We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario. Although this matrix provides us critical information regarding similarity between tasks, its asymmetric property and unreliable performance scores can affe...

Many data mining algorithms developed recently are based on inductive learning methods. Very few are based on similarity-based learning. However, similarity-based learning accrues advantages, such as simple representations for concept descriptions, low incremental learning costs, small storage requirements, etc. We present a similarity-based learning method from databases in the context of roug...

We use referential translation machines (RTMs) for predicting the semantic similarity of text. RTMs are a computational model for identifying the translation acts between any two data sets with respect to interpretants selected in the same domain, which are effective when making monolingual and bilingual similarity judgments. RTMs judge the quality or the semantic similarity of text by using re...

This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks through task transfer. Related transfer can increase learning rate and can help prevent convergence to sub-optimal policies in reinforcement learning. Unrelated transfer can be extremely detrimental to the learning rate. ...

Word similarity computation is a fundamental task for natural language processing. We organize a semantic campaign of Chinese word similarity measurement at NLPCC-ICCPOL 2016. This task provides a benchmark dataset of Chinese word similarity (PKU-500 dataset), including 500 word pairs with their similarity scores. There are 21 teams submitting 24 systems in this campaign. In this paper, we desc...

What can differences tell us about the process of comparison? The structural alignment model posits that psychologically salient differences arise out of commonalities (Markman & Gentner, 1993) . This leads to the counterintuitive prediction that high similarity pairs (e .g ., bicycle/tricycle) should elicit more differences than low similarity pairs (e .g ., broom/ambulance), since high simila...

Every clustering algorithm requires a similarity measure, ideally optimized for the task in question. In this paper we are concerned with the task of identifying events in social media data and address the question of how a suitable similarity function can be learned from training data for this task. The task consists essentially in grouping social media documents by the event they belong to. I...

Two experiments on the internal representation of auditory stimuli compared the pairwise and grouping methodologies as means of deriving similarity judgements. A total of 45 undergraduate students participated in each experiment, judging the similarity of short auditory stimuli, using one of the methodologies. The experiments support and extend Bonebright's (1996) findings, using a further 60 s...

Phonological similarity effects were used to assess the role of acoustic coding in verbal complex span, a processing-plus-storage measure found to correlate significantly with aspects of complex cognition. Three experiments demonstrated consistent effects of phonological similarity on listening span. These effects appeared relatively insensitive to manipulations of task materials (Experiment 1)...

Previous studies have reported seemingly conflicting results regarding how the amount of stimulus similarity between two simultaneously presented target stimuli impacts perceptual performance. There are many reports of 'repetition blindness', where individuals do worse when shown two similar stimuli relative to two different stimuli. On the other hand, there are reports of 'similarity grouping'...