• Publications
  • Influence
SQuAD: 100, 000+ Questions for Machine Comprehension of Text
We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answerExpand
  • 2,154
  • 629
  • PDF
Semantic Parsing on Freebase from Question-Answer Pairs
In this paper, we train a semantic parser that scales up to Freebase. Instead of relying on annotated logical forms, which is especially expensive to obtain at large scale, we learn fromExpand
  • 951
  • 175
  • PDF
Know What You Don't Know: Unanswerable Questions for SQuAD
Extractive reading comprehension systems can often locate the correct answer to a question in a context document, but they also tend to make unreliable guesses on questions for which the correctExpand
  • 593
  • 155
  • PDF
Understanding Black-box Predictions via Influence Functions
How can we explain the predictions of a black-box model? In this paper, we use influence functions — a classic technique from robust statistics — to trace a model's prediction through the learningExpand
  • 827
  • 87
  • PDF
Alignment by Agreement
We present an unsupervised approach to symmetric word alignment in which two simple asymmetric models are trained jointly to maximize a combination of data likelihood and agreement between theExpand
  • 475
  • 66
  • PDF
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e.g., sentiment) while preserving its attribute-independent content (e.g., changing "screen isExpand
  • 185
  • 65
  • PDF
Adversarial Examples for Evaluating Reading Comprehension Systems
Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systemsExpand
  • 606
  • 61
  • PDF
Learning Dependency-Based Compositional Semantics
Suppose we want to build a system that answers a natural language question by representing its semantics as a logical forxm and computing the answer given a structured database of facts. The coreExpand
  • 503
  • 51
  • PDF
QuAC : Question Answering in Context
We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who posesExpand
  • 191
  • 50
  • PDF
An End-to-End Discriminative Approach to Machine Translation
We present a perceptron-style discriminative approach to machine translation in which large feature sets can be exploited. Unlike discriminative reranking approaches, our system can take advantage ofExpand
  • 310
  • 49
  • PDF