Related papers: On the Language Neutrality of Pre-trained Multilin…
Transformer-based pre-trained language models (PLMs) have achieved remarkable performance in various natural language processing (NLP) tasks. However, pre-training such models can take considerable resources that are almost only available…
Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these settings. Such…
This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing…
We investigate how Multilingual BERT (mBERT) encodes grammar by examining how the high-order grammatical feature of morphosyntactic alignment (how different languages define what counts as a "subject") is manifested across the embedding…
Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…
While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate…
Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models (Wu and Dredze 2019), but only between related languages.…
While recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks, there is a lack of consensus in the community as to what shared properties between languages enable…
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In…
Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…
There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings. State-of-the-art approaches have relied on expensive labeled data, which…
Cross-lingual document representations enable language understanding in multilingual contexts and allow transfer learning from high-resource to low-resource languages at the document level. Recently large pre-trained language models such as…
Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…
Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional…
Multilingual pretraining typically lacks explicit alignment signals, leading to suboptimal cross-lingual alignment in the representation space. In this work, we show that training standard pretrained models for cross-lingual alignment with…
Token embeddings in multilingual BERT (m-BERT) contain both language and semantic information. We find that the representation of a language can be obtained by simply averaging the embeddings of the tokens of the language. Given this…
A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the…
Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level…
Replacing static word embeddings with contextualized word representations has yielded significant improvements on many NLP tasks. However, just how contextual are the contextualized representations produced by models such as ELMo and BERT?…