Papers by Shaonan Wang
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. |