paper-with-me

Papers

Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue

2019-06-17 · ACL 2019 7 · Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White, Rajen Subba

Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset.

📄 PDF Abstract BibTeX arXiv:1906.07220

Code (1)

facebookresearch/TreeNLG 공식 구현 pytorch

Tasks

Sentence

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Self-Training for Compositional Neural NLG in Task-Oriented Dialogue

2021-08-01 · INLG (ACL) 2021 8 · Xintong Li, Symon Stevens-Guille, Aleksandre Maskharashvili, Michael White

Neural approaches to natural language generation in task-oriented dialogue have typically required large amounts of annotated training data to achieve satisfactory performance, especially when generating from composition…

Text Generation

A Tree-to-Sequence Model for Neural NLG in Task-Oriented Dialog

2019-10-01 · WS 2019 10 · Jinfeng Rao, Kartikeya Upasani, Anusha Balakrishnan, Michael White 외

Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Sequence-to-sequence models on flat meaning representations (MR) have been…

Sentence

AMR Dependency Parsing with a Typed Semantic Algebra

2018-05-29 · ACL 2018 7 · Jonas Groschwitz, Matthias Lindemann, Meaghan Fowlie, Mark Johnson 외

We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph. This allows us to use standard neural techniques f…

Dependency Parsing

Efficient Decoding of Compositional Structure in Holistic Representations

2023-05-26 · Denis Kleyko, Connor Bybee, Ping-Chen Huang, Christopher J. Kymn 외

We investigate the task of retrieving information from compositional distributed representations formed by Hyperdimensional Computing/Vector Symbolic Architectures and present novel techniques which achieve new informati…

compressed sensingRetrieval

Evaluating Neural Word Representations in Tensor-Based Compositional Settings

2014-08-26 · EMNLP 2014 10 · Dmitrijs Milajevs, Dimitri Kartsaklis, Mehrnoosh Sadrzadeh, Matthew Purver

We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement sev…

SentenceSentence SimilarityWord Embeddings