Kenton Lee

Broad-coverage CCG Semantic Parsing with AMR

2015

We propose a grammar induction technique for AMR semantic parsing. While previous grammar induction techniques were designed to re-learn a new parser for each target application, the recently annotated AMR Bank provides a unique opportunity …

LSTM CCG Parsing

2016

We demonstrate that a state-of-the-art parser can be built using only a lexical tagging model and a deterministic grammar, with no explicit model of bi-lexical dependencies.Instead, all dependencies are implicitly encoded in an LSTM supertagger …

Learning Recurrent Span Representations for Extractive Question Answering

2016 · arXiv (Cornell University)

The reading comprehension task, that asks questions about a given evidence document, is a central problem in natural language understanding. Recent formulations of this task have typically focused on answer selection from a set of …

Deep Semantic Role Labeling: What Works and What’s Next

2017

We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use a deep highway …

Deep Contextualized Word Representations

2018

Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume …

A BERT Baseline for the Natural Questions

2019 · arXiv (Cornell University)

This technical note describes a new baseline for the Natural Questions. Our model is based on BERT and reduces the gap between the model F1 scores reported in the original dataset paper and the human …

Natural Questions: A Benchmark for Question Answering Research

2019 · Transactions of the Association for Computational Linguistics

We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a question along with a Wikipedia …

BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

2019 · arXiv (Cornell University)

In this paper we study yes/no questions that are naturally occurring --- meaning that they are generated in unprompted and unconstrained settings. We build a reading comprehension dataset, BoolQ, of such questions, and show that …

Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling

2018

Recent BIO-tagging-based neural semantic role labeling models are very high performing, but assume gold predicates as part of the input and cannot incorporate span-level features. We propose an endto-end approach for jointly predicting all predicates, …

REALM: Retrieval-Augmented Language Model Pre-Training

2020 · arXiv (Cornell University)

Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering. However, this knowledge is stored implicitly in the parameters of a neural network, …