OmniGraph: Rich Representation and Graph Kernel Learning
This work addresses the need for richer representations in NLP for tasks such as financial forecasting and sentiment analysis, though it appears incremental as it builds on existing graph kernel methods.
The authors tackled the problem of NLP classification tasks by introducing OmniGraph, a novel graph representation integrating lexical, syntactic, and semantic features, which outperformed benchmarks like bag-of-words and semantic trees in predicting stock price changes from news and achieved high performance on a sentiment corpus.
OmniGraph, a novel representation to support a range of NLP classification tasks, integrates lexical items, syntactic dependencies and frame semantic parses into graphs. Feature engineering is folded into the learning through convolution graph kernel learning to explore different extents of the graph. A high-dimensional space of features includes individual nodes as well as complex subgraphs. In experiments on a text-forecasting problem that predicts stock price change from news for company mentions, OmniGraph beats several benchmarks based on bag-of-words, syntactic dependencies, and semantic trees. The highly expressive features OmniGraph discovers provide insights into the semantics across distinct market sectors. To demonstrate the method's generality, we also report its high performance results on a fine-grained sentiment corpus.