Extract, Transform and Filling: A Pipeline Model for Question Paraphrasing based on Template (D19-55)
Copied to clipboard
| Challenge: | Recent approaches for paraphrasing generate unpredictable results . |
| Approach: | They propose a question paraphrasing pipeline model based on templates that identifies template and retrieves candidate templates and fills them with original topic words. |
| Outcome: | The proposed model outperforms the seq2seq model on two datasets and is more promising when the training sample is small. |
Similar Papers
Expanding, Retrieving and Infilling: Diversifying Cross-Domain Question Generation with Flexible Templates (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing models for question generation suffer from lack of diversity and bad sentence structures. |
| Approach: | They propose a framework that integrates flexible templates with a neural-based model to generate diverse expressions of questions with sentence structure guidance. |
| Outcome: | The proposed framework generates diverse expressions of questions with sentence structure guidance while maintaining high quality and consistency under automatic evaluation and human evaluation. |
Template Filling with Generative Transformers (2021.naacl-main)
Copied to clipboard
| Challenge: | Template filling tasks are usually tackled by a pipeline of two separate systems, one for role-filler extraction and another for template/event recognition. |
| Approach: | They propose a framework that naturally models the dependence between entities within a single event and across multiple events described in a document. |
| Outcome: | The proposed framework outperforms pipeline-based approaches and other neural baselines that do not model between-event dependencies on documents containing multiple events. |
Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation (N18-1)
Copied to clipboard
| Challenge: | Existing models tend to memorize words instead of learning meaning of words . existing models tend not to model semantic information, resulting in incorrect sentences . |
| Approach: | They propose a novel model that generates words by querying distributed word representations . they evaluate model on two paraphrase-oriented tasks, namely text simplification and short abstractive summarization . |
| Outcome: | The proposed model outperforms the baseline model on two paraphrase-oriented tasks . it achieves state-of-the-art performance on these benchmark datasets . |
Unsupervised Paraphrasing with Pretrained Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Paraphrase generation has benefited from recent advances in the design of training objectives and model architectures, but previous studies focused on supervised methods that require a large amount of labeled data that is costly to collect. |
| Approach: | They propose a transfer learning approach that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. |
| Outcome: | The proposed model performs state-of-the-art on the Quora Question Pair and ParaNMT datasets and is robust to domain shift between the two datasets. |
Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to answer reading comprehension tasks are inefficient since the input is re-encoded within each module. |
| Approach: | They propose a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer. |
| Outcome: | The proposed model outperforms the baseline model and achieves state-of-the-art results on two versions of TriviaQA and two variants of SQuAD. |
An End-to-End Generative Architecture for Paraphrase Generation (D19-1)
Copied to clipboard
| Challenge: | Existing methods for generating paraphrases with linguistic knowledge are often domain specific and hard to scale, or yield inferior results. |
| Approach: | They propose an end-to-end conditional generative architecture for generating paraphrases via adversarial training which does not depend on extra linguistic information. |
| Outcome: | The proposed method outperforms existing models on automatic metrics and human evaluations on four public datasets. |
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have investigated the multi-head self-attention mechanism of transformers. |
| Approach: | They propose to use a human-in-the-loop pipeline to discover task-specific attention patterns and inject them into transformer models to improve their accuracy. |
| Outcome: | The proposed methods improve the performance of transformer models by incorporating predefined patterns into their attention matrices. |
Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to extract implicit knowledge from pretrained models are still unclear. |
| Approach: | They propose to use a template-based approach to extract implicit knowledge for commonsense reasoning on multiple-choice questions. |
| Outcome: | The proposed template can be extended to other MC tasks with contexts such as supporting facts in open-book question answering settings. |
ConRPG: Paraphrase Generation using Contexts as Regularizer (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for paraphrase generation lack reliable supervision signals. |
| Approach: | They propose an unsupervised paradigm for paraphrase generation based on contextual language models, candidate filtering and paraphrase model training based upon the selected candidates. |
| Outcome: | The proposed paradigm outperforms existing paraphrase generation methods in supervised and unsupervised setups. |
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing approaches to extracting answer from text are expensive to train and train. |
| Approach: | They investigate how much models benefit from retrieving text passages . they obtain state-of-the-art results on the Natural Questions and TriviaQA open benchmarks ." |
| Outcome: | The proposed model performs better when retrieving more passages than previously thought . |