paper-with-me

Papers

Using Semantic Role Labeling to Improve Neural Machine Translation

2022-06-01 · LREC 2022 6 · Reinhard Rapp

Despite impressive progress in machine translation in recent years, it has occasionally been argued that current systems are still mainly based on pattern recognition and that further progress may be possible by using text understanding techniques, thereby e.g. looking at semantics of the type “Who is doing what to whom?”. In the current research we aim to take a small step into this direction. Assuming that semantic role labeling (SRL) grasps some of the relevant semantics, we automatically annotate the source language side of a standard parallel corpus, namely Europarl, with semantic roles. We then train a neural machine translation (NMT) system using the annotated corpus on the source language side, and the original unannotated corpus on the target language side. New text to be translated is first annotated by the same SRL system and then fed into the translation system. We compare the results to those of a baseline NMT system trained with unannotated text on both sides and find that the SRL-based system yields small improvements in terms of BLEU scores for each of the four language pairs under investigation, involving English, French, German, Greek and Spanish.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTSemantic Role LabelingTranslation

Similar Papers 제목 키워드 기반

Alignment-free Cross-lingual Semantic Role Labeling

2020-11-01 · EMNLP 2020 11 · Rui Cai, Mirella Lapata

Cross-lingual semantic role labeling (SRL) aims at leveraging resources in a source language to minimize the effort required to construct annotations or models for a new target language. Recent approaches rely on word al…

Machine TranslationMultilingual Word EmbeddingsSemantic Role LabelingTranslation+1

Persian Semantic Role Labeling Using Transfer Learning and BERT-Based Models

2023-06-17 · Saeideh Niksirat Aghdam, Sayyed Ali Hossayni, Erfan Khedersolh Sadeh, Nasim Khozouei 외

Semantic role labeling (SRL) is the process of detecting the predicate-argument structure of each predicate in a sentence. SRL plays a crucial role as a pre-processing step in many NLP applications such as topic and conc…

Machine TranslationQuestion AnsweringSemantic Role LabelingSentence+2

An MRC Framework for Semantic Role Labeling

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tas…

Computational EfficiencyMachine Reading ComprehensionMultiple-choiceReading Comprehension+2

Transferring Semantic Roles Using Translation and Syntactic Information

2017-10-03 · IJCNLP 2017 11 · Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab

Our paper addresses the problem of annotation projection for semantic role labeling for resource-poor languages using supervised annotations from a resource-rich language through parallel data. We propose a transfer meth…

Semantic Role LabelingTranslationWord Alignment

An MRC Framework for Semantic Role Labeling

2021-09-14 · COLING 2022 10 · Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun 외

Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tas…

Computational EfficiencyMachine Reading ComprehensionMultiple-choiceReading Comprehension+2