Papers by Chris Hokamp
GLiREL - Generalist Model for Zero-Shot Relation Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot named entity recognition rely on distant supervision and training data for unseen labels. |
| Approach: | They propose an efficient architecture and training paradigm for zero-shot relation classification . they use a protocol to generate multiple relation labels in a single forward pass . |
| Outcome: | The proposed architecture and training paradigm achieve state-of-the-art results on the zero-shot relation classification task. |
Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Recent unsupervised sentence compression approaches use custom objectives to guide discrete search, but guided search is expensive at inference time. |
| Approach: | They propose to use reinforcement learning to train effective sentence compression models that are also fast when generating predictions. |
| Outcome: | The proposed model outperforms other unsupervised models while being faster at inference time. |
A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal (2020.acl-main)
Copied to clipboard
| Challenge: | Multidocument summarization (MDS) aims to compress large document collections into short summaries. |
| Approach: | They propose a large-scale multidocument summarization dataset that is large both in total number of document clusters and in the size of individual clusters. |
| Outcome: | The proposed dataset is large both in the total number of document clusters and in the size of individual clusters. |