Papers by Phong Le
Improving Entity Linking by Modeling Latent Relations between Mentions (P18-1)
Copied to clipboard
| Challenge: | Entity linking systems often exploit relations between textual mentions to decide if the linking decisions are compatible. |
| Approach: | They treat relations as latent variables while optimizing the neural entity-linking model without supervision. |
| Outcome: | The proposed model outperforms its relation-agnostic version and significantly outperformed its relational version. |
DoLFIn: Distributions over Latent Features for Interpretability (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to interpret neural networks face a trade-off between a model's usefulness and its complexity. |
| Approach: | They propose a novel approach to achieve interpretability that avoids this trade-off by using probability as the central quantity instead of a fixed quantity. |
| Outcome: | The proposed approach outperforms the classical CNN and BiLSTM classifiers on the SST2 and AG-news datasets. |
Hierarchical Text Classification with LLM-Refined Taxonomies (2026.eacl-long)
Copied to clipboard
| Challenge: | Hierarchical text classification (HTC) relies on taxonomies that organize labels into structured hierarchies, but many real-world taxonomies introduce ambiguities, such as identical leaf names under similar parent nodes, which prevent language models from learning clear decision boundaries. |
| Approach: | They propose a framework that uses large language models to transform entire taxonomies through operations such as renaming, merging, splitting, and reordering to better match the semantics encoded by LMs. |
| Outcome: | The proposed framework outperforms human-curated taxonomies in three HTC benchmarks and shows that it aligns better with the model's actual confusion patterns. |
Boosting Entity Linking Performance by Leveraging Unlabeled Documents (P19-1)
Copied to clipboard
| Challenge: | a new approach to entity linking relies on unlabeled documents and Wikipedia . a supervised approach uses only natural information, such as unlabed documents . |
| Approach: | They propose a method which exploits only naturally occurring information . they construct a high recall list of candidate entities for each mention in an unlabeled document . |
| Outcome: | The proposed model outperforms fully-supervised state-of-the-art systems on standard test sets. |
Distant Learning for Entity Linking with Automatic Noise Detection (P19-1)
Copied to clipboard
| Challenge: | Accurate entity linkers have been produced for domains and languages where no or very limited amounts of labeled data are available. |
| Approach: | They propose to use annotated text to learn to link entities without labeling . they frame the task as a multi-instance learning problem and rely on surface matching to create initial noisy labels. |
| Outcome: | The proposed method outperforms the baseline surface matching model for a subset of entities. |
Revisiting Unsupervised Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). |
| Approach: | They compare unsupervised relation extraction methods to generative and discriminative approaches . they conclude that entity types provide a strong inductive bias for URE . |
| Outcome: | The proposed method outperforms generative and discriminative approaches on two popular datasets. |
The Emergence of Compositional Languages in Multi-entity Referential Games: from Image to Graph Representations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Language Emergence research uses jointly trained artificial agents to solve a task. |
| Approach: | They propose a multi-entity game in which targets include multiple entities that are spatially related. |
| Outcome: | The proposed multi-entity game shows that the emergent languages exhibit a considerable degree of compositionality, but not over all features. |