Search Results for author:
Found 29 papers, 11 papers with code
Kernel Embeddings of Latent Tree Graphical Models
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.
Language Modeling with Power Low Rank Ensembles
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.
Infinite Mixed Membership Matrix Factorization
Rating and recommendation systems have become a popular application area for applying a suite of machine learning techniques.
A Decomposable Attention Model for Natural Language Inference
We propose a simple neural architecture for natural language inference.
Ranked #47 on
Natural Language Inference
on SNLI
Multi-Mention Learning for Reading Comprehension with Neural Cascades
Reading comprehension is a challenging task, especially when executed across longer or across multiple evidence documents, where the answer is likely to reoccur.
Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension
We formalize a new modular variant of current question answering tasks by enforcing complete independence of the document encoder from the question encoder.
Hybrid Subspace Learning for High-Dimensional Data
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.
Consistency by Agreement in Zero-shot Neural Machine Translation
Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest.
Text Generation with Exemplar-based Adaptive Decoding
We propose a novel conditioned text generation model.
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
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.
Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
We address the issue of hallucination in data-to-text generation, i. e., reducing the generation of text that is unsupported by the source.
Thieves on Sesame Street! Model Extraction of BERT-based APIs
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.
A Multilingual View of Unsupervised Machine Translation
We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation.
BLEURT: Learning Robust Metrics for Text Generation
We propose BLEURT, a learned evaluation metric based on BERT that can model human judgments with a few thousand possibly biased training examples.
ToTTo: A Controlled Table-To-Text Generation Dataset
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
Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages
We outperform all current state-of-the-art unsupervised baselines for these languages, achieving gains of up to 14. 4 BLEU.
Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task
The quality of machine translation systems has dramatically improved over the last decade, and as a result, evaluation has become an increasingly challenging problem.
Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution
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.
Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning
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.
Learning Compact Metrics for MT
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.
Improving Compositional Generalization with Self-Training for Data-to-Text Generation
Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs).
Simple Recurrence Improves Masked Language Models
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.
SQuId: Measuring Speech Naturalness in Many Languages
The main insight is that training one model on many locales consistently outperforms mono-locale baselines.
Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale
We present Amos, a stochastic gradient-based optimizer designed for training deep neural networks.
Reward Gaming in Conditional Text Generation
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.
Extrapolative Controlled Sequence Generation via Iterative Refinement
We study the problem of extrapolative controlled generation, i. e., generating sequences with attribute values beyond the range seen in training.
SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation
In this work, we introduce SEAHORSE, a dataset for multilingual, multifaceted summarization evaluation.
