相关论文: Gibberish Semantics: How Good is Russian Twitter i…

In recent years several novel models were developed to process natural language, development of accurate language translation systems have helped us overcome geographical barriers and communicate ideas effectively. These models are…

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language…

There has been an influx of biomedical domain-specific language models, showing language models pre-trained on biomedical text perform better on biomedical domain benchmarks than those trained on general domain text corpora such as…

The paper is devoted to the creation of the semantic sketches for English verbs. The pilot corpus consists of the English-Russian sketch pairs and is aimed to show what kind of contrastive studies the sketches help to conduct. Special…

When deriving contextualized word representations from language models, a decision needs to be made on how to obtain one for out-of-vocabulary (OOV) words that are segmented into subwords. What is the best way to represent these words with…

The rapid advancement of social media enables us to analyze user opinions. In recent times, sentiment analysis has shown a prominent research gap in understanding human sentiment based on the content shared on social media. Although…

Distributed representations of words and paragraphs as semantic embeddings in high dimensional data are used across a number of Natural Language Understanding tasks such as retrieval, translation, and classification. In this work, we…

Pre-training large-scale language models (LMs) requires huge amounts of text corpora. LMs for English enjoy ever growing corpora of diverse language resources. However, less resourced languages and their mono- and multilingual LMs often…

We study the role of the second language in bilingual word embeddings in monolingual semantic evaluation tasks. We find strongly and weakly positive correlations between down-stream task performance and second language similarity to the…

Developing natural language processing (NLP) systems for social media analysis remains an important topic in artificial intelligence research. This article introduces RoBERTweet, the first Transformer architecture trained on Romanian…

This paper measures similarity both within and between 84 language varieties across nine languages. These corpora are drawn from digital sources (the web and tweets), allowing us to evaluate whether such geo-referenced corpora are reliable…

The vocabulary mismatch problem is a long-standing problem in information retrieval. Semantic matching holds the promise of solving the problem. Recent advances in language technology have given rise to unsupervised neural models for…

With internet quickly becoming an easy access to many, voice calling over internet is slowly gaining momentum. Individuals has been engaging in video communication across the world in different languages. The decade saw the emergence of…

A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little attention has…

Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by…

A recent study has shown that, compared to human translations, neural machine translations contain more strongly-associated formulaic sequences made of relatively high-frequency words, but far less strongly-associated formulaic sequences…

Word-vector representations associate a high dimensional real-vector to every word from a corpus. Recently, neural-network based methods have been proposed for learning this representation from large corpora. This type of word-to-vector…

Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to `vector similarity searching' over dense semantic representations of words and documents that can be…

Inspired by the inductive transfer learning on computer vision, many efforts have been made to train contextualized language models that boost the performance of natural language processing tasks. These models are mostly trained on large…

Various social networks have been allowing media uploads for over a decade now. Still, it has not always been clear what is their relation with the posted text or even if there is any at all. In this work, we explore how multilingual…