Obtaining labeled data is a significant obstacle for many NLP tasks. Recently, online games have been proposed as a new way of obtaining labeled data; games attract users by being fun to play. In this paper, we consider the application of this idea to collecting semantic relations between words, such as hypernym/hyponym relationships. We built three online games, inspired by the real-life games...

Word embeddings encode semantic meanings of words into low-dimension word vectors. In most word embeddings, one cannot interpret the meanings of specific dimensions of those word vectors. Nonnegative matrix factorization (NMF) has been proposed to learn interpretable word embeddings via non-negative constraints. However, NMF methods suffer from scale and memory issue because they have to mainta...

In April 2003, Critical Care made two important changes: firstly, only the abstracts of research articles now appear in print while the full text is open access (freely and universally accessible online); and secondly, all articles over two years old are free to access online – including commentaries, reviews and reports. All this is part of the journal's ongoing quest to be a good scientific c...

In this paper, we present a simple protocol to evaluate word aligners on bilingual lexicon induction tasks from parallel corpora. Rather than resorting to gold standards, it relies on a comparison of the outputs of word aligners against a reference bilingual lexicon. The quality of this reference bilingual lexicon does not need to be particularly high, because evaluation quality is ensured by s...

Virtual communities are the uppermost communication spaces and channels for online word-of-mouth. And opinion leaders are the most important group for enterprises’ word-of-mouth communication. As enterprises are engaged in online word-of-mouth marketing activities, the key is to find out the opinion leaders in virtual communities. In this paper, after affirming the effects of opinion leaders an...

Strict compositionality in morphological theory is problematic for explaining how language-users comprehend phenomena like the partial yet non-decomposable forms in phonaesthemes and in blends like edutainment. An alternative account, based on discriminative learning, proposes that language-users associate linguistic cues (e.g., short segment or letter strings) with multiple simultaneous possib...

Obtaining a useful complete overview of Web-based product information has become difficult nowadays due to the ever-growing amount of information available on online shops. Findings from previous studies suggest that better search capabilities, such as the exploitation of annotated data, are needed to keep online shopping transparent for the user. Annotations can, for example, help present info...

Sometimes conventional feedback controllers may not perform well online because of the variation in process dynamics due to nonlinear actuators, changes in environmental conditions and variation in the character of the disturbances. To overcome the above problem, this paper deals with the designing of a controller for a second order system with Model Reference Adaptive Control (MRAC) scheme usi...

This paper describes a method to mine Hindi-English transliteration pairs from online Hindi song lyrics. The technique is based on the observations that lyrics are transliterated word-by-word, maintaining the precise word order. The mining task is nevertheless challenging because the Hindi lyrics and its transliterations are usually available from different, often unrelated, websites. Therefore...