Saurabh Kulshreshtha


pdf bib
Reasoning Circuits: Few-shot Multi-hop Question Generation with Structured Rationales
Saurabh Kulshreshtha | Anna Rumshisky
Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE)

Multi-hop Question Generation is the task of generating questions which require the reader to reason over and combine information spread across multiple passages employing several reasoning steps. Chain-of-thought rationale generation has been shown to improve performance on multi-step reasoning tasks and make model predictions more interpretable. However, few-shot performance gains from including rationales have been largely observed only in +100B language models, and otherwise require large-scale manual rationale annotation. In this paper, we introduce a new framework for applying chain-of-thought inspired structured rationale generation to multi-hop question generation under a very low supervision regime (8- to 128-shot). We propose to annotate a small number of examples following our proposed multi-step rationale schema, treating each reasoning step as a separate task to be performed by a generative language model. We show that our framework leads to improved control over the difficulty of the generated questions and better performance compared to baselines trained without rationales, both on automatic evaluation metrics and in human evaluation. Importantly, we show that this is achievable with a modest model size.


pdf bib
Down and Across: Introducing Crossword-Solving as a New NLP Benchmark
Saurabh Kulshreshtha | Olga Kovaleva | Namrata Shivagunde | Anna Rumshisky
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Solving crossword puzzles requires diverse reasoning capabilities, access to a vast amount of knowledge about language and the world, and the ability to satisfy the constraints imposed by the structure of the puzzle. In this work, we introduce solving crossword puzzles as a new natural language understanding task. We release a corpus of crossword puzzles collected from the New York Times daily crossword spanning 25 years and comprised of a total of around nine thousand puzzles. These puzzles include a diverse set of clues: historic, factual, word meaning, synonyms/antonyms, fill-in-the-blank, abbreviations, prefixes/suffixes, wordplay, and cross-lingual, as well as clues that depend on the answers to other clues. We separately release the clue-answer pairs from these puzzles as an open-domain question answering dataset containing over half a million unique clue-answer pairs. For the question answering task, our baselines include several sequence-to-sequence and retrieval-based generative models. We also introduce a non-parametric constraint satisfaction baseline for solving the entire crossword puzzle. Finally, we propose an evaluation framework which consists of several complementary performance metrics.


pdf bib
BERT Busters: Outlier Dimensions that Disrupt Transformers
Olga Kovaleva | Saurabh Kulshreshtha | Anna Rogers | Anna Rumshisky
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021


pdf bib
Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study
Saurabh Kulshreshtha | Jose Luis Redondo Garcia | Ching-Yun Chang
Findings of the Association for Computational Linguistics: EMNLP 2020

Multilingual BERT (mBERT) has shown reasonable capability for zero-shot cross-lingual transfer when fine-tuned on downstream tasks. Since mBERT is not pre-trained with explicit cross-lingual supervision, transfer performance can further be improved by aligning mBERT with cross-lingual signal. Prior work propose several approaches to align contextualised embeddings. In this paper we analyse how different forms of cross-lingual supervision and various alignment methods influence the transfer capability of mBERT in zero-shot setting. Specifically, we compare parallel corpora vs dictionary-based supervision and rotational vs fine-tuning based alignment methods. We evaluate the performance of different alignment methodologies across eight languages on two tasks: Name Entity Recognition and Semantic Slot Filling. In addition, we propose a novel normalisation method which consistently improves the performance of rotation-based alignment including a notable 3% F1 improvement for distant and typologically dissimilar languages. Importantly we identify the biases of the alignment methods to the type of task and proximity to the transfer language. We also find that supervision from parallel corpus is generally superior to dictionary alignments.