Neural Headline Generation on Abstract Meaning Representation

By Sho Takase, Jun Suzuki, Naoaki Okazaki, Tsutomu Hirao, Masaaki Nagata. 2016

172 citations recorded by the source corpus.

Neural network-based encoder-decoder models are among recent attractive methodologies for tackling natural language generation tasks. This paper investigates the usefulness of structural syntactic and semantic information additionally incorporated in a baseline neural attention-based model. We encode results obtained from an abstract meaning representation (AMR) parser using a modiﬁed version of Tree-LSTM. Our proposed attention-based AMR encoder-decoder model improves head-line generation benchmarks compared with the baseline neural attention-based model.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Get To The Point: Summarization with Pointer-Generator Networks (2017, background): “Their approach, which is centered on the attention mechanism, has been augmented with recurrent decoders (Chopra et al., 2016), Abstract Meaning Representations (Takase et al., 2016), hierarchical networks (Nallapati et al., 2016), variational autoencoders (Miao and Blunsom, 2016), and direct optimi”
Neural Text Summarization: A Critical Evaluation (2019, methodology): “Gi-gaword (Graff and Cieri, 2003) is a set of articles and corresponding titles that was originally used for headline generation (Takase et al., 2016), but it has also been adapted to single-sentence summarization (Rush et al., 2015; Chopra et al., 2016).”
Structural Neural Encoders for AMR-to-text Generation (2019, methodology): “…over all nodes, as in traditional NMT (Bahdanau et al., 2015), we can however build node embeddings by extracting the hidden states of each node in the tree: The encoder is related to the TreeLSTM encoder of Takase et al. (2016), which however encodes labeled trees and does not use a top-down pass.”
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation (2017, methodology): “AMR has been used as an intermediate meaning representation for several applications including machine translation (MT) (Jones et al., 2012), summarization (Liu et al., 2015), sentence compression (Takase et al., 2016), and event extraction (Huang et al., 2016).”
Source-side Prediction for Neural Headline Generation (2017, methodology): “Takase et al. [2016] incorporated AMR Banarescu et al. [2013] the encoder to use the syntactic and semantic information of the source.”
Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization (2018, background): “Sequence-to-sequence (seq2seq) model that encodes a source sequence into a latent representation and outputs another sequence is the dominating framework for sentence summarization (Rush et al., 2015; Chopra et al., 2016; Takase et al., 2016; Zhou et al., 2017; Li et al., 2017b; Li et al., 2018).”
RNN-based Encoder-decoder Approach with Word Frequency Estimation (2017, methodology): “Finally, we evaluate the eﬀectiveness of our method on well-studied ABS benchmark data provided by Rush et al. Rush et al. [2015], and evaluated in Chopra et al. [2016], Nallapati et al. [2016b], Kikuchi et al. [2016], Takase et al. [2016], Ayana et al. [2016], Gulcehre et al. [2016].”