Papers by Prasad Tadepalli
Description-Based Zero-shot Fine-Grained Entity Typing (N19-1)
Copied to clipboard
| Challenge: | Existing systems consider a small set of coarse types, but fine-grained Entity Typing can be used for a variety of tasks. |
| Approach: | They propose a zero-shot entity typing approach that utilizes the type description available from Wikipedia to build a distributed semantic representation of the types. |
| Outcome: | The proposed method is able to recognize novel types without additional training on a public benchmark dataset. |
Saliency Learning: Teaching the Model Where to Pay Attention (N19-1)
Copied to clipboard
| Challenge: | Recent work on explanation and interpretation has introduced methods to provide insights toward the model’s behaviour and predictions, but they do not improve the model's reliability. |
| Approach: | They propose to provide explanation training and ensure alignment of model’s explanation with ground truth explanation to ensure the model makes correct predictions for the right reason. |
| Outcome: | The proposed method produces more reliable predictions while delivering better results compared to traditional models. |
Dependent Gated Reading for Cloze-Style Question Answering (C18-1)
Copied to clipboard
| Challenge: | Existing approaches do not fully exploit the interdependency between document and query. |
| Approach: | They propose a novel dependent gated reading bidirectional GRU network to efficiently model the relationship between the document and the query during encoding and decision making. |
| Outcome: | The proposed model performs well on machine comprehension benchmarks such as the Children’s Book Test and Who DiD What. |
On the Sub-layer Functionalities of Transformer Decoder (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation have focused on assessing the encoded representations or interpreting the multi-head self-attentions. |
| Approach: | They propose to use Transformer-based encoder-decoder architectures to analyze how information is propagated through each module of each decoder layer. |
| Outcome: | The proposed model can be dropped with minimal loss of performance on three translation datasets and can be used to train and inference faster. |
Relation Extraction with Explanation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies focus on improving relation extraction accuracy but little is known about their explanability. |
| Approach: | They propose to automatically generate "distractor" sentences to augment the bags and train the model to ignore the distractors. |
| Outcome: | The proposed model improves extraction accuracy while also explanability. |
Improving Multilingual Translation by Representation and Gradient Regularization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual Neural Machine Translation models often produce low quality translations, often failing to produce outputs in the right target language. |
| Approach: | They propose a joint approach to regularize NMT models at both representation-level and gradient-level to reduce off-target translation occurrences and improve zero-shot translation performance. |
| Outcome: | The proposed approach reduces off-target translation occurrences and improves zero-shot translation performance by +5.59 and +10.38 BLEU on WMT and OPUS datasets. |
Joint Neural Entity Disambiguation with Output Space Search (C18-1)
Copied to clipboard
| Challenge: | Existing models for entity disambiguation combine local contextual information and global evidences. |
| Approach: | They propose a limited discrepancy search model that combines local contextual information and global evidences to improve a local solution from a global view point. |
| Outcome: | The proposed model improves local and global solutions on CoNLL 2003 and TAC 2010 benchmarks. |
Event Detection with Neural Networks: A Rigorous Empirical Evaluation (D18-1)
Copied to clipboard
| Challenge: | Neural network models have been the most successful for event detection, but they ignore syntactic relationships in the text. |
| Approach: | They propose a GRU-based model that combines syntactic information along with temporal structure through an attention mechanism. |
| Outcome: | The proposed model is competitive with existing models on a ACE2005 dataset. |
Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference (D18-1)
Copied to clipboard
| Challenge: | In this paper, we examine the behavior of deep learning models in their intermediate layers . saliency determines what is critical for the final decision of a deep model . |
| Approach: | They propose to interpret the intermediate layers of deep models by visualizing the saliency of attention and LSTM gating signals. |
| Outcome: | The proposed methods reveal interesting insights and identify critical information contributing to the model decisions. |
Language-Informed Beam Search Decoding for Multilingual Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Beam search decoding is the de-facto method for decoding auto-regressive Neural Machine Translation (NMT) models, but decoding multilingual NMT models produces off-target translations . |
| Approach: | They propose a general decoding algorithm incorporating an off-the-shelf Language Identification (LiD) model into beam search decoding to reduce off-target translations. |
| Outcome: | The proposed language-informed beam search improves +1.1 BLEU and +0.9 BLUE on WMT and OPUS datasets and reduces off-target rates from 22.9% to 7.7% and 65.8% to 25.3% respectively. |