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 .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations