In order to extract bilingual terms in a corpus of comparable patents, we present a novel framework in this paper. The framework includes the following major steps: 1) extract monolingual single-word and multi-word term candidates in monolingual patents; 2) Find parallel sentences in comparable patents; 3) extract bilingual single-word and multi-word term candidates; 4) identify correct bilingu...

Hypernym links acquired through an information extraction procedure are projected on multi-word terms through the recognition of semantic variations. The quality of the projected links resulting from corpus-based acquisition is compared with projected links extracted from a technical thesaurus. 1 Motivation In the domain of corpus-based terminology, there are two main topics of research: term a...

In two experiments, we investigated the correspondences between off-line word segmentation and on-line processing during Chinese reading. Experiment 1, participants were asked to read sentences which contained critical four-character strings, then, they required segment same into words in a later task. For each item, split 1-word segmenters (who segmented strings as single word) 2-word 2 two-ch...

Recent work has shown success in learning word embeddings with neural network language models (NNLM). However, the majority of previous NNLMs represent each word with a single embedding, which fails to capture polysemy. In this paper, we address this problem by representing words with multiple and sense-specific embeddings, which are learned from bilingual parallel data. We evaluate our embeddi...

Current vector-space models of lexical semantics create a single “prototype” vector to represent the meaning of a word. However, due to lexical ambiguity, encoding word meaning with a single vector is problematic. This paper presents a method that uses clustering to produce multiple “sense-specific” vectors for each word. This approach provides a context-dependent vector representation of word ...

Zipf’s law states that the frequency of word tokens in a large corpus of natural language is inversely proportional to the rank. The law is investigated for two languages English and Mandarin and for ngram word phrases as well as for single words. The law for single words is shown to be valid only for high frequency words. However, when single word and n-gram phrases are combined together in on...

The first pattern recognition approaches to machine translation were based on single-word models. However, these models present an important deficiency; they do not take contextual information into account for the translation decision. The phrase-based approach consists in translating a multiword source sequence into a multiword target sequence, instead of a single source word into a single tar...