Recursive neural 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 models. The basic idea is to use more than one composition functions and adaptively select them depending on the input vectors. We present a general framework to model each semantic composition as a distribution over these composition functions. The composition functions and parameters used for adaptive selection are learned jointly from data. We integrate AdaMC into existing recursive neural models and conduct extensive experiments on the Stanford Sentiment Treebank. The results illustrate that AdaMC significantly outperforms state-of-the-art sentiment classification methods. It helps push the best accuracy of sentence-level negative/positive classification from 85.4% up to 88.5%.
One of the most effective ways to change the mood of a photo is to add and subtract color to it. That's something Adobe's Lightroom software has given you the option to do for a while, but in one of the biggest changes the company has made to the Develop Module in a while, it's adding a new Color Grading module to give users even more control over the colors in their photos. The new tool builds on Lightroom's existing split toning feature by adding control of midtones to the mix. If you're not familiar with split toning, it's a tool you can use to tint the highlights and shadows of an image to give it a specific mood. If you've ever seen a "orange and teal" image on Instagram, chances are it was made with the split toning tool.
The behavior composition problem involves automatically building a controller that is able to realize a desired, but unavailable, target system (e.g., a house surveillance) by suitably coordinating a set of available components (e.g., video cameras, blinds, lamps, a vacuum cleaner, phones, etc.) Previous work has almost exclusively aimed at bringing about the desired component in its totality, which is highly unsatisfactory for unsolvable problems. In this work, we develop an approach for approximate behavior composition without departing from the classical setting, thus making the problem applicable to a much wider range of cases. Based on the notion of simulation, we characterize what a maximal controller and the "closest" implementable target module (optimal approximation) are, and show how these can be computed using ATL model checking technology for a special case. We show the uniqueness of optimal approximations, and prove their soundness and completeness with respect to their imported controllers.
We present a neural network method for review rating prediction in this paper. Existing neural network methods for sentiment prediction typically only capture the semantics of texts, but ignore the user who expresses the sentiment.This is not desirable for review rating prediction as each user has an influence on how to interpret the textual content of a review.For example, the same word (e.g. good) might indicate different sentiment strengths when written by different users. We address this issue by developing a new neural network that takes user information into account. The intuition is to factor in user-specific modification to the meaning of a certain word.Specifically, we extend the lexical semantic composition models and introduce a user-word composition vector model (UWCVM), which effectively captures how user acts as a function affecting the continuous word representation. We integrate UWCVM into a supervised learning framework for review rating prediction, andconduct experiments on two benchmark review datasets.Experimental results demonstrate the effectiveness of our method. It shows superior performances over several strong baseline methods.
We consider the problem of minimizing the composition of a smooth (nonconvex) function and a smooth vector mapping, where the inner mapping is in the form of an expectation over some random variable or a finite sum. We propose a stochastic composite gradient method that employs incremental variance-reduced estimators for both the inner vector mapping and its Jacobian. We show that this method achieves the same orders of complexity as the best known first-order methods for minimizing expected-value and finite-sum nonconvex functions, despite the additional outer composition which renders the composite gradient estimator biased. This finding enables a much broader range of applications in machine learning to benefit from the low complexity of incremental variance-reduction methods. Papers published at the Neural Information Processing Systems Conference.