Abstract | ||
---|---|---|
Recursive neural network models have achieved promising results in many natural language processing tasks. The main difference among these models lies in the composition function, i.e., how to obtain the vector representation for a phrase or sentence using the representations of words it contains. This paper introduces a novel Adaptive Multi-Compositionality (AdaMC) layer to recursive neural network models. The basic idea is to use more than one composition function and adaptively select them depending on input vectors. We develop a general framework to model the semantic composition as a distribution of these composition functions. The composition functions and parameters used for adaptive selection are jointly learnt from the supervision of specific tasks. We integrate AdaMC into existing recursive neural network models and conduct extensive experiments on the Stanford Sentiment Treebank and semantic relation classification task. The experimental results demonstrate that AdaMC improves the performance of recursive neural network models and outperforms the baseline methods. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TASLP.2015.2509257 | IEEE/ACM Trans. Audio, Speech & Language Processing |
Keywords | Field | DocType |
Semantics,Neural networks,Adaptation models,Computational modeling,Syntactics,Tensile stress,Adaptive systems | Computer science,Recurrent neural network,Phrase,Time delay neural network,Artificial intelligence,Artificial neural network,Principle of compositionality,Nervous system network models,Pattern recognition,Probabilistic neural network,Speech recognition,Treebank,Machine learning | Journal |
Volume | Issue | ISSN |
24 | 3 | 2329-9290 |
Citations | PageRank | References |
4 | 0.41 | 20 |
Authors | ||
5 |