Papers by Lakshminarayanan Subramanian
Identifying Predictive Causal Factors from News Streams (D19-1)
Copied to clipboard
| Challenge: | Existing word embedding techniques are not suited to learn relationships between words in different documents and contexts. |
| Approach: | They propose a new framework to uncover the relationship between news events and real world phenomena by measuring how word occurrence influences future occurrence. |
| Outcome: | The proposed framework outperforms existing methods in stock price prediction errors for 12 months and 4 years. |
Learning Faithful Representations of Causal Graphs (2021.acl-long)
Copied to clipboard
| Challenge: | Existing text embeddings that predict direct causal links fail to capture other indirect causal links, leading to spurious correlations in downstream tasks. |
| Approach: | They define faithfulness property of contextual embeddings to capture geometric distance-based properties of directed acyclic causal graphs. |
| Outcome: | The embeddings are 31.3% more faithful to human validated graphs with 800K and 200K causal links and achieve better Precision-Recall AUC in a link prediction fine-tuning task. |