no code implementations • 22 May 2023 • Elizabeth Clark, Shruti Rijhwani, Sebastian Gehrmann, Joshua Maynez, Roee Aharoni, Vitaly Nikolaev, Thibault Sellam, Aditya Siddhant, Dipanjan Das, Ankur P. Parikh
In this work, we introduce SEAHORSE, a dataset for multilingual, multifaceted summarization evaluation.
1 code implementation • 8 Mar 2023 • Vishakh Padmakumar, Richard Yuanzhe Pang, He He, Ankur P. Parikh
We study the problem of extrapolative controlled generation, i. e., generating sequences with attribute values beyond the range seen in training.
no code implementations • 16 Nov 2022 • Richard Yuanzhe Pang, Vishakh Padmakumar, Thibault Sellam, Ankur P. Parikh, He He
To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations.
1 code implementation • 21 Oct 2022 • Ran Tian, Ankur P. Parikh
We present Amos, a stochastic gradient-based optimizer designed for training deep neural networks.
no code implementations • 12 Oct 2022 • Thibault Sellam, Ankur Bapna, Joshua Camp, Diana Mackinnon, Ankur P. Parikh, Jason Riesa
The main insight is that training one model on many locales consistently outperforms mono-locale baselines.
no code implementations • 23 May 2022 • Tao Lei, Ran Tian, Jasmijn Bastings, Ankur P. Parikh
In this work, we explore whether modeling recurrence into the Transformer architecture can both be beneficial and efficient, by building an extremely simple recurrent module into the Transformer.
1 code implementation • ACL 2022 • Sanket Vaibhav Mehta, Jinfeng Rao, Yi Tay, Mihir Kale, Ankur P. Parikh, Emma Strubell
Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs).
1 code implementation • EMNLP 2021 • Amy Pu, Hyung Won Chung, Ankur P. Parikh, Sebastian Gehrmann, Thibault Sellam
Recent developments in machine translation and multilingual text generation have led researchers to adopt trained metrics such as COMET or BLEURT, which treat evaluation as a regression problem and use representations from multilingual pre-trained models such as XLM-RoBERTa or mBERT.
no code implementations • 30 Aug 2021 • Ran Tian, Joshua Maynez, Ankur P. Parikh
The highly popular Transformer architecture, based on self-attention, is the foundation of large pretrained models such as BERT, that have become an enduring paradigm in NLP.
no code implementations • NAACL 2021 • Xavier Garcia, Noah Constant, Ankur P. Parikh, Orhan Firat
We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual learning for multilingual machine translation.
no code implementations • WMT (EMNLP) 2020 • Thibault Sellam, Amy Pu, Hyung Won Chung, Sebastian Gehrmann, Qijun Tan, Markus Freitag, Dipanjan Das, Ankur P. Parikh
The quality of machine translation systems has dramatically improved over the last decade, and as a result, evaluation has become an increasingly challenging problem.
no code implementations • NAACL 2021 • Xavier Garcia, Aditya Siddhant, Orhan Firat, Ankur P. Parikh
We outperform all current state-of-the-art unsupervised baselines for these languages, achieving gains of up to 14. 4 BLEU.
1 code implementation • EMNLP 2020 • Ankur P. Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, Dipanjan Das
We present ToTTo, an open-domain English table-to-text dataset with over 120, 000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description.
Ranked #3 on Data-to-Text Generation on ToTTo
3 code implementations • ACL 2020 • Thibault Sellam, Dipanjan Das, Ankur P. Parikh
We propose BLEURT, a learned evaluation metric based on BERT that can model human judgments with a few thousand possibly biased training examples.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Xavier Garcia, Pierre Foret, Thibault Sellam, Ankur P. Parikh
We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation.
1 code implementation • ICLR 2020 • Kalpesh Krishna, Gaurav Singh Tomar, Ankur P. Parikh, Nicolas Papernot, Mohit Iyyer
We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that model.
no code implementations • 19 Oct 2019 • Ran Tian, Shashi Narayan, Thibault Sellam, Ankur P. Parikh
We address the issue of hallucination in data-to-text generation, i. e., reducing the generation of text that is unsupported by the source.
1 code implementation • ACL 2019 • Minjoon Seo, Jinhyuk Lee, Tom Kwiatkowski, Ankur P. Parikh, Ali Farhadi, Hannaneh Hajishirzi
Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query.
no code implementations • NAACL 2019 • Hao Peng, Ankur P. Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das
We propose a novel conditioned text generation model.
2 code implementations • NAACL 2019 • Maruan Al-Shedivat, Ankur P. Parikh
Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest.
no code implementations • 5 Aug 2018 • Micol Marchetti-Bowick, Benjamin J. Lengerich, Ankur P. Parikh, Eric P. Xing
One way to achieve this goal is to perform subspace learning to estimate a small set of latent features that capture the majority of the variance in the original data.
1 code implementation • EMNLP 2018 • Minjoon Seo, Tom Kwiatkowski, Ankur P. Parikh, Ali Farhadi, Hannaneh Hajishirzi
We formalize a new modular variant of current question answering tasks by enforcing complete independence of the document encoder from the question encoder.
no code implementations • ICLR 2018 • Swabha Swayamdipta, Ankur P. Parikh, Tom Kwiatkowski
Reading comprehension is a challenging task, especially when executed across longer or across multiple evidence documents, where the answer is likely to reoccur.
10 code implementations • EMNLP 2016 • Ankur P. Parikh, Oscar Täckström, Dipanjan Das, Jakob Uszkoreit
We propose a simple neural architecture for natural language inference.
Ranked #47 on Natural Language Inference on SNLI
no code implementations • 15 Jan 2014 • Avneesh Saluja, Mahdi Pakdaman, Dongzhen Piao, Ankur P. Parikh
Rating and recommendation systems have become a popular application area for applying a suite of machine learning techniques.
no code implementations • EMNLP 2014 • Ankur P. Parikh, Avneesh Saluja, Chris Dyer, Eric P. Xing
We present power low rank ensembles (PLRE), a flexible framework for n-gram language modeling where ensembles of low rank matrices and tensors are used to obtain smoothed probability estimates of words in context.
no code implementations • NeurIPS 2011 • Le Song, Eric P. Xing, Ankur P. Parikh
Latent tree graphical models are natural tools for expressing long range and hierarchical dependencies among many variables which are common in computer vision, bioinformatics and natural language processing problems.