Papers by Preksha Nema
A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization (N18-2)
Copied to clipboard
| Challenge: | Structured data summarization involves generation of summaries from structured input data. |
| Approach: | They propose a hierarchical attention-based encoder-decoder model which leverages the structure in addition to the content of the tables. |
| Outcome: | The proposed model improves on the weathergov dataset by 30% over the current state-of-the-art. |
Towards a Better Metric for Evaluating Question Generation Systems (D18-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics based on n-gram similarity do not correlate well with human judgments . large datasets for document Question Answering (QA) have enabled the development of end-to-end supervised models . |
| Approach: | They propose a scoring function to capture answerability of questions . they also integrate existing similarity metrics into the scoring function . |
| Outcome: | The proposed scoring function improves human judgments on question answerability . the proposed scoring functions are made publicly available . |
ReTAG: Reasoning Aware Table to Analytic Text Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Table to text models generate descriptive summaries that repeat information contained within a table in sentences. |
| Approach: | They propose a table-aware table-to-text model that uses vector-quantization to infuse different types of analytical reasoning into the output. |
| Outcome: | The proposed model achieves 2.2%, 2.9% improvement on PARENT metric over state-of-the-art models. |
T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Unavailability of parallel corpora for training text style transfer models is a challenge but common . a large corpus of parallel data is not available for text style transfers . |
| Approach: | They propose to use AMR as an intermediate style agnostic representation to train TST models. |
| Outcome: | The proposed model outperforms state-of-the-art models in the style agnostic task. |
Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization (N18-1)
Copied to clipboard
| Challenge: | a proposed model for generating natural language descriptions is too generic and does not exploit task specific characteristics. |
| Approach: | They propose a model which uses a fused bifocal attention mechanism to exploit micro and macro level information and a gated orthogonalization mechanism to ensure that a field is remembered for a few time steps and then forgotten. |
| Outcome: | The proposed model improves on a recently released dataset with two similar datasets for French and German. |
Towards Transparent and Explainable Attention Models (2020.acl-main)
Copied to clipboard
Akash Kumar Mohankumar, Preksha Nema, Sharan Narasimhan, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran
| Challenge: | Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model’s predictions. |
| Approach: | They propose to modify LSTM cells to ensure that the hidden representations learned at different time steps are diverse. |
| Outcome: | The proposed model can provide a faithful explanation if a higher attention weight implies a greater impact on the model’s prediction. |
Towards Interpreting BERT for Reading Comprehension Based QA (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained language models such as ELMO and XLNet have achieved state-of-the-art performance on various NLP tasks. |
| Approach: | They propose to define a layer’s role or functionality using Integrated Gradients and perform preliminary analysis across all layers. |
| Outcome: | The proposed model performs better than existing models on RCQA and ELMO, but it lacks the human-level performance needed to perform the task. |
Let’s Ask Again: Refine Network for Automatic Question Generation (D19-1)
Copied to clipboard
Preksha Nema, Akash Kumar Mohankumar, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran
| Challenge: | Existing AQG models produce incomplete questions which look like incomplete drafts with scope for refinement. |
| Approach: | They propose a method which mimics the human process of generating questions by first creating an initial draft and then refining it. |
| Outcome: | The proposed method outperforms state-of-the-art methods on three datasets and improves on fluency and answerability metrics. |
On the weak link between importance and prunability of attention heads (2020.emnlp-main)
Copied to clipboard
| Challenge: | a large fraction of attention heads can be randomly pruned with limited effect on accuracy, a new study finds . a second study finds no advantage in pruning attention heads identified to be important based on the location of a head . |
| Approach: | They examine the importance of pruning attention heads on a Transformer-based model . they find no advantage in pruning attention head positions on the BERT model based on location . |
| Outcome: | The results show that pruning strategies on Transformer and BERT models are not important based on location . the results suggest that interpretation of attention heads does not strongly inform pruning strategies. |