Discourse-level features for statistical machine translation

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Genes implicated in translation control have been associated with autism spectrum disorders (ASDs). However, some important genetic causes of autism, including the 16p11.2 microdeletion, bear no obvious connection to translation. Here, we use proteomics, g ...

The thesis explores the issue of fairness in the real-time (RT) control of battery energy storage systems (BESSs) hosted in active distribution networks (ADNs) in the presence of uncertainties by proposing and experimentally validating appropriate control ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Extracting maximal information from experimental data requires access to the likelihood function, which however is never directly available for complex experiments like those performed at high energy colliders. Theoretical predictions are obtained in this ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

The quality of automatic transcription of heritage documents, whether from printed, manuscripts or audio sources, has a decisive impact on the ability to search and process historical texts. Although significant progress has been made in text recognition ( ...

Dense image-based prediction methods have advanced tremendously in recent years. Their remarkable development has been possible due to the ample availability of real-world imagery. While these methods work well on photographs, their abilities do not genera ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

Text Reuse reveals meaningful reiterations of text in large corpora. Humanities researchers use text reuse to study, e.g., the posterior reception of influential texts or to reveal evolving publication practices of historical media. This research is often ...

Objective. Syntax involves complex neurobiological mechanisms, which are difficult to disentangle for multiple reasons. Using a protocol able to separate syntactic information from sound information we investigated the neural causal connections evoked by t ...

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

This paper examines how the European press dealt with the no-vax reactions against the Covid-19 vaccine and the dis- and misinformation associated with this movement. Using a curated dataset of 1786 articles from 19 European newspapers on the anti-vaccine ...

Abstractive summarization has seen big improvements in recent years, mostly due to advances in neural language modeling, language model pretraining, and scaling models and datasets. While large language models generate summaries that are fluent, coherent, ...

Polymer brushes have been theoretically described, their behavior under diverse conditions has been modeled, and their preparation via surface-initiated polymerizations (SIPs) has been progressively refined. However, despite three decades of research endea ...

Vision-Language Pre-training (VLP) has advanced the performance of many visionlanguage tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous w ...

Technology supporting meditation is a multimillion-dollar market that continues to grow. There is also strong academic interest to understand and improve the impact technology can have for the user experience of practitioners. However, little work investig ...

End-to-end learning methods like deep neural networks have been the driving force in the remarkable progress of machine learning in recent years. However, despite their success, the deployment process of such networks in safety-critical use cases, such as ...

The Dependent Object Type (DOT) calculus was designed to put Scala on a sound basis, but while DOT relies on structural subtyping, Scala is a fundamentally class-based language. This impedance mismatch means that a proof of DOT soundness by itself is ...

Discourse-level features for statistical machine translation

Chat with Graph Search

The autism susceptibility kinase, TAOK2, phosphorylates eEF2 and modulates translation

Fair real-time control of energy storage systems in active distribution networks in the presence of uncertainties

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Boosting likelihood learning with event reweighting

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Post-correction of Historical Text Transcripts with Large Language Models: An Exploratory Study

Dense Image-based Predictions for Comics Analysis

Transformer Models for Vision

Regularization Techniques for Low-Resource Machine Translation

Modeling Structured Data in Attention-based Models

impresso Text Reuse at Scale. An interface for the exploration of text reuse data in semantically enriched historical newspapers

Event-related causality in stereo-EEG discriminates syntactic processing of noun phrases and verb phrases

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Examining European Press Coverage of the Covid-19 No-Vax Movement: An NLP Framework

Interpretable Representation Learning and Evaluation for Abstractive Summarization

Opportunities, Challenges, and Pitfalls in Making, Characterizing, and Understanding Polymer Brushes

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Adapting Haptic Feedback for Guided Meditation

Estimating and Improving the Robustness of Attributions in Text

Type-Preserving Compilation of Class-Based Languages