Papers by Zhousi Chen
Neural Combinatory Constituency Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to constituency parsing are based on symbolic engineering, but they are simplified by their adaptive distributed representation. |
| Approach: | They propose two fast combinatory models for constituency parsing: binary and multibranching. |
| Outcome: | The proposed models achieve an F1 score of 92.54 on Penn Treebank, speeding at 1327.2 sents/sec. |
Query Generation Using GPT-3 for CLIP-Based Word Sense Disambiguation for Image Retrieval (2023.starsem-1)
Copied to clipboard
| Challenge: | Existing studies show that human-like prompts with quotes benefit both CLIP and GPT-3 as implicit word sense disambiguation components. |
| Approach: | They propose using the GPT-3 as a query generator for the backend of CLIP as an implicit word sense disambiguation component for the SemEval 2023 shared task Visual Word Sense Disambiguation. |
| Outcome: | The proposed query generator for CLIP is an implicit word sense disambiguation component for the SemEval 2023 shared task Visual Word Sense Disambiguation (VWSD). human-like prompts adapted for WSD with quotes benefit both CLIP and GPT-3, whereas plain phrases or poorly templated prompts give the worst results. |
Discontinuous Combinatory Constituency Parsing (2023.tacl-1)
Copied to clipboard
| Challenge: | Discontinuous parsing is more challenging than continuous parsers because children can group with syntactic cousins in the sentence rather than its two adjacent neighbors. |
| Approach: | They extend a pair of combinator-based constituency parsers into a discontinuous pair . they use a swap action and biaffine attention to iteratively compose constituent vectors from word embeddings without any grammar constraints. |
| Outcome: | The proposed parsers achieve state-of-the-art discontinuous accuracy with a significant speed advantage over continuous parsing. |
A Fair Comparison without Translationese: English vs. Target-language Instructions for Multilingual LLMs (2025.naacl-short)
Copied to clipboard
| Challenge: | Prior studies suggested that English instructions are more effective for non-English tasks . however, these studies often use datasets and instructions translated from English . |
| Approach: | They conduct a fair comparison between English and target-language instructions by eliminating translationese effects. |
| Outcome: | The results show that the advantage of adopting English instructions is not overwhelming . the results also show that instruction-following abilities are improved when using respective instructions. |