Search Results - "Specia, Lucia"

Data-Driven Sentence Simplification: Survey and Benchmark by Alva-Manchego, Fernando, Scarton, Carolina, Specia, Lucia

“…Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand. In order to do so, several rewriting transformations…”
Get full text

A Survey on Lexical Simplification by Paetzold, Gustavo H., Specia, Lucia

“…Lexical Simplification is the process of replacing complex words in a given sentence with simpler alternatives of equivalent meaning. This task has wide…”
Get full text

The (Un)Suitability of Automatic Evaluation Metrics for Text Simplification by Alva-Manchego, Fernando, Scarton, Carolina, Specia, Lucia

“…In order to simplify sentences, several rewriting operations can be performed, such as replacing complex words per simpler synonyms, deleting unnecessary…”
Get full text

Multimodal machine translation through visuals and speech by Sulubacak, Umut, Caglayan, Ozan, Grönroos, Stig-Arne, Rouhe, Aku, Elliott, Desmond, Specia, Lucia, Tiedemann, Jörg

“…Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain…”
Get full text

Unsupervised Quality Estimation for Neural Machine Translation by Fomicheva, Marina, Sun, Shuo, Yankovskaya, Lisa, Blain, Frédéric, Guzmán, Francisco, Fishel, Mark, Aletras, Nikolaos, Chaudhary, Vishrav, Specia, Lucia

“…Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on…”
Get full text

Read, spot and translate by Specia, Lucia, Wang, Josiah, Lee, Sun Jae, Ostapenko, Alissa, Madhyastha, Pranava

“…We propose multimodal machine translation (MMT) approaches that exploit the correspondences between words and image regions. In contrast to existing work, our…”
Get full text

MSVD-Turkish: a comprehensive multimodal video dataset for integrated vision and language research in Turkish by Citamak, Begum, Caglayan, Ozan, Kuyu, Menekse, Erdem, Erkut, Erdem, Aykut, Madhyastha, Pranava, Specia, Lucia

“…Automatic generation of video descriptions in natural language, also called video captioning , aims to understand the visual content of the video and produce a…”
Get full text

A Quantitative Analysis of Discourse Phenomena in Machine Translation by Scarton, Carolina, Specia, Lucia

“…State-of-the-art Machine Translation (MT) systems translate documents by considering isolated sentences, disregarding information beyond sentence level. As a…”
Get full text

Phrase Localization Without Paired Training Examples by Wang, Josiah, Specia, Lucia

“…Localizing phrases in images is an important part of image understanding and can be useful in many applications that require mappings between textual and…”
Get full text

Taking MT Evaluation Metrics to Extremes: Beyond Correlation with Human Judgments by Fomicheva, Marina, Specia, Lucia

“…Automatic Machine Translation (MT) evaluation is an active field of research, with a handful of new metrics devised every year. Evaluation metrics are…”
Get full text

Supervised Visual Attention for Simultaneous Multimodal Machine Translation by Haralampieva, Veneta, Caglayan, Ozan, Specia, Lucia

“…There has been a surge in research in multimodal machine translation (MMT), where additional modalities such as images are used to improve translation quality…”
Get full text

Leveraging auxiliary image descriptions for dense video captioning by Boran, Emre, Erdem, Aykut, Ikizler-Cinbis, Nazli, Erdem, Erkut, Madhyastha, Pranava, Specia, Lucia

“…•A pipeline that fetches visually relevant images for dense video captioning.•Attention mechanism to include auxiliary phrases within adversarial training.•On…”
Get full text

Machine translation evaluation versus quality estimation by Specia, Lucia, Raj, Dhwaj, Turchi, Marco

“…Most evaluation metrics for machine translation (MT) require reference translations for each sentence in order to produce a score reflecting certain aspects of…”
Get full text

Latent Variable Models for Visual Question Answering by Wang, Zixu, Miao, Yishu, Specia, Lucia

“…Current work on Visual Question Answering (VQA) explore deterministic approaches conditioned on various types of image and question features. We posit that, in…”
Get full text

Kirsten Malmkjær and Kevin Windle (eds.): The Oxford handbook of translation studies: Oxford University Press, 2011, xvii + 607 pp, ISBN: 978-0-19-923930-6 by Specia, Lucia

Get full text

Quality estimation for machine translation: preface by Specia, Lucia, Soricut, Radu

Get full text

A Bayesian non-linear method for feature selection in machine translation quality estimation by Shah, Kashif, Cohn, Trevor, Specia, Lucia

“…We perform a systematic analysis of the effectiveness of features for the problem of predicting the quality of machine translation (MT) at the sentence level…”
Get full text

Predicting and Using Implicit Discourse Elements in Chinese-English Translation by Steele, David, Specia, Lucia

“…In machine translation (MT) implicitation can occur when elements such as discourse markers and pronouns are not expected or mandatory in the source language,…”
Get full text

Investigating the contribution of linguistic information to quality estimation by Felice, Mariano, Specia, Lucia

“…This paper describes a study on the contribution of linguistically-informed features to the task of quality estimation for machine translation at sentence…”
Get full text

Tuning Language Models by Mixture-of-Depths Ensemble by Luo, Haoyan, Specia, Lucia

“…Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for training and final-layer representations for predictions, potentially…”
Get full text