paper-with-me

Papers

DiscoTK: Using Discourse Structure for Machine Translation Evaluation

2019-11-28 · WS 2014 6 · Shafiq Joty, Francisco Guzman, Lluis Marquez, Preslav Nakov

We present novel automatic metrics for machine translation evaluation that use discourse structure and convolution kernels to compare the discourse tree of an automatic translation with that of the human reference. We experiment with five transformations and augmentations of a base discourse tree representation based on the rhetorical structure theory, and we combine the kernel scores for each of them into a single score. Finally, we add other metrics from the ASIYA MT evaluation toolkit, and we tune the weights of the combination on actual human judgments. Experiments on the WMT12 and WMT13 metrics shared task datasets show correlation with human judgments that outperforms what the best systems that participated in these years achieved, both at the segment and at the system level.

📄 PDF Abstract BibTeX arXiv:1911.12547

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Discourse Structure in Machine Translation Evaluation

2017-10-04 · CL 2017 12 · Shafiq Joty, Francisco Guzmán, Lluís Màrquez, Preslav Nakov

In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare disc…

Machine TranslationSentenceTranslation

Using Discourse Structure Improves Machine Translation Evaluation

2014-06-01 · ACL 2014 6 · Francisco Guzm{\'a}n, Shafiq Joty, Llu{\'\i}s M{\`a}rquez, Preslav Nakov
Machine TranslationTranslation

A Bilingual Discourse Corpus and Its Applications

2016-05-01 · LREC 2016 5 · Yang Liu, Jiajun Zhang, Cheng-qing Zong, Yating Yang 외

Existing discourse research only focuses on the monolingual languages and the inconsistency between languages limits the power of the discourse theory in multilingual applications such as machine translation. To address …

Machine TranslationTranslation

Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus

2023-05-18 · Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang 외

Several recent papers claim human parity at sentence-level Machine Translation (MT), especially in high-resource languages. Thus, in response, the MT community has, in part, shifted its focus to document-level translatio…

Machine TranslationSentenceTranslation

How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups

2026-06-15 · Wafaa Mohammed, Kata Naszadi, Vlad Niculae arxiv

Existing machine translation (MT) metrics and discourse-focused evaluations primarily assess translation quality intrinsically, without measuring the downstream consequences of translation errors. In this work, we focus …

Machine Translation