Matt Gardner

Incorporating Vector Space Similarity in Random Walk Inference over Knowledge Bases

Much work in recent years has gone into the construction of large knowledge bases (KBs), such as Freebase, DBPedia, NELL, and YAGO. While these KBs are very large, they are still very incomplete, necessitating the use of inference to fill in gaps. Prior work has shown how to make use of a large text corpus to augment random walk inference over KBs. We present two improvements to the use of such large corpora to augment KB inference. First, we present a new technique for combining KB relations and surface text into a single graph representation that is much more compact than graphs used in prior work. Second, we describe how to incorporate vector space similarity into random walk inference over KBs, reducing the feature sparsity inherent in using surface text. This allows us to combine distributional similarity with symbolic logical inference in novel and effective ways. With experiments on many relations from two separate KBs, we show that our methods significantly outperform prior work on KB inference, both in the size of problem our methods can handle and in the quality of predictions made.

Efficient and Expressive Knowledge Base Completion Using Subgraph Feature Extraction

We explore some of the practicalities of using random walk inference methods, such as the Path Ranking Algorithm (PRA), for the task of knowledge base completion. We show that the random walk probabilities computed (at great expense) by PRA provide no discernible benefit to performance on this task, so they can safely be dropped. This allows us to define a simpler algorithm for generating feature matrices from graphs, which we call subgraph feature extraction (SFE). In addition to being conceptually simpler than PRA, SFE is much more efficient, reducing computation by an order of magnitude, and more expressive, allowing for much richer features than paths between two nodes in a graph. We show experimentally that this technique gives substantially better performance than PRA and its variants, improving mean average precision from .432 to .528 on a knowledge base completion task using the NELL KB.

Translation Invariant Word Embeddings

This work focuses on the task of finding latent vector representations of the words in a corpus. In particular, we address the issue of what to do when there are multiple languages in the corpus. Prior work has, among other techniques, used canonical correlation analysis to project pre-trained vectors in two languages into a common space. We propose a simple and scalable method that is inspired by the notion that the learned vector representations should be invariant to translation between languages. We show empirically that our method outperforms prior work on multilingual tasks, matches the performance of prior work on monolingual tasks, and scales linearly with the size of the input data (and thus the number of languages being embedded).