Text Summarization with Pretrained Encoders
- Yang Liu, Mirella Lapata
- Computer ScienceConference on Empirical Methods in Natural…
- 1 August 2019
This paper introduces a novel document-level encoder based on BERT which is able to express the semantics of a document and obtain representations for its sentences and proposes a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two.
Fine-tune BERT for Extractive Summarization
- Yang Liu
- Computer ScienceArXiv
- 25 March 2019
BERTSUM, a simple variant of BERT, for extractive summarization, is described, which is the state of the art on the CNN/Dailymail dataset, outperforming the previous best-performed system by 1.65 on ROUGE-L.
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
- Ming Zhong, Da Yin, Dragomir R. Radev
- Computer ScienceNorth American Chapter of the Association for…
- 23 March 2021
This work defines a new query-based multi-domain meeting summarization task, where models have to select and summarize relevant spans of meetings in response to a query, and introduces QMSum, a new benchmark for this task.
A Dependency-Based Neural Network for Relation Classification
- Yang Liu, Furu Wei, Sujian Li, Heng Ji, M. Zhou, Houfeng Wang
- Computer ScienceAnnual Meeting of the Association for…
- 16 July 2015
A new structure, termed augmented dependency path (ADP), is proposed, which is composed of the shortest dependency path between two entities and the subtrees attached to the shortest path, and a dependency-based neural networks (DepNN) are developed to exploit the semantic representation behind the ADP.
Hierarchical Transformers for Multi-Document Summarization
- Yang Liu, Mirella Lapata
- Computer ScienceAnnual Meeting of the Association for…
- 30 May 2019
A neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner is developed.
DialogSum: A Real-Life Scenario Dialogue Summarization Dataset
- Yulong Chen, Yang Liu, Liang Chen, Yue Zhang
- Computer ScienceFindings
- 2021
Experimental results show unique challenges in dialogue summarization, such as spoken terms, special discourse structures, coreferences and ellipsis, pragmatics and social common sense, which require specific representation learning technologies to better deal with.
Learning Structured Text Representations
- Yang Liu, Mirella Lapata
- Computer ScienceInternational Conference on Topology, Algebra and…
- 25 May 2017
A model that can encode a document while automatically inducing rich structural dependencies is proposed that embeds a differentiable non-projective parsing algorithm into a neural model and uses attention mechanisms to incorporate the structural biases.
Implicit Discourse Relation Classification via Multi-Task Neural Networks
- Yang Liu, Sujian Li, Xiaodong Zhang, Zhifang Sui
- Computer ScienceAAAI Conference on Artificial Intelligence
- 12 February 2016
This work designs related discourse classification tasks specific to a corpus, and proposes a novel Convolutional Neural Network embedded multi-task learning system to synthesize these tasks by learning both unique and shared representations for each task.
Recognizing Implicit Discourse Relations via Repeated Reading: Neural Networks with Multi-Level Attention
This work proposes the neural networks with multi-level attention (NNMA), combining the attention mechanism and external memories to gradually fix the attention on some specific words helpful to judging the discourse relations.
A Novel Neural Topic Model and Its Supervised Extension
- Ziqiang Cao, Sujian Li, Yang Liu, Wenjie Li, Heng Ji
- Computer ScienceAAAI Conference on Artificial Intelligence
- 25 January 2015
A novel neural topic model (NTM) is proposed where the representation of words and documents are efficiently and naturally combined into a uniform framework and is competitive in both topic discovery and classification/regression tasks.
...
...