Papers by Wee Sun Lee
Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents (2023.findings-eacl)
Copied to clipboard
Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, Wee Sun Lee
| Challenge: | Existing datasets do not cover documents with complex spatial structures and a lack of spatial information for document entity classification. |
| Approach: | They propose a new spatial bias in attention calculation based on the K-nearest-neighbor graph of document entities that limits entities’ attention to their local radius. |
| Outcome: | The proposed model outperforms baselines in most entity types and is highly parameter-efficient compared to existing methods. |
When Phrases Meet Probabilities: Enabling Open Relation Extraction with Cooperating Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing clustering-based open relation extraction methods use pre-trained language models . embeddings from language models are high-dimensional and anisotropic, so there is a gap . |
| Approach: | They propose a framework that makes two LLMs work collaboratively to achieve clustering. |
| Outcome: | The proposed framework outperforms existing methods by 1.4%3.13% on different datasets. |
Tell2Design: A Dataset for Language-Guided Floor Plan Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies have demonstrated impressive results in generating high-fidelity artistic images. |
| Approach: | They propose a Sequence-to-Sequence model that can serve as a strong baseline for future research. |
| Outcome: | The proposed model can be used as a baseline for future research and human evaluations are conducted on the generated samples and provided an analysis of human performance. |
Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification (D18-1)
Copied to clipboard
| Challenge: | Existing methods for cross-domain sentiment classification are difficult and costly . domain adaptation is difficult because data in source and target domains are drawn from different distributions. |
| Approach: | They propose a semi-supervised learning approach that minimizes the distance between source and target instances in embedded feature space. |
| Outcome: | The proposed approach can improve on baseline methods in various settings. |
Exploiting Document Knowledge for Aspect-level Sentiment Classification (P18-2)
Copied to clipboard
| Challenge: | Existing public aspect-level datasets for aspect-based sentiment classification are small . existing methods for aspect level sentiment classification require annotation of all opinion targets . |
| Approach: | They propose two approaches that transfer knowledge from document-level data to improve aspect-level sentiment classification. |
| Outcome: | The proposed methods improve aspect-level sentiment classification on 4 public datasets. |
Effective Attention Modeling for Aspect-Level Sentiment Classification (C18-1)
Copied to clipboard
| Challenge: | Aspect-level sentiment classification aims to determine sentiment polarity of review sentence towards opinion target . main challenge is to separate different opinion contexts for different targets . |
| Approach: | They propose a method that captures the semantic meaning of the opinion target and a model that incorporates syntactic information into the attention mechanism. |
| Outcome: | The proposed method captures the semantic meaning of the opinion target and incorporates syntactic information into the attention mechanism. |
An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis (P19-1)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a sentence. |
| Approach: | They propose an interactive multi-task learning network which can learn multiple tasks simultaneously . they use a shared set of latent variables to iteratively pass information between tasks . |
| Outcome: | The proposed method outperforms existing methods on three benchmark datasets. |