Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense
The rise in malicious usage of large language models, such as fake content creation and
academic plagiarism, has motivated the development of approaches that identify AI …
academic plagiarism, has motivated the development of approaches that identify AI …
Interpreting language models with contrastive explanations
Model interpretability methods are often used to explain NLP model decisions on tasks such
as text classification, where the output space is relatively small. However, when applied to …
as text classification, where the output space is relatively small. However, when applied to …
Quantifying the plausibility of context reliance in neural machine translation
Establishing whether language models can use contextual information in a human-plausible
way is important to ensure their safe adoption in real-world settings. However, the questions …
way is important to ensure their safe adoption in real-world settings. However, the questions …
A baseline revisited: Pushing the limits of multi-segment models for context-aware translation
This paper addresses the task of contextual translation using multi-segment models.
Specifically we show that increasing model capacity further pushes the limits of this …
Specifically we show that increasing model capacity further pushes the limits of this …
Clarify when necessary: Resolving ambiguity through interaction with lms
Resolving ambiguities through interaction is a hallmark of natural language, and modeling
this behavior is a core challenge in crafting AI assistants. In this work, we study such …
this behavior is a core challenge in crafting AI assistants. In this work, we study such …
Impact of visual context on noisy multimodal NMT: an empirical study for English to Indian languages
The study investigates the effectiveness of utilizing multimodal information in Neural
Machine Translation (NMT). While prior research focused on using multimodal data in low …
Machine Translation (NMT). While prior research focused on using multimodal data in low …
Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition
Numerous AI-assisted scholarly applications have been developed to aid different stages of
the research process. We present an analysis of AI-assisted scholarly writing generated with …
the research process. We present an analysis of AI-assisted scholarly writing generated with …
Context-aware Neural Machine Translation for English-Japanese Business Scene Dialogues
S Honda, P Fernandes, C Zerva - arXiv preprint arXiv:2311.11976, 2023 - arxiv.org
Despite the remarkable advancements in machine translation, the current sentence-level
paradigm faces challenges when dealing with highly-contextual languages like Japanese …
paradigm faces challenges when dealing with highly-contextual languages like Japanese …
Sequence Shortening for Context-Aware Machine Translation
P Mąka, YC Semerci, J Scholtes… - arXiv preprint arXiv …, 2024 - arxiv.org
Context-aware Machine Translation aims to improve translations of sentences by
incorporating surrounding sentences as context. Towards this task, two main architectures …
incorporating surrounding sentences as context. Towards this task, two main architectures …
Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing
Large Language Models (LLM's) have demonstrated considerable success in various
Natural Language Processing tasks, but they have yet to attain state-of-the-art performance …
Natural Language Processing tasks, but they have yet to attain state-of-the-art performance …