In this work, we compare the translation performance of word alignments obtained via Bayesian inference to those obtained via expectation-maximization (EM). We propose a Gibbs sampler for fully Bayesian inference in IBM Model 1, integrating over all possible parameter values in finding the alignment distribution. We show that Bayesian inference outperforms EM in all of the tested language pairs...

This paper explores the relative contributions made by orthography, syllabic segment, and lexical tone in the word recognition and retrieval process. It also challenges recent assumptions regarding the role of orthography and tones in mental lexicon architecture. Using an implicit priming paradigm, a word recognition experiment was conducted with native speakers of two tonal languages, Chinese ...

In this paper we describe an approach to finding the shortest reset word of a finite synchronizing automaton by using a SAT solver. We use this approach to perform an experimental study of the length of the shortest reset word of a finite synchronizing automaton. The largest automata we considered had 100 states. The results of the experiments allow us to formulate a hypothesis that the length ...

This research focuses on analyzing illocutionary acts in Finding Nemo film. uses speech theory of pragmatics approach to analyze the meaning uttered applies qualitative method. The functions act by characters are declarative, representative, expressive, directive, and commisive. illocutinary film classified Yule, Word Orders Performative Verbs as indicator.

Word sense disambiguation (WSD) has been a long-standing research objective for natural language processing. In this paper we are concerned with developing graph-based unsupervised algorithms for alleviating the data requirements for large scale WSD. Under this framework, finding the right sense for a given word amounts to identifying the most “important” node among the set of graph nodes repre...

Word Sense Disambiguation (WSD from now on) represents an established task within Natural Language Processing community, aiming at finding the right sense of a word occurring in a free running text through the use of a computer algorithm. Currently, most of the WSD approaches consider only monolingual texts, and, as such, they rely mainly on the discriminatory power of the words appearing in th...

Motivated by the psycholinguistic finding that human eye gaze is tightly linked to speech production, previous work has applied naturally occurring eye gaze for automatic vocabulary acquisition. However, unlike in the typical settings for psycholinguistic studies, eye gaze can serve different functions in human-machine conversation. Some gaze streams do not link to the content of the spoken utt...

Assessing vocabulary difficulty is useful for finding and creating texts at low reading levels. Prior work has focused on characteristics such as word length and word frequency. In this work, we explore whether other cues might be useful, using features extracted from Wiktionary entries. Comparing words in comparable articles in Standard and Simple English Wikipedia, we find that words that app...

This paper summarizes the results of some experiments for finding the effective features for disambiguation of Turkish verbs. Word sense disambiguation is a current area of investigation in which verbs have the dominant role. Generally verbs have more senses than the other types of words in the average and detecting these features for verbs may lead to some improvements for other word types. In...

GloVe, global vectors for word representation, performs well in some word analogy and semantic relatedness tasks. However, we find that some dimensions of the trained word embedding are abnormal. We verify our conjecture via removing these abnormal dimensions using Kolmogorov–Smimov test and experiment on several benchmark datasets for semantic relatedness measurement. The experimental results ...