activity
20152022
most citedBoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

209 citations · 310 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

17 papers · 1 filter

cs.CL20223 cited

Coreference Resolution through a seq2seq Transition-Based System

Bernd Bohnet, Chris Alberti, Michael Collins

Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution syste…

cs.CL2022

Towards Computationally Verifiable Semantic Grounding for Language Models

Chris Alberti, Kuzman Ganchev, Michael Collins +2

The paper presents an approach to semantic grounding of language models (LMs) that conceptualizes the LM as a conditional model generating text given a desired semantic message for…

cs.CL20225 cited

Query Refinement Prompts for Closed-Book Long-Form Question Answering

Reinald Kim Amplayo, Kellie Webster, Michael Collins +2

Large language models (LLMs) have been shown to perform well in answering questions and in producing long-form texts, both in few-shot closed-book settings. While the former can be…

cs.CL20222 cited

Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization

Thomas Effland, Michael Collins

We present Expected Statistic Regularization (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi-…

cs.CL20211 cited

Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss

Thomas Effland, Michael Collins

We study learning named entity recognizers in the presence of missing entity annotations. We approach this setting as tagging with latent variables and propose a novel loss, the Ex…

cs.CL2021

Decontextualization: Making Sentences Stand-Alone

Eunsol Choi, Jennimaria Palomaki, Matthew Lamm +3

Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context. Taking excerpts…