Papers by William L. Hamilton
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text (D19-1)
Copied to clipboard
| Challenge: | Existing datasets for reading comprehension tasks have been used to test the generalization of natural language understanding systems. |
| Approach: | They propose a diagnostic benchmark suite to clarify key issues related to the robustness and systematicity of NLU systems. |
| Outcome: | The proposed benchmark suite clarifies key issues related to the robustness and systematicity of NLU systems. |
Distilling Structured Knowledge for Text-Based Relational Reasoning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing text-based relational reasoning models lack a symbolic representation of text . performance gap between NLP models and structured models remains . |
| Approach: | They first pre-train a GNN on a reasoning task using structured inputs and then incorporate its knowledge into an NLP model. |
| Outcome: | The proposed model improves on two state-of-the-art NLP models on 13 different inductive reasoning datasets from the CLUTRR benchmark. |
TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for static knowledge graphs do not explicitly leverage multi-hop structural information and temporal facts from recent time steps to enhance their predictions. |
| Approach: | They propose a framework to leverage time-dependent temporal information to infer missing facts in temporal knowledge graphs. |
| Outcome: | The proposed framework achieves 10.7% improvement in Hits@10 across three standard benchmarks. |
Structure Aware Negative Sampling in Knowledge Graphs (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for learning low-dimensional representations of entities and relations in knowledge graphs employing corruption distributions that generate hard negative samples. |
| Approach: | They propose a structure-aware negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node’s k-hop neighborhood. |
| Outcome: | The proposed method finds semantically meaningful negatives and is competitive with SOTA approaches while requires no additional parameters nor difficult adversarial optimization. |
Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for few-shot link prediction are limited by having only a few examples of a relation . low-frequency relations are abundant in knowledge graphs, but link prediction for these relations is important . |
| Approach: | They perform few-shot link prediction for a set of new relations unseen during training, given only a few examples of each relation at test time. |
| Outcome: | The proposed model is based on a simple, zero-shot baseline that ignores relation-specific information and achieves surprisingly strong performance. |
Learning an Unreferenced Metric for Online Dialogue Evaluation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing tools for dialogue evaluation do not generalize to unseen datasets and/or need a human-generated reference response during inference. |
| Approach: | They propose an unreferenced automated dialogue evaluation metric that uses large pre-trained language models to extract latent representations of utterances and leverages the temporal transitions that exist between them. |
| Outcome: | The proposed model achieves higher correlation with human annotations in an online setting, while not requiring true responses for comparison during inference. |
Do Syntax Trees Help Pre-trained Transformers Extract Information? (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. |
| Approach: | They propose to incorporate dependency tree information into pre-trained transformers for three tasks . they propose a late fusion approach and a joint fusion technique to infuses syntax structure into attention layers. |
| Outcome: | The proposed models obtain state-of-the-art results on SRL and relation extraction tasks. |
End-to-End Training of Neural Retrievers for Open-Domain Question Answering (2021.acl-long)
Copied to clipboard
Devendra Sachan, Mostofa Patwary, Mohammad Shoeybi, Neel Kant, Wei Ping, William L. Hamilton, Bryan Catanzaro
| Challenge: | Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised methods. |
| Approach: | They propose an approach of unsupervised pre-training with the Inverse Cloze Task and masked salient spans followed by supervised finetuning using question-context pairs. |
| Outcome: | The proposed approach outperforms models like REALM and RAG in retrieval accuracy and answer extraction. |