Word alignment is a challenging task aiming at the identification of translational relations between words and multi-word units in parallel corpora. Many alignment strategies are based on links between single words. Different strategies can be used to find the optimal word alignment using such one-toone word links including relations between multi-word units. In this paper seven algorithms are ...

In this paper, we study the use of so-called word trigger pairs to improve an existing language model, which is typically a trigram model in combination with a cache component. A word trigger pair is defined as a long-distance word pair. We present two methods to select the most significant single word trigger pairs. The selected trigger pairs are used in a combined model where the interpolatio...

We present a method for named entity extraction from word lattices produced by a speech recogniser. Previous work by others on named entity extraction from speech has used either a manual transcript or 1-best recogniser output. We describe how a single Viterbi search can recover both the named entity sequence and the corresponding word sequence from a word lattice, and further that it is possib...

The study examined the nature of eye movement control and word recognition during scanning for a specific topic, compared with reading for comprehension. Experimental trials included a manipulation of word frequency: the critical word was frequent (and orthographically familiar) or infrequent (2 conditions: orthographically familiar and orthographically unfamiliar). First-pass reading times sho...

Based on the observation that the unpredictable nature of conversational speech makes it almost impossible to reliably model sequential word constraints, the notion of word set error criteria is proposed for improved recognition of spontaneous dialogues. The single pass Adaptive Boosting (AB) algorithm enables the language model weights to be tuned using the word set error criteria. In the two ...

Participants' eye movements were recorded as they read single sentences presented normally, presented entirely in faint text, or presented normally except for a single faint word. Fixations were longer when the entire sentence was faint than when the sentence was presented normally. In addition, fixations were much longer on a single faint word embedded in normal text, compared to when the enti...

OBJECTIVE We report (1) the quantitative investigation of text reading in posterior cortical atrophy (PCA), and (2) the effects of 2 novel software-based reading aids that result in dramatic improvements in the reading ability of patients with PCA. METHODS Reading performance, eye movements, and fixations were assessed in patients with PCA and typical Alzheimer disease and in healthy controls...

Many NLP applications require disambiguating polysemous words. Existing methods that learn polysemous word vector representations involve first detecting various senses and optimizing the sensespecific embeddings separately, which are invariably more involved than single sense learning methods such as word2vec. Evaluating these methods is also problematic, as rigorous quantitative evaluations i...

The purpose of this study was to determine the effect application word method for "LEMBAGA" on improving articulation ability hear impairment students in second grade elementary special school. This uses Single Subject Research (SSR) with an A-B-A design one school student a hearing student. learning begins introduction particular word. is then broken down into syllables, syllables letters. Nex...