Papers by Tianxiang Xu
Enhancing Language Representation with Constructional Information for Natural Language Understanding (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in natural language processing focus on acquiring lexico-semantic information. |
| Approach: | They propose a construction grammar which highlights the pairings of form and meaning to enrich language representation. |
| Outcome: | The proposed model is superior to existing models on a variety of NLU tasks. |
Constrained Tuple Extraction with Interaction-Aware Network (2023.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge triples lack constraints for their authenticity due to spatial, temporal, or other constraints. |
| Approach: | They propose a constrained tuple extraction task to guarantee the validity of knowledge tifles by using an interaction-aware network to extract constrained text. |
| Outcome: | The proposed model outperforms existing models on the dataset and the public CaRB dataset. |
CxGGEC: Construction-Guided Grammatical Error Correction (2025.acl-long)
Copied to clipboard
| Challenge: | Current GEC methods rely on grammatical labels for syntactic information, often overlooking the inherent usage patterns of language. |
| Approach: | They propose to use construction grammar to capture underlying language patterns and guide corrections by decoding construction tokens into their original forms and correcting erroneous tokens. |
| Outcome: | The proposed model captures underlying language patterns and corrects erroneous construction tokens on English and Chinese benchmarks. |
CoELM: Construction-Enhanced Language Modeling (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that integrating constructional information can improve the performance of pre-trained language models. |
| Approach: | They propose a construction-Enhanced language model that embeds constructional semantics into language models for natural language generation. |
| Outcome: | The proposed model outperforms existing models on various benchmarks. |
DAPE-BR: Distance-Aware Positional Encoding for Mitigating Object Hallucination in LVLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Vision–Language Models (LVLMs) suffer from object hallucination, generating descriptions for objects that are absent from the image, which undermines reliability and hinders real-world deployment. |
| Approach: | They propose a positional-alignment scheme that preserves pretrained weight order while globally—- visual–text distances, embeds an isotropic fused patch-distance metric, and applies a patch-delay causal mask to enforce spatial causality. |
| Outcome: | Extensive experiments on POPE, MMStar and SQA show that DAPE-BR reduces hallucinations and boosts performance. |