Transformer-Based Neural Text Generation with Syntactic Guidance

• URL: http://arxiv.org/abs/2010.01737v1
• Date: Mon, 5 Oct 2020 01:33:58 GMT
• Title: Transformer-Based Neural Text Generation with Syntactic Guidance
• Authors: Yinghao Li (Georgia Institute of Technology), Rui Feng (Georgia Institute of Technology), Isaac Rehg (Georgia Institute of Technology), Chao Zhang (Georgia Institute of Technology)
• Abstract summary: We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Our method first expands a partial template parse tree to a full-fledged parse tree tailored for the input source text. Our experiments in the controlled paraphrasing task show that our method outperforms SOTA models both semantically and syntactically.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem but also falls short in modeling the tree structure of the syntactic guidance. We propose to leverage the parallelism of Transformer to better incorporate parse trees. Our method first expands a partial template constituency parse tree to a full-fledged parse tree tailored for the input source text, and then uses the expanded tree to guide text generation. The effectiveness of our model in this process hinges upon two new attention mechanisms: 1) a path attention mechanism that forces one node to attend to only other nodes located in its path in the syntax tree to better incorporate syntax guidance; 2) a multi-encoder attention mechanism that allows the decoder to dynamically attend to information from multiple encoders. Our experiments in the controlled paraphrasing task show that our method outperforms SOTA models both semantically and syntactically, improving the best baseline's BLEU score from 11.83 to 26.27.

Related papers

• Pushdown Layers: Encoding Recursive Structure in Transformer Language Models [86.75729087623259]
  Recursion is a prominent feature of human language, and fundamentally challenging for self-attention. This work introduces Pushdown Layers, a new self-attention layer. Transformers equipped with Pushdown Layers achieve dramatically better and 3-5x more sample-efficient syntactic generalization.
  arXiv  Detail & Related papers  (2023-10-29T17:27:18Z)
• Structured Dialogue Discourse Parsing [79.37200787463917]
  discourse parsing aims to uncover the internal structure of a multi-participant conversation. We propose a principled method that improves upon previous work from two perspectives: encoding and decoding. Experiments show that our method achieves new state-of-the-art, surpassing the previous model by 2.3 on STAC and 1.5 on Molweni.
  arXiv  Detail & Related papers  (2023-06-26T22:51:01Z)
• Spatial Attention and Syntax Rule Enhanced Tree Decoder for Offine Handwritten Mathematical Expression Recognition [12.656673677551778]
  We propose a novel model called Spatial Attention and Syntax Rule Enhanced Tree Decoder (SS-TD) Our model can effectively describe tree structure and increase the accuracy of output expression. Experiments show that SS-TD achieves better recognition performance than prior models on CROHME 14/16/19 datasets.
  arXiv  Detail & Related papers  (2023-03-13T12:59:53Z)
• A Tree-structured Transformer for Program Representation Learning [27.31416015946351]
  Long-term/global dependencies widely exist in programs, and most neural networks fail to capture these dependencies. In this paper, we propose Tree-Transformer, a novel tree-structured neural network which aims to overcome the above limitations. By combining bottom-up and top-down propagation, Tree-Transformer can learn both global contexts and meaningful node features.
  arXiv  Detail & Related papers  (2022-08-18T05:42:01Z)
• Integrating Dependency Tree Into Self-attention for Sentence Representation [9.676884071651205]
  We propose Dependency-Transformer, which applies a relation-attention mechanism that works in concert with the self-attention mechanism. By a score-based method, we successfully inject the syntax information without affecting Transformer's parallelizability. Our model outperforms or is comparable to the state-of-the-art methods on four tasks for sentence representation.
  arXiv  Detail & Related papers  (2022-03-11T13:44:41Z)
• Incorporating Constituent Syntax for Coreference Resolution [50.71868417008133]
  We propose a graph-based method to incorporate constituent syntactic structures. We also explore to utilise higher-order neighbourhood information to encode rich structures in constituent trees. Experiments on the English and Chinese portions of OntoNotes 5.0 benchmark show that our proposed model either beats a strong baseline or achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-02-22T07:40:42Z)
• Syntactic representation learning for neural network based TTS with syntactic parse tree traversal [49.05471750563229]
  We propose a syntactic representation learning method based on syntactic parse tree to automatically utilize the syntactic structure information. Experimental results demonstrate the effectiveness of our proposed approach. For sentences with multiple syntactic parse trees, prosodic differences can be clearly perceived from the synthesized speeches.
  arXiv  Detail & Related papers  (2020-12-13T05:52:07Z)
• Recursive Tree Grammar Autoencoders [3.791857415239352]
  We propose a novel autoencoder approach that encodes trees via a bottom-up grammar and decodes trees via a tree grammar. We show experimentally that our proposed method improves the autoencoding error, training time, and optimization score on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-03T17:37:25Z)
• Recursive Top-Down Production for Sentence Generation with Latent Trees [77.56794870399288]
  We model the production property of context-free grammars for natural and synthetic languages. We present a dynamic programming algorithm that marginalises over latent binary tree structures with $N$ leaves. We also present experimental results on German-English translation on the Multi30k dataset.
  arXiv  Detail & Related papers  (2020-10-09T17:47:16Z)
• Tree-structured Attention with Hierarchical Accumulation [103.47584968330325]
  "Hierarchical Accumulation" encodes parse tree structures into self-attention at constant time complexity. Our approach outperforms SOTA methods in four IWSLT translation tasks and the WMT'14 English-German translation task.
  arXiv  Detail & Related papers  (2020-02-19T08:17:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.