paper-with-me

Papers

Memory-Based Semantic Parsing

2021-09-07 · Parag Jain, Mirella Lapata

We present a memory-based model for context-dependent semantic parsing. Previous approaches focus on enabling the decoder to copy or modify the parse from the previous utterance, assuming there is a dependency between the current and previous parses. In this work, we propose to represent contextual information using an external memory. We learn a context memory controller that manages the memory by maintaining the cumulative meaning of sequential user utterances. We evaluate our approach on three semantic parsing benchmarks. Experimental results show that our model can better process context-dependent information and demonstrates improved performance without using task-specific decoders.

📄 PDF Abstract BibTeX arXiv:2110.07358

Code (1)

https://worksheets.codalab.org/worksheets/0xbd49d04e5a494a978642bbaf028b659b

Tasks

DecoderSemantic Parsing

Methods 이 논문이 사용한 방법론

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 $x$…
GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…
Dynamic Memory Network A Dynamic Memory Network is a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers. Questions…

Similar Papers 제목 키워드 기반

Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings

2020-10-10 · Findings of the Association for Computational Linguistics 2020 · Prafull Prakash, Saurabh Kumar Shashidhar, Wenlong Zhao, Subendhu Rongali 외

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants suc…

Semantic Parsing

Memory Based Video Scene Parsing

2021-09-01 · Zhenchao Jin, Dongdong Yu, Kai Su, Zehuan Yuan 외

Video scene parsing is a long-standing challenging task in computer vision, aiming to assign pre-defined semantic labels to pixels of all frames in a given video. Compared with image semantic segmentation, this task pays…

Scene ParsingSemantic Segmentation

Syntax Aware LSTM Model for Chinese Semantic Role Labeling

2017-04-03 · Feng Qian, Lei Sha, Baobao Chang, Lu-chen Liu 외

As for semantic role labeling (SRL) task, when it comes to utilizing parsing information, both traditional methods and recent recurrent neural network (RNN) based methods use the feature engineering way. In this paper, w…

Chinese Semantic Role LabelingDependency ParsingFeature EngineeringSemantic Role Labeling

HSGM: Hierarchical Segment-Graph Memory for Scalable Long-Text Semantics

2025-09-17 · Dong Liu, Yanxuan Yu arxiv

Semantic parsing of long documents remains challenging due to quadratic growth in pairwise composition and memory requirements. We introduce \textbf{Hierarchical Segment-Graph Memory (HSGM)}, a novel framework that decom…

Semantic Role LabelingEvent ExtractionSemantic ParsingAMR Parsing

Semantic Object Parsing with Graph LSTM

2016-03-23 · Xiaodan Liang, Xiaohui Shen, Jiashi Feng, Liang Lin 외

By taking the semantic object parsing task as an exemplar application scenario, we propose the Graph Long Short-Term Memory (Graph LSTM) network, which is the generalization of LSTM from sequential data or multi-dimensio…

ObjectSuperpixels