Bridging the gap: A survey on integrating (human) feedback for natural language generation
Natural language generation has witnessed significant advancements due to the training of
large language models on vast internet-scale datasets. Despite these advancements, there …
large language models on vast internet-scale datasets. Despite these advancements, there …
xTower: A multilingual LLM for explaining and correcting translation errors
While machine translation (MT) systems are achieving increasingly strong performance on
benchmarks, they often produce translations with errors and anomalies. Understanding …
benchmarks, they often produce translations with errors and anomalies. Understanding …
BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation
Although neural-based machine translation evaluation metrics, such as COMET or BLEURT,
have achieved strong correlations with human judgements, they are sometimes unreliable in …
have achieved strong correlations with human judgements, they are sometimes unreliable in …
Multi-pass Decoding for Grammatical Error Correction
X Wang, L Mu, J Zhang, H Xu - Proceedings of the 2024 …, 2024 - aclanthology.org
Abstract Sequence-to-sequence (seq2seq) models achieve comparable or better
grammatical error correction performance compared to sequence-to-edit (seq2edit) models …
grammatical error correction performance compared to sequence-to-edit (seq2edit) models …
Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages
This exploratory study investigates the potential of multilingual Automatic Post-Editing (APE)
systems to enhance the quality of machine translations for low-resource Indo-Aryan …
systems to enhance the quality of machine translations for low-resource Indo-Aryan …
Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs
In recent years, neural machine translation (NMT) has been widely used in everyday life.
However, the current NMT lacks a mechanism to adjust the difficulty level of translations to …
However, the current NMT lacks a mechanism to adjust the difficulty level of translations to …
[PDF][PDF] Leveraging chatgpt and multilingual knowledge graph for automatic post-editing
Recently, ChatGPT has shown promising results for Machine Translation (MT). However,
how to apply ChatGPT for Automatic Post-Editing (APE) remains as an open question. In this …
how to apply ChatGPT for Automatic Post-Editing (APE) remains as an open question. In this …
Enhancing Translation Quality: A Comparative Study of Fine-Tuning and Prompt Engineering in Dialog-Oriented Machine Translation Systems. Insights from the …
L Zhu, M Zimina-Poirot, B Namdarzadeh… - Ninth Conference on …, 2024 - hal.science
For this shared task, we have used several machine translation engines to produce
translations (en⇔ fr) by fine-tuning a dialog-oriented NMT engine and having NMT baseline …
translations (en⇔ fr) by fine-tuning a dialog-oriented NMT engine and having NMT baseline …
Improving Automatic Post-editing with Error Prompts Extracted from Quality Estimation
M Xu, Y Zhang - CCF International Conference on Natural Language …, 2024 - Springer
This work introduces a simple yet effective approach to integrate Automatic Post-editing
(APE) with Word Level Quality Estimation (QE) using an encoder-decoder Transformer …
(APE) with Word Level Quality Estimation (QE) using an encoder-decoder Transformer …
Automatic Decomposition of Text Editing Examples into Primitive Edit Operations: Toward Analytic Evaluation of Editing Systems
This paper presents our work on a task of automatic decomposition of text editing examples
into primitive edit operations. Toward a detailed analysis of the behavior of text editing …
into primitive edit operations. Toward a detailed analysis of the behavior of text editing …