High quality distributional models can capture lexical and semantic relations between words. Hence, researchers design various intrinsic tasks to test whether such relations are captured. However, most of the intrinsic tasks are designed for modern l
anguages, and there is a lack of evaluation methods for distributional models of historical corpora. In this paper, we conducted BAHP: a benchmark of assessing word embeddings in Historical Portuguese, which contains four types of tests: analogy, similarity, outlier detection, and coherence. We examined word2vec models generated from two historical Portuguese corpora in these four test sets. The results demonstrate that our test sets are capable of measuring the quality of vector space models and can provide a holistic view of the model's ability to capture syntactic and semantic information. Furthermore, the methodology for the creation of our test sets can be easily extended to other historical languages.
Term and glossary management are vital steps of preparation of every language specialist, and they play a very important role at the stage of education of translation professionals. The growing trend of efficient time management and constant time con
straints we may observe in every job sector increases the necessity of the automatic glossary compilation. Many well-performing bilingual AET systems are based on processing parallel data, however, such parallel corpora are not always available for a specific domain or a language pair. Domain-specific, bilingual access to information and its retrieval based on comparable corpora is a very promising area of research that requires a detailed analysis of both available data sources and the possible extraction techniques. This work focuses on domain-specific automatic terminology extraction from comparable corpora for the English -- Russian language pair by utilizing neural word embeddings.
Word embeddings are widely used in Natural Language Processing (NLP) for a vast range of applications. However, it has been consistently proven that these embeddings reflect the same human biases that exist in the data used to train them. Most of the
introduced bias indicators to reveal word embeddings' bias are average-based indicators based on the cosine similarity measure. In this study, we examine the impacts of different similarity measures as well as other descriptive techniques than averaging in measuring the biases of contextual and non-contextual word embeddings. We show that the extent of revealed biases in word embeddings depends on the descriptive statistics and similarity measures used to measure the bias. We found that over the ten categories of word embedding association tests, Mahalanobis distance reveals the smallest bias, and Euclidean distance reveals the largest bias in word embeddings. In addition, the contextual models reveal less severe biases than the non-contextual word embedding models.
