Related papers: Fine-tuning the SwissBERT Encoder Model for Embedd…
Contextual language models have been trained on Classical languages, including Ancient Greek and Latin, for tasks such as lemmatization, morphological tagging, part of speech tagging, authorship attribution, and detection of scribal errors.…
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…
Since the appearance of BERT, recent works including XLNet and RoBERTa utilize sentence embedding models pre-trained by large corpora and a large number of parameters. Because such models have large hardware and a huge amount of data, they…
Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either…
In this paper, we present a multi-lingual sentence encoder that can be used in search engines as a query and document encoder. This embedding enables a semantic similarity score between queries and documents that can be an important feature…
BERT (Bidirectional Encoder Representations from Transformers) and ALBERT (A Lite BERT) are methods for pre-training language models which can later be fine-tuned for a variety of Natural Language Understanding tasks. These methods have…
Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for…
Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text embedding models in a compute-optimal fashion, given a suite…
We propose an automated image selection system to assist photo editors in selecting suitable images for news articles. The system fuses multiple textual sources extracted from news articles and accepts multilingual inputs. It is equipped…
The multilingual Sentence-BERT (SBERT) models map different languages to common representation space and are useful for cross-language similarity and mining tasks. We propose a simple yet effective approach to convert vanilla multilingual…
We explore to what extent knowledge about the pre-trained language model that is used is beneficial for the task of abstractive summarization. To this end, we experiment with conditioning the encoder and decoder of a Transformer-based…
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…
We provide the first exploration of sentence embeddings from text-to-text transformers (T5). Sentence embeddings are broadly useful for language processing tasks. While T5 achieves impressive performance on language tasks cast as…
The growing volume of digitized historical texts requires effective semantic search using text embeddings. However, pre-trained multilingual models face challenges with historical content due to OCR noise and outdated spellings. This study…
Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a…
Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et al., 2018) to address the lack of high-quality, large-scale…
Multilingual pretrained language models have demonstrated remarkable zero-shot cross-lingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and evaluating on a distinct language, not seen…
The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research…
Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks. Contextual embeddings assign each word a…
Large pre-trained language models such as BERT have been the driving force behind recent improvements across many NLP tasks. However, BERT is only trained to predict missing words - either behind masks or in the next sentence - and has no…