Graph-Based Decoding for Task Oriented Semantic Parsing

2021-09-09 · Findings (EMNLP) 2021 11 · Jeremy R. Cole, Nanjiang Jiang, Panupong Pasupat, Luheng He, Peter Shaw

The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic parsing as a dependency parsing task, applying graph-based decoding techniques developed for syntactic parsing. We compare various decoding techniques given the same pre-trained Transformer encoder on the TOP dataset, including settings where training data is limited or contains only partially-annotated examples. We find that our graph-based approach is competitive with sequence decoders on the standard setting, and offers significant improvements in data efficiency and settings where partially-annotated data is available.

📄 PDF Abstract BibTeX arXiv:2109.04587

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency Parsing Semantic Parsing

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Position-Wise Feed-Forward Layer 설명 없음

Adam 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis

2018-10-01 · CONLL 2018 10 · Yufei Chen, Sheng Huang, Fang Wang, Junjie Cao 외

We present experiments for cross-domain semantic dependency analysis with a neural Maximum Subgraph parser. Our parser targets 1-endpoint-crossing, pagenumber-2 graphs which are a good fit to semantic dependency graphs, …

Dependency Parsing Semantic Parsing

Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog

2019-11-01 · IJCNLP 2019 11 · Panupong Pasupat, Sonal Gupta, M, Karishma yam 외

We propose a semantic parser for parsing compositional utterances into Task Oriented Parse (TOP), a tree representation that has intents and slots as labels of nesting tree nodes. Our parser is span-based: it scores labe…

Decoder Semantic Parsing valid

Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing

2021-04-15 · Findings (EMNLP) 2021 11 · Akshat Shrivastava, Pierce Chuang, Arun Babu, Shrey Desai 외

An effective recipe for building seq2seq, non-autoregressive, task-oriented parsers to map utterances to semantic frames proceeds in three steps: encoding an utterance $x$, predicting a frame's length |y|, and decoding a…

Cross-Lingual Transfer Decoder Prediction Quantization+2

Retrieve-and-Fill for Scenario-based Task-Oriented Semantic Parsing

2022-02-02 · Akshat Shrivastava, Shrey Desai, Anchit Gupta, Ali Elkahky 외

Task-oriented semantic parsing models have achieved strong results in recent years, but unfortunately do not strike an appealing balance between model size, runtime latency, and cross-domain generalizability. We tackle t…

Retrieval Semantic Parsing

Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

2018-10-18 · EMNLP 2018 10 · Sonal Gupta, Rushin Shah, Mrinal Mohit, Anuj Kumar 외

Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots. Previous work on task oriented intent and slot-filling work has been restricted to one intent per quer…

Constituency Parsing Semantic Parsing slot-filling Slot Filling