Papers by Shaonan Wang

16 papers
Associative Multichannel Autoencoder for Multimodal Word Representation (D18-1)

Copied to clipboard

Challenge: Existing models that represent word meanings from word co-occurrences ignore associations between modalities and lack ability to transfer information between .
Approach: They propose a novel associative multichannel autoencoder that integrates textual, visual and auditory inputs to learn multimodal word representations.
Outcome: The proposed model outperforms strong unimodal models and state-of-the-art models on six benchmark concepts similarity tests.
How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models? (2022.lrec-1)

Copied to clipboard

Challenge: Recent studies have shown that neural encoding models explore brain language processing using naturalistic stimuli.
Approach: They propose a block-wise cross-validation training method and an adequate data size for increasing the performance of neural encoding models.
Outcome: The proposed training method and data size can significantly decrease the performance of neural encoding models in the temporal and frontal lobes.
Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs (2026.acl-long)

Copied to clipboard

Challenge: Decoder-only large language models are brittle to minor grammatical perturbations, causing reliability problems.
Approach: They propose a checkpoint-compatible gated tree cross-attention branch that reads constituency chunk memory while keeping the backbone architecture unchanged.
Outcome: The proposed framework strengthens syntactic competence beyond continued training benchmarks and transformer backbones without compromising commonsense reasoning.
X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions (2024.findings-acl)

Copied to clipboard

Challenge: Large language models respond well in high-resource languages but struggle in low-resourced languages.
Approach: They propose a method to construct cross-lingual instruction following samples with instruction in English and response in low-resource languages.
Outcome: The proposed method builds a large-scale cross-lingual instruction tuning dataset on 10 languages.
Cross-Modal Cloze Task: A New Task to Brain-to-Word Decoding (2022.findings-acl)

Copied to clipboard

Challenge: Existing work on decoding language from non-invasive brain activity is limited due to noisy nature of brain recordings.
Approach: They propose a cross-modal cloze task to predict a word from a neural image . they use a pre-trained language model to leverage the pre-training language model .
Outcome: The proposed method outperforms baselines on 20 participants from two brain imaging datasets.
Is the Brain Mechanism for Hierarchical Structure Building Universal Across Languages? An fMRI Study of Chinese and English (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies have shown that the brain builds hierarchical syntactic structures, but it is unknown whether they are universal across languages.
Approach: They analyze the working memory requirements when applying parsing strategies to two languages: Chinese and English.
Outcome: The proposed method shows that the brain adopts parsing strategies with less memory load according to different language structures.
Discovering Semantic Subdimensions through Disentangled Conceptual Representations (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches focus on predefined dimensions that overlook finer conceptual distinctions . a new framework is proposed to investigate the subdimensions underlying coarse-grained semantic dimensions .
Approach: They propose a framework that decomposes word embeddings into multiple sub-embeddings . they propose to map these subdimensions to brain activation to assess their plausibility .
Outcome: The proposed framework decomposes word embeddings from large language models into sub-embeddings, each encoding specific semantic information.
Do Neural Language Models Inferentially Compose Concepts the Way Humans Can? (2024.lrec-main)

Copied to clipboard

Challenge: a new study shows that language models and humans may rely on different approaches to represent and compose lexical items across sentence structure.
Approach: They propose to use a dataset to test the performance of neural language models and humans on inferentially driven conceptual compositions.
Outcome: The proposed model elicits probability estimates for a noun in a minimally composed phrase . RoBERTa, BERT-large, and GPT-2 exhibited the closest resemblance to human responses .
Distill and Replay for Continual Language Learning (2020.coling-main)

Copied to clipboard

Challenge: Existing models fail to isolate acquired knowledge and forget previously learned tasks when learning in a stream where data distribution may shift.
Approach: They propose a framework that distills knowledge and replays experience from previous tasks when fitting on a new task.
Outcome: The proposed framework outperforms state-of-the-art models in continuously learning tasks of the same type but from different domains, as well as tasks of different types.
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning (2023.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that multi-head attention module evolves functional specialization after multi-task training.
Approach: They propose a method to quantify the degree of functional specialization in multi-head attention . they propose 'multi-task training' method to increase functional specialisation and mitigate negative information transfer .
Outcome: The proposed method increases functional specialization and mitigates negative information transfer in multi-task learning without adding any parameters.
Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment (2024.naacl-long)

Copied to clipboard

Challenge: Existing studies show that multilingual generative models exhibit a strong language bias toward high-resource languages.
Approach: They propose a cross-lingual alignment framework exploiting pairs of translation sentences to improve cross-linguistic abilities.
Outcome: The proposed framework improves cross-lingual abilities and mitigates performance gap.
Computational Linguistics for Brain Encoding and Decoding: Principles, Practices and Beyond (2024.acl-tutorials)

Copied to clipboard

Challenge: This tutorial will explore the potential of computational linguistics to help understand brain language processing.
Approach: This tutorial will explore the principles and practices of using computational linguistics methods for brain encoding and decoding.
Outcome: This tutorial will explore the principles and practices of using computational linguistics methods for brain encoding and decoding.
Memory, Show the Way: Memory Based Few Shot Word Representation Learning (D18-1)

Copied to clipboard

Challenge: Existing word embedding methods for distributed semantic models require limited examples to learn a high quality representation.
Approach: They propose a memory-based embedding learning method capable of acquiring word representations from limited context.
Outcome: The proposed method delivers impressive performance on two challenging few-shot word similarity tasks.
Decoding the Multimodal Mind: Generalizable Brain-to-Text Translation via Multimodal Alignment and Adaptive Routing (2026.findings-acl)

Copied to clipboard

Challenge: Current approaches to decoding language from the human brain rely on unimodal representations, neglecting the brain’s inherently multimodal processing.
Approach: They propose a framework that leverages Multimodal Large Language Models to align brain signals with a shared semantic space encompassing text, images, and audio.
Outcome: The proposed framework achieves an 8.48% improvement on the most commonly used benchmark on fMRI datasets with textual, visual, and auditory stimuli.
MapGuide: A Simple yet Effective Method to Reconstruct Continuous Language from Brain Activities (2024.naacl-long)

Copied to clipboard

Challenge: Decoding continuous language from brain activity is a formidable but promising field of research . previous attempts to map brain activity to text relied on learning to encode brain activity .
Approach: They propose a method that maps brain activity to text embeddings by directly comparing them with predicted brain responses.
Outcome: The proposed method outperforms the current state-of-the-art model showing improvements on BLEU and METEOR scores.
NCLS: Neural Cross-Lingual Summarization (D19-1)

Copied to clipboard

Challenge: Existing approaches to cross-lingual summarization divide the task into two steps: summarizing and translation.
Approach: They propose to integrate two related tasks into the training process of CLS under multi-task learning to improve cross-lingual summarization.
Outcome: The proposed framework improves on English-to-Chinese and Chinese-to English CLS human-corrected test sets.

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