Evaluating multi-sense embeddings for semantic resolution monolingually and in word translation
نویسندگان
چکیده
Multi-sense word embeddings (MSEs) model different meanings of word forms with different vectors. We propose two new methods for evaluating MSEs, one based on monolingual dictionaries, and the other exploiting the principle that words may be ambiguous as far as the postulated senses translate to different words in some other language.
منابع مشابه
Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings
Word sense disambiguation is necessary in translation because different word senses often have different translations. Neural machine translation models learn different senses of words as part of an end-to-end translation task, and their capability to perform word sense disambiguation has so far not been quantified. We exploit the fact that neural translation models can score arbitrary translat...
متن کاملDo Multi-Sense Embeddings Improve Natural Language Understanding?
Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while ‘multi-sense’ methods have been proposed and tested on artificial wordsimilarity tasks, we don’t know if they improve real natural language understanding tasks. In this paper we introduce a multisense embedding model based on Chine...
متن کاملBilingual Word Embeddings for Phrase-Based Machine Translation
We introduce bilingual word embeddings: semantic embeddings associated across two languages in the context of neural language models. We propose a method to learn bilingual embeddings from a large unlabeled corpus, while utilizing MT word alignments to constrain translational equivalence. The new embeddings significantly out-perform baselines in word semantic similarity. A single semantic simil...
متن کاملAutoExtend: Combining Word Embeddings with Semantic Resources
We present AutoExtend, a system that combines word embeddings with semantic resources by learning embeddings for non-word objects like synsets and entities and learning word embeddings which incorporate the semantic information from the resource. The method is based on encoding and decoding the word embeddings and is flexible in that it can take any word embeddings as input and does not need an...
متن کاملIs Hesaabdaaree an Adequate Equivalent for Accounting?
Some of the difficulties and misunderstandings that happen in accounting theory, practice, regulation and education are grounded in language and linguistics. As an illustration of this the Persian equivalent of 'accounting' is linguistically analysed to reveal how a mistranslation may cause difficulties in understanding and improving Iranian Accounting. This paper shows how Hesaabdaaree is not ...
متن کامل