNLP 2021

There has been a significant progress in the field of Extractive Question Answering (EQA) in the recent years. However, most of them are reliant on annotations of answer-spans in the corresponding passages. In this work, we address the problem of EQA when no annotations are present for the answer span, i.e., when the dataset contains only questions and corresponding passages. Our method is based on auto-encoding of the question that performs a question answering task during encoding and a question generation task during decoding. We show that our method performs well in a zero-shot setting and can provide an additional loss to boost performance for EQA.

2020

pdf
CopyBERT: A Unified Approach to Question Generation with Self-Attention
Stalin Varanasi | Saadullah Amin | Guenter Neumann
Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

Contextualized word embeddings provide better initialization for neural networks that deal with various natural language understanding (NLU) tasks including Question Answering (QA) and more recently, Question Generation(QG). Apart from providing meaningful word representations, pre-trained transformer models (Vaswani et al., 2017), such as BERT (Devlin et al., 2019) also provide self-attentions which encode syntactic information that can be probed for dependency parsing (Hewitt and Manning, 2019) and POStagging (Coenen et al., 2019). In this paper, we show that the information from selfattentions of BERT are useful for language modeling of questions conditioned on paragraph and answer phrases. To control the attention span, we use semi-diagonal mask and utilize a shared model for encoding and decoding, unlike sequence-to-sequence. We further employ copy-mechanism over self-attentions to acheive state-of-the-art results for Question Generation on SQuAD v1.1 (Rajpurkar et al., 2016).

2019

pdf
DOMLIN at SemEval-2019 Task 8: Automated Fact Checking exploiting Ratings in Community Question Answering Forums
Dominik Stammbach | Stalin Varanasi | Guenter Neumann
Proceedings of the 13th International Workshop on Semantic Evaluation

In the following, we describe our system developed for the Semeval2019 Task 8. We fine-tuned a BERT checkpoint on the qatar living forum dump and used this checkpoint to train a number of models. Our hand-in for subtask A consists of a fine-tuned classifier from this BERT checkpoint. For subtask B, we first have a classifier deciding whether a comment is factual or non-factual. If it is factual, we retrieve intra-forum evidence and using this evidence, have a classifier deciding the comment’s veracity. We trained this classifier on ratings which we crawled from qatarliving.com

2018

pdf
How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?
Georg Heigold | Stalin Varanasi | Günter Neumann | Josef van Genabith
Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)