Оптимальный транспорт

AbstractWe propose a novel manifold based geometric approach for learning unsupervised alignment of word embeddings between the source and the target languages. Our approach formulates the alignment learning problem as …...

AbstractNeural language models are often trained with maximum likelihood estimation (MLE), where the next word is generated conditioned on the ground-truth word tokens. During testing, however, the model is instead …...

AbstractSelecting input features of top relevance has become a popular method for building self-explaining models. In this work, we extend this selective rationalization approach to text matching, where the goal …...

AbstractIn sequence-to-sequence models, classical optimal transport (OT) can be applied to semantically match generated sentences with target sentences. However, in non-parallel settings, target sentences are usually unavailable. To tackle this …...

AbstractConventional neural generative models tend to generate safe and generic responses which have little connection with previous utterances semantically and would disengage users in a dialog system. To generate relevant …...

AbstractEvent Detection (ED) aims to recognize mentions of events (i.e., event triggers) and their types in text. Recently, several ED datasets in various domains have been proposed. However, the major …...

AbstractIn this work, we focus on Cross-Lingual Event Detection where a model is trained on data from a source language but its performance is evaluated on data from a second, …...

AbstractEvent Argument Extraction (EAE) is one of the sub-tasks of event extraction, aiming to recognize the role of each entity mention toward a specific event trigger. Despite the success of …...

AbstractKeyphrase generation aims to generate a set of condensed phrases given a source document. Although maximum likelihood estimation (MLE) based keyphrase generation methods have shown impressive performance, they suffer from …...

AbstractWe present a new scientific document similarity model based on matching fine-grained aspects of texts. To train our model, we exploit a naturally-occurring source of supervision: sentences in the full-text …...

AbstractPre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT). However, it usually fails to achieve notable gains (some- times, even worse) on resource-rich NMT …...

AbstractMotivated by the widespread interest in the cross-lingual transfer of NLP models from high resource to low resource languages, research on Cross-lingual word embeddings (CLWEs) has gained much popularity over …...

AbstractText style transfer (TST) is a well-known task whose goal is to convert the style of the text (e.g., from formal to informal) while preserving its content. Recently, it has …...

AbstractThe concerning rise of hateful content on online platforms has increased the attention towards automatic hate speech detection, commonly formulated as a supervised classification task. State-of-the-art deep learning-based approaches usually …...

AbstractEvent Detection (ED) aims to identify mentions/triggers of real world events in text. In the literature, this task is modeled as a sequence-labeling or word-prediction problem. In this work, we …...

AbstractOpen Information Extraction (OIE) seeks to extract structured information from raw text without the limitations of close ontology. Recently, the detection-based OIE methods have received great attention from the community …...

AbstractThis paper focuses on the task of cross domain few-shot named entity recognition (NER), which aims to adapt the knowledge learned from source domain to recognize named entities in target …...

AbstractNeural machine translation (NMT) has become the de-facto standard in real-world machine translation applications. However, NMT models can unpredictably produce severely pathological translations, known as hallucinations, that seriously undermine user …...

AbstractThis paper describes the submission of the UPC Machine Translation group to the IWSLT 2023 Offline Speech Translation task. Our Speech Translation systems utilize foundation models for speech (wav2vec 2.0) …...

AbstractRecent advancements in Large Language Models (LLMs) have drawn increasing attention since the learned embeddings pretrained on large-scale datasets have shown powerful ability in various downstream applications. However, whether the …...

AbstractMonolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling …...