Papers with language and

14 papers
Cross-Lingual Transfer with Target Language-Ready Task Adapters (2023.findings-acl)

Copied to clipboard

Challenge: Existing frameworks for (zero-shot) cross-lingual transfer employ separate language and task adapters which can be arbitrarily combined to perform any task to any target language.
Approach: They propose to fine-tune 'target language-ready' adapters to the target language to achieve better transfer performance without sacrificing the modularity of MAD-X.
Outcome: The proposed adapters outperform MAD-X and BAD-X on most tasks and languages while maintaining the modularity of MAD.
RB-LoRA: Rank-Balanced Aggregation for Low-Rank Adaptation with Federated Fine-Tuning (2026.findings-eacl)

Copied to clipboard

Challenge: Low-rank adaptation (LoRA) improves fine-tuning of foundation models by updating only compact adapter matrices . varying client device capabilities lead to different adapter ranks, causing rank heterogeneity that undermines aggregation.
Approach: They propose a rank-balanced aggregation framework that decomposes each update into rank-wise components and aligns them using analytically derived weights.
Outcome: Experiments on language and vision models show that RB-LoRA improves under one and three rounds of communication in federated learning environments.
Unifying Cross-Lingual Transfer across Scenarios of Resource Scarcity (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to deal with resource scarcity have not been developed to deal effectively with the problem.
Approach: They propose to use a set of tools to harness data from one or more high-resource "source" languages to compensate for a shortage of data in low-resourced "target" languages.
Outcome: The proposed technique can be easily adapted to unseen languages, extending the range of the proposed technique and translation-based transfer more broadly.
ProsocialDialog: A Prosocial Backbone for Conversational Agents (2022.emnlp-main)

Copied to clipboard

Challenge: Existing dialogue systems fail to respond properly to potentially unsafe user utterances . existing systems either ignore or passively agree with unsafe content .
Approach: They introduce a dataset to teach conversational agents to respond to problematic content following social norms.
Outcome: The proposed dataset shows that ProsocialDialog generates more socially acceptable dialogues than existing models.
Jejueo Datasets for Machine Translation and Speech Synthesis (2020.lrec-1)

Copied to clipboard

Challenge: Jejueo, or the Jeju language, is a minority language used on Jeju Island . there have been many efforts to revitalize the language, but few computational approaches have been used to solve its problems.
Approach: They construct two new Jejueo datasets using interviews and transcripts . they build machine translation and speech synthesis using these datasets based on their results .
Outcome: The proposed datasets will attract interest of both language and machine learning communities.
BabyCloud, a Technological Platform for Parents and Researchers (L18-1)

Copied to clipboard

Challenge: a platform for capturing, storing and analyzing day-long audio recordings and photos of children's linguistic environments is proposed . the proposed platform connects families and academics, with strong innovation potential for each type of users.
Approach: They propose a platform for capturing, storing and analyzing audio recordings and photos of children's linguistic environments.
Outcome: The proposed platform connects families and academics with strong innovation potential for each type of users.
Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Multimodal instruction tuning often causes catastrophic forgetting of the base LLM’s language ability, even in strong models like Llama3.
Approach: They propose a training-free parameter fusion framework that locates important parameters and selectively merges them.
Outcome: The proposed framework preserves the influence of neurons with large parameter shifts while attenuating the influence . of neurons likely responsible for newly acquired visual capabilities while mitigating language degradation.
ISAAQ - Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention (2020.emnlp-main)

Copied to clipboard

Challenge: Textbook Question Answering is a complex task that requires reasoning with multimodal information from text and diagrams.
Approach: They propose to use transformer language models and bottom-up and top-down attention to tackle the language and visual understanding challenges of text and diagrams.
Outcome: The proposed system achieves unprecedented accuracies on all TQA question types . the system also obtains state-of-the-art results in other demanding datasets .
Train Once, Use Flexibly: A Modular Framework for Multi-Aspect Neural News Recommendation (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent neural news recommenders (NNRs) extend content-based recommendation by aligning additional aspects between candidate news and user history or diversifying recommendations w.r.t. these aspects require retraining of the model with a modified objective.
Approach: They introduce a modular framework for multi-aspect neural news recommendation that supports on-the-fly customization over individual aspects at inference time.
Outcome: The proposed framework outperforms state-of-the-art NNRs on both content-based recommendation and single- and multi-aspect customization.
R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Reasoning is a fundamental capability underpinning text-to-image (T2I) generation.
Approach: They propose a benchmark to rigorously assess reasoning-driven T2I generation.
Outcome: Experiments with 16 representative T2I models show limited reasoning performance . a strong pipeline-based framework decouples reasoning and generation .
CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Copied to clipboard

Challenge: End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach: They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome: The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.
Project MOSLA: Recording Every Moment of Second Language Acquisition (2024.lrec-main)

Copied to clipboard

Challenge: Second language acquisition (SLA) is a complex and dynamic process.
Approach: They created a longitudinal, multimodal, multilingual, and controlled dataset by inviting participants to learn one of three target languages from scratch over a span of two years, exclusively through online instruction.
Outcome: The proposed dataset sheds light on the complex and dynamic nature of the acquisition of a second language and its implications for proficiency assessment, language and speech processing, and multimodal learning analytics.
GraphAgent: Agentic Graph Language Assistant (2025.emnlp-main)

Copied to clipboard

Challenge: Real-world data combines structured and unstructured formats, capturing explicit relationships and implicit semantic interdependencies.
Approach: They propose GraphAgent, an automated agent pipeline addressing both explicit and implicit graph-enhanced semantic dependencies for predictive and generative tasks.
Outcome: Extensive experiments on diverse datasets validate GraphAgent’s effectiveness in graph-related predictive and text generative tasks.
From Words to Pixels: A Comprehensive Survey on Large Language Models in Visual Segmentation (2026.acl-long)

Copied to clipboard

Challenge: Visual segmentation with instruction has been a challenging task for many years . large language models and large multimodal models have spurred a new wave of research .
Approach: They review recent works in LLM-based visual segmentation and analyze their architectural innovations, training strategies, and benchmark performance.
Outcome: The present study reviews the most recent works in LLM-driven visual segmentation . it identifies key challenges and promising future directions .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations