Papers by Ho Hung Lim
Unsupervised Paraphrasability Prediction for Compound Nominalizations (2022.naacl-main)
Copied to clipboard
| Challenge: | Nominalizations can be difficult to interpret because of ambiguous semantic relations between deverbal noun and its arguments. |
| Approach: | They propose to over-generate clausal paraphrases to predict whether a prenominal modifier can be re-written as a noun or adverb in a claual paraphrasability. |
| Outcome: | The proposed method improves paraphrasability prediction and paraphrase generation in English . it shows that the prenominal modifier can be re-written as a noun or adverb in a clausal paraphrase . |
Automatic Nominalization of Clauses through Textual Entailment (2022.coling-1)
Copied to clipboard
| Challenge: | Past research on clause nominalization has focused on replacement of the head verb with a deverbal noun and resource development to support the task. |
| Approach: | They propose to use a textual entailment model to optimize the position and POS of nominal arguments by fine-tuning a model on the task. |
| Outcome: | The proposed model outperforms unsupervised approaches on the nominalization task and outperformed a state-of-the-art neural language model. |
Paraphrasing Compound Nominalizations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Nominalizations are difficult to interpret because of ambiguous semantic relations between deverbal noun and its arguments. |
| Approach: | They propose to generate clausal paraphrases for nominalizations by mapping arguments to verbs . they use a contextualized language model to re-rank nominalization candidates . |
| Outcome: | The proposed task is based on a pre-trained model to re-rank paraphrase candidates identified by a textual entailment model. |
A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Visual RAG is an alternative to traditional RAG, but it requires hundreds of patch tokens per document to retrieve and store information. |
| Approach: | They propose to aggregate documents into a single vector to avoid semantic loss . they find global texture dominance is the root cause of this loss - they say . |
| Outcome: | The proposed model shows that aggregation obscures semantic changes in financial documents . global texture dominance is the root cause, and the model scales are consistent across models and embeddings. |