Papers by Sagnik Ray Choudhury
Explaining Interactions Between Text Spans (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing highlight-based explanations focus on identifying individual important features or interactions only between adjacent tokens or tuples of tokens. |
| Approach: | They propose a multi-annotator dataset of human span interaction explanations for NLU and FC. |
| Outcome: | The proposed method compares human reasoning processes to those of a fine-tuned large language model. |
Can Edge Probing Tests Reveal Linguistic Knowledge in QA Models? (2022.coling-1)
Copied to clipboard
| Challenge: | grammatical knowledge is encoded in large pre-trained language models (LMs) this is done through supervised classification tasks to predict the grammamatical properties of a span using only the token representations coming from the LM encoder. |
| Approach: | They propose to use a supervised 'edge probing' task to detect grammatical knowledge in large pre-trained language models (LMs) this is done by encoding grammamatical properties using only token representations coming from the LM encoder. |
| Outcome: | The proposed model performs well when fine-tuned or in adversarial situations where the model is forced to learn wrong correlations. |
Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Named entity recognition models use a conditional random field as the final layer . current work eschews prior knowledge of how the span encoding scheme works . |
| Approach: | They propose to constrain the output to suppress illegal transitions to train a tagger with a cross-entropy loss twice as fast as a CRF. |
| Outcome: | The proposed model trains twice as fast as a CRF with statistically insignificant differences in F1 . the proposed model is open source and can be used in PyTorch and TensorFlow. |
Intent Features for Rich Natural Language Understanding (2021.naacl-industry)
Copied to clipboard
| Challenge: | generic dialog systems, or chatbots, are increasingly popular, but most industrial dialog systems are built for specific clients and use cases. |
| Approach: | They propose a new neural network architecture that allows for domain and topic agnostic properties of intents that can be learnt from syntactic cues only. |
| Outcome: | The proposed model improves on baselines for identifying intent features in a deployed, multi-intent natural language understanding module. |
Machine Reading, Fast and Slow: When Do Models “Understand” Language? (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models of reading comprehension score highly on NLU benchmarks, but they are often 'read fast', i.e. rely on shallow patterns. |
| Approach: | They propose a definition for the reasoning steps expected from a system that would be 'reading slowly' they compare that behavior with five models of the BERT family of various sizes, observed through saliency scores and counterfactual explanations. |
| Outcome: | The proposed model is compared with five models of the BERT family of various sizes, and compared using saliency scores and counterfactual explanations. |