activity
20092026
most citedFrustratingly Easy Domain Adaptation

1.4k citations · 4.5k across the 58 of their papers we have counts for

collaborators
Showing 2019Show all

9 papers · 1 filter

cs.CL2019★ 22 cited

Toward Gender-Inclusive Coreference Resolution

Yang Trista Cao, Hal Daumé

Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systemic biases in coreference resoluti…

cs.CL2019

Global Voices: Crossing Borders in Automatic News Summarization

Khanh Nguyen, Hal Daumé

We construct Global Voices, a multilingual dataset for evaluating cross-lingual summarization methods. We extract social-network descriptions of Global Voices news articles to chea…

cs.HC2019★ 5 cited

Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning

Khanh Nguyen, Hal Daumé

Mobile agents that can leverage help from humans can potentially accomplish more complex tasks than they could entirely on their own. We develop "Help, Anna!" (HANNA), an interacti…

cs.LG2019★ 48 cited

Reinforcement Learning with Convex Constraints

Sobhan Miryoosefi, Kianté Brantley, Hal Daumé +2

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as cons…

cs.CL2019★ 41 cited

Answer-based Adversarial Training for Generating Clarification Questions

Sudha Rao, Hal Daumé

We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that mo…

cs.CL2019★ 62 cited

Non-Monotonic Sequential Text Generation

Sean Welleck, Kianté Brantley, Hal Daumé +1

Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a…