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 interactive photo-realistic simulator in which an agent fulfills object-finding tasks by requesting and interpreting natural language-and-vision assistance. An agent solving tasks in a HANNA environment can leverage simulated human assistants, called ANNA (Automatic Natural Navigation Assistants), which, upon request, provide natural language and visual instructions to direct the agent towards the goals. To address the HANNA problem, we develop a memory-augmented neural agent that hierarchically models multiple levels of decision-making, and an imitation learning algorithm that teaches the agent to avoid repeating past mistakes while simultaneously predicting its own chances of making future progress. Empirically, our approach is able to ask for help more effectively than competitive baselines and, thus, attains higher task success rate on both previously seen and previously unseen environments.

We construct Global Voices, a multilingual dataset for evaluating cross-lingual summarization methods. We extract social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-English summarization in 15 languages. Especially, for the into-English summarization task, we crowd-source a high-quality evaluation dataset based on guidelines that emphasize accuracy, coverage, and understandability. To ensure the quality of this dataset, we collect human ratings to filter out bad summaries, and conduct a survey on humans, which shows that the remaining summaries are preferred over the social-network summaries. We study the effect of translation quality in cross-lingual summarization, comparing a translate-then-summarize approach with several baselines. Our results highlight the limitations of the ROUGE metric that are overlooked in monolingual summarization.

Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems from simulated human feedback. Our algorithm combines the advantage actor-critic algorithm (Mnih et al., 2016) with the attention-based neural encoder-decoder architecture (Luong et al., 2015). This algorithm (a) is well-designed for problems with a large action space and delayed rewards, (b) effectively optimizes traditional corpus-level machine translation metrics, and (c) is robust to skewed, high-variance, granular feedback modeled after actual human behaviors.