Nitish Shirish Keskar


pdf bib
Modeling Multi-hop Question Answering as Single Sequence Prediction
Semih Yavuz | Kazuma Hashimoto | Yingbo Zhou | Nitish Shirish Keskar | Caiming Xiong
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA. However, the complexity of multi-hop QA hinders the effectiveness of the generative QA approach. In this work, we propose a simple generative approach (PathFid) that extends the task beyond just answer generation by explicitly modeling the reasoning process to resolve the answer for multi-hop questions. By linearizing the hierarchical reasoning path of supporting passages, their key sentences, and finally the factoid answer, we cast the problem as a single sequence prediction task. To facilitate complex reasoning with multiple clues, we further extend the unified flat representation of multiple input documents by encoding cross-passage interactions. Our extensive experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets: HotpotQA and IIRC. Besides the performance gains, PathFid is more interpretable, which in turn yields answers that are more faithfully grounded to the supporting passages and facts compared to the baseline Fid model.


pdf bib
Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality
Gustavo Aguilar | Bryan McCann | Tong Niu | Nazneen Rajani | Nitish Shirish Keskar | Thamar Solorio
Findings of the Association for Computational Linguistics: EMNLP 2021

Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokenization process of language models as it provides multiple benefits. However, this process is solely based on pre-training data statistics, making it hard for the tokenizer to handle infrequent spellings. On the other hand, though robust to misspellings, pure character-level models often lead to unreasonably long sequences and make it harder for the model to learn meaningful words. To alleviate these challenges, we propose a character-based subword module (char2subword) that learns the subword embedding table in pre-trained models like BERT. Our char2subword module builds representations from characters out of the subword vocabulary, and it can be used as a drop-in replacement of the subword embedding table. The module is robust to character-level alterations such as misspellings, word inflection, casing, and punctuation. We integrate it further with BERT through pre-training while keeping BERT transformer parameters fixed–and thus, providing a practical method. Finally, we show that incorporating our module to mBERT significantly improves the performance on the social media linguistic code-switching evaluation (LinCE) benchmark.

pdf bib
GeDi: Generative Discriminator Guided Sequence Generation
Ben Krause | Akhilesh Deepak Gotmare | Bryan McCann | Nitish Shirish Keskar | Shafiq Joty | Richard Socher | Nazneen Fatema Rajani
Findings of the Association for Computational Linguistics: EMNLP 2021

pdf bib
Unsupervised Paraphrasing with Pretrained Language Models
Tong Niu | Semih Yavuz | Yingbo Zhou | Nitish Shirish Keskar | Huan Wang | Caiming Xiong
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of labeled data that is costly to collect. To address this drawback, we adopt a transfer learning approach and propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking (DB). To enforce a surface form dissimilar from the input, whenever the language model emits a token contained in the source sequence, DB prevents the model from outputting the subsequent source token for the next generation step. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair (QQP) and the ParaNMT datasets and is robust to domain shift between the two datasets of distinct distributions. We also demonstrate that our model transfers to paraphrasing in other languages without any additional finetuning.


pdf bib
Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging
Semih Yavuz | Kazuma Hashimoto | Wenhao Liu | Nitish Shirish Keskar | Richard Socher | Caiming Xiong
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The concept of Dialogue Act (DA) is universal across different task-oriented dialogue domains - the act of “request” carries the same speaker intention whether it is for restaurant reservation or flight booking. However, DA taggers trained on one domain do not generalize well to other domains, which leaves us with the expensive need for a large amount of annotated data in the target domain. In this work, we investigate how to better adapt DA taggers to desired target domains with only unlabeled data. We propose MaskAugment, a controllable mechanism that augments text input by leveraging the pre-trained Mask token from BERT model. Inspired by consistency regularization, we use MaskAugment to introduce an unsupervised teacher-student learning scheme to examine the domain adaptation of DA taggers. Our extensive experiments on the Simulated Dialogue (GSim) and Schema-Guided Dialogue (SGD) datasets show that MaskAugment is useful in improving the cross-domain generalization for DA tagging.

pdf bib
The Thieves on Sesame Street are Polyglots - Extracting Multilingual Models from Monolingual APIs
Nitish Shirish Keskar | Bryan McCann | Caiming Xiong | Richard Socher
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Pre-training in natural language processing makes it easier for an adversary with only query access to a victim model to reconstruct a local copy of the victim by training with gibberish input data paired with the victim’s labels for that data. We discover that this extraction process extends to local copies initialized from a pre-trained, multilingual model while the victim remains monolingual. The extracted model learns the task from the monolingual victim, but it generalizes far better than the victim to several other languages. This is done without ever showing the multilingual, extracted model a well-formed input in any of the languages for the target task. We also demonstrate that a few real examples can greatly improve performance, and we analyze how these results shed light on how such extraction methods succeed.


pdf bib
Neural Text Summarization: A Critical Evaluation
Wojciech Kryscinski | Nitish Shirish Keskar | Bryan McCann | Caiming Xiong | Richard Socher
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Text summarization aims at compressing long documents into a shorter form that conveys the most important parts of the original document. Despite increased interest in the community and notable research effort, progress on benchmark datasets has stagnated. We critically evaluate key ingredients of the current research setup: datasets, evaluation metrics, and models, and highlight three primary shortcomings: 1) automatically collected datasets leave the task underconstrained and may contain noise detrimental to training and evaluation, 2) current evaluation protocol is weakly correlated with human judgment and does not account for important characteristics such as factual correctness, 3) models overfit to layout biases of current datasets and offer limited diversity in their outputs.