Papers by Manik Bhandari
Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation (N19-1)
Copied to clipboard
| Challenge: | Previous work focused on generating semantically similar paraphrases without considering diversity. |
| Approach: | They propose a method to obtain highly diverse paraphrases without compromising on paraphrasing quality by using monotone submodular function maximization. |
| Outcome: | The proposed method is effective on multiple tasks such as intent classification and paraphrase recognition. |
Re-evaluating Evaluation in Text Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Automated evaluation metrics are an essential part of the development of text-generation tasks such as summarization. |
| Approach: | They propose to use top-scoring system outputs to assess the reliability of automatic evaluation metrics for text summarization. |
| Outcome: | The proposed evaluation method is based on human judgments from 25 top-scoring neural summarization systems. |
Metrics also Disagree in the Low Scoring Range: Revisiting Summarization Evaluation Metrics (2020.coling-main)
Copied to clipboard
| Challenge: | In text summarization evaluation, evaluating the efficacy of automated metrics without human judgments has become popular. |
| Approach: | They revisit their experiments and find that automatic metrics disagree when ranking high-scoring summaries. |
| Outcome: | The proposed method is a human judgment-free method, but it is not a meta-evaluation strategy. |
Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks (P19-1)
Copied to clipboard
Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, Partha Talukdar
| Challenge: | Existing word embedding methods utilize sequential context of a word to learn its embeddment, but such methods result in an explosion of the vocabulary size. |
| Approach: | They propose a flexible Graph Convolution based method for learning word embeddings that utilizes the dependency context of a word without increasing the vocabulary size. |
| Outcome: | The proposed model outperforms existing methods on intrinsic and extrinsic tasks and provides an advantage when used with ELMo. |