paper-with-me

Papers

Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

2017-04-30 · Ganbin Zhou, Ping Luo, Rongyu Cao, Yijun Xiao, Fen Lin, Bo Chen, Qing He

Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible responses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of sentence generation for high-quality conversation generation. Specifically, we use a dependency parser to transform each response sentence into a dependency tree and construct a training corpus of sentence-tree pairs. A tree-structured decoder is developed to learn the mapping from a sentence to its tree, where different types of hidden states are used to depict the local dependencies from an internal tree node to its children. For training acceleration, we propose a tree canonicalization method, which transforms trees into equivalent ternary trees. Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output. Experimental results demonstrate that the proposed X2Tree framework outperforms baseline methods over 11.15% increase of acceptance ratio.

📄 PDF Abstract BibTeX arXiv:1705.00321

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderSentence

Similar Papers 제목 키워드 기반

Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing

2018-09-06 · EMNLP 2018 10 · Jetic Gū, Hassan S. Shavarani, Anoop Sarkar

The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to …

Constituency ParsingDecoderDependency ParsingMachine Translation+4

Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval

2021-08-05 · Xuri Ge, Fuhai Chen, Joemon M. Jose, Zhilong Ji 외

The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-…

cross-modal alignmentRetrievalSemantic correspondenceSentence+1

The Lifted Matrix-Space Model for Semantic Composition

2017-11-09 · CONLL 2018 10 · WooJin Chung, Sheng-Fu Wang, Samuel R. Bowman

Tree-structured neural network architectures for sentence encoding draw inspiration from the approach to semantic composition generally seen in formal linguistics, and have shown empirical improvements over comparable se…

Semantic CompositionSentenceWord Embeddings

Incremental Tree Substitution Grammar for Parsing and Sentence Prediction

2013-01-01 · TACL 2013 1 · Federico Sangati, Frank Keller

In this paper, we present the first incremental parser for Tree Substitution Grammar (TSG). A TSG allows arbitrarily large syntactic fragments to be combined into complete trees; we show how constraints (including lexica…

Language ModelingLanguage ModellingMachine TranslationPrediction+3

Do latent tree learning models identify meaningful structure in sentences?

2017-09-04 · TACL 2018 1 · Adina Williams, Andrew Drozdov, Samuel R. Bowman

Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to ground-t…

SentenceSentence Classification