Жергілікті сезімтал хештеу
Related Papers
Unsupervised Word Sense Induction from Multiple Semantic Spaces with Locality Sensitive Hashing
Word Sense Disambiguation is the task dedi- cated to the problem of finding out the sense of a word in context, from all of its many pos- sible senses. Solving …...
Streaming First Story Detection with application to Twitter
With the recent rise in popularity and size of social media, there is a growing need for sys- tems that can extract useful information from this amount of data. We …...
A Minimally Supervised Approach for Detecting and Ranking Document Translation Pairs
We describe an approach for generating a ranked list of candidate document transla- tion pairs without the use of bilingual dic- tionary or machine translation system. We developed this approach …...
Using paraphrases for improving first story detection in news and Twitter
First story detection (FSD) involves identify- ing first stories about events from a continuous stream of documents. A major problem in this task is the high degree of lexical variation …...
Trading accuracy for faster named entity linking
Named entity linking (NEL) can be applied to documents such as financial reports, web pages and news articles, but state of the art disambiguation techniques are currently too slow for …...
Integrating a Large, Monolingual Corpus as Translation Memory into Statistical Machine translation
Translation memories (TM) are widely used in the localization industry to im- prove consistency and speed of human translation. Several approaches have been presented to integrate the bilingual trans- lation …...
Learning Translation Models from Monolingual Continuous Representations
Translation models often fail to generate good translations for infrequent words or phrases. Previous work attacked this problem by in- ducing new translation rules from monolin- gual data with a …...
Deduplication of Scholarly Documents using Locality Sensitive Hashing and Word Embeddings
AbstractDeduplication is the task of identifying near and exact duplicate data items in a collection. In this paper, we present a novel method for deduplication of scholarly documents. We develop …...
A Strong Baseline for Query Efficient Attacks in a Black Box Setting
AbstractExisting black box search methods have achieved high success rate in generating adversarial attacks against NLP models. However, such search methods are inefficient as they do not consider the amount …...
On-Device Text Representations Robust To Misspellings via Projections
AbstractRecently, there has been a strong interest in developing natural language applications that live on personal devices such as mobile phones, watches and IoT with the objective to preserve user …...
HashFormers: Towards Vocabulary-independent Pre-trained Transformers
AbstractTransformer-based pre-trained language models are vocabulary-dependent, mapping by default each token to its corresponding embedding. This one-to-one mapping results into embedding matrices that occupy a lot of memory (i.e. millions …...
Locality-Sensitive Hashing for Long Context Neural Machine Translation
AbstractAfter its introduction the Transformer architecture quickly became the gold standard for the task of neural machine translation. A major advantage of the Transformer compared to previous architectures is the …...
Revisiting Locality Sensitive Hashing for Vocabulary Selection in Fast Neural Machine Translation
AbstractNeural machine translation models often contain large target vocabularies. The calculation of logits, softmax and beam search is computationally costly over so many classes. We investigate the use of locality …...