Li Fei-Fei


Neural Event Semantics for Grounded Language Understanding
Shyamal Buch | Li Fei-Fei | Noah D. Goodman
Transactions of the Association for Computational Linguistics, Volume 9

Abstract We present a new conjunctivist framework, neural event semantics (NES), for compositional grounded language understanding. Our approach treats all words as classifiers that compose to form a sentence meaning by multiplying output scores. These classifiers apply to spatial regions (events) and NES derives its semantic structure from language by routing events to different classifier argument inputs via soft attention. NES is trainable end-to-end by gradient descent with minimal supervision. We evaluate our method on compositional grounded language tasks in controlled synthetic and real-world settings. NES offers stronger generalization capability than standard function-based compositional frameworks, while improving accuracy over state-of-the-art neural methods on real-world language tasks.

Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
Siddharth Karamcheti | Ranjay Krishna | Li Fei-Fei | Christopher Manning
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Active learning promises to alleviate the massive data needs of supervised machine learning: it has successfully improved sample efficiency by an order of magnitude on traditional tasks like topic classification and object recognition. However, we uncover a striking contrast to this promise: across 5 models and 4 datasets on the task of visual question answering, a wide variety of active learning approaches fail to outperform random selection. To understand this discrepancy, we profile 8 active learning methods on a per-example basis, and identify the problem as collective outliers – groups of examples that active learning methods prefer to acquire but models fail to learn (e.g., questions that ask about text in images or require external knowledge). Through systematic ablation experiments and qualitative visualizations, we verify that collective outliers are a general phenomenon responsible for degrading pool-based active learning. Notably, we show that active learning sample efficiency increases significantly as the number of collective outliers in the active learning pool decreases. We conclude with a discussion and prescriptive recommendations for mitigating the effects of these outliers in future work.


Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval
Sebastian Schuster | Ranjay Krishna | Angel Chang | Li Fei-Fei | Christopher D. Manning
Proceedings of the Fourth Workshop on Vision and Language