English
Related papers

Related papers: Fast Rule-Based Decoding: Revisiting Syntactic Rul…

200 papers

We propose a novel algorithm that improves on the previous neural span-based CKY decoder for constituency parsing. In contrast to the traditional span-based decoding, where spans are combined only based on the sum of their scores, we…

Computation and Language · Computer Science 2022-11-02 Zhicheng Wang , Tianyu Shi , Liyin Xiao , Cong Liu

Non-local features have been exploited by syntactic parsers for capturing dependencies between sub output structures. Such features have been a key to the success of state-of-the-art statistical parsers. With the rise of deep learning,…

Computation and Language · Computer Science 2018-08-29 Zhiyang Teng , Yue Zhang

We propose a novel constituency parsing model that casts the parsing problem into a series of pointing tasks. Specifically, our model estimates the likelihood of a span being a legitimate tree constituent via the pointing score…

Computation and Language · Computer Science 2020-06-25 Thanh-Tung Nguyen , Xuan-Phi Nguyen , Shafiq Joty , Xiaoli Li

We propose two fast neural combinatory models for constituency parsing: binary and multi-branching. Our models decompose the bottom-up parsing process into 1) classification of tags, labels, and binary orientations or chunks and 2) vector…

Computation and Language · Computer Science 2021-06-15 Zhousi Chen , Longtu Zhang , Aizhan Imankulova , Mamoru Komachi

We investigate the ability of transformer models to approximate the CKY algorithm, using them to directly predict a sentence's parse and thus avoid the CKY algorithm's cubic dependence on sentence length. We find that on standard…

Computation and Language · Computer Science 2023-11-07 Ghazal Khalighinejad , Ollie Liu , Sam Wiseman

Estimating probability distribution is one of the core issues in the NLP field. However, in both deep learning (DL) and pre-DL eras, unlike the vast applications of linear-chain CRF in sequence labeling tasks, very few works have applied…

Computation and Language · Computer Science 2020-08-11 Yu Zhang , Houquan Zhou , Zhenghua Li

This paper describes a parsing model that combines the exact dynamic programming of CRF parsing with the rich nonlinear featurization of neural net approaches. Our model is structurally a CRF that factors over anchored rule productions, but…

Computation and Language · Computer Science 2015-07-15 Greg Durrett , Dan Klein

A number of differences have emerged between modern and classic approaches to constituency parsing in recent years, with structural components like grammars and feature-rich lexicons becoming less central while recurrent neural network…

Computation and Language · Computer Science 2018-04-24 David Gaddy , Mitchell Stern , Dan Klein

Thanks to the strong representation power of neural encoders, neural chart-based parsers have achieved highly competitive performance by using local features. Recently, it has been shown that non-local features in CRF structures lead to…

Computation and Language · Computer Science 2022-03-29 Leyang Cui , Sen Yang , Yue Zhang

In this work, we propose a novel constituency parsing scheme. The model predicts a vector of real-valued scalars, named syntactic distances, for each split position in the input sentence. The syntactic distances specify the order in which…

Computation and Language · Computer Science 2018-06-13 Yikang Shen , Zhouhan Lin , Athul Paul Jacob , Alessandro Sordoni , Aaron Courville , Yoshua Bengio

We introduce a method to reduce constituent parsing to sequence labeling. For each word w_t, it generates a label that encodes: (1) the number of ancestors in the tree that the words w_t and w_{t+1} have in common, and (2) the nonterminal…

Computation and Language · Computer Science 2019-09-18 Carlos Gómez-Rodríguez , David Vilares

Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications…

While deep learning approaches to information extraction have had many successes, they can be difficult to augment or maintain as needs shift. Rule-based methods, on the other hand, can be more easily modified. However, crafting rules…

Computation and Language · Computer Science 2022-02-02 Robert Vacareanu , Marco A. Valenzuela-Escarcega , George C. G. Barbosa , Rebecca Sharp , Mihai Surdeanu

Recently, unsupervised parsing of syntactic trees has gained considerable attention. A prototypical approach to such unsupervised parsing employs reinforcement learning and auto-encoders. However, no mechanism ensures that the learnt model…

Computation and Language · Computer Science 2021-05-24 Atul Sahay , Anshul Nasery , Ayush Maheshwari , Ganesh Ramakrishnan , Rishabh Iyer

In this work we propose an accelerated stochastic learning system for very large-scale applications. Acceleration is achieved by mapping the training algorithm onto massively parallel processors: we demonstrate a parallel, asynchronous GPU…

Machine Learning · Computer Science 2017-02-24 Thomas Parnell , Celestine Dünner , Kubilay Atasu , Manolis Sifalakis , Haris Pozidis

Attention encoder-decoder model architecture is the backbone of several recent top performing foundation speech models: Whisper, Seamless, OWSM, and Canary-1B. However, the reported data and compute requirements for their training are…

This research introduces a new parsing approach, based on earlier syntactic work on context free grammar (CFG) and generalized phrase structure grammar (GPSG). The approach comprises both a new parsing algorithm and a set of syntactic rules…

Computation and Language · Computer Science 2026-02-17 Ghaly Hussein

High-performance learned image compression codecs require flexible probability models to fit latent representations. Gaussian Mixture Models (GMMs) were proposed to satisfy this demand, but suffer from a significant runtime performance…

Image and Video Processing · Electrical Eng. & Systems 2025-09-24 Shimon Murai , Fangzheng Lin , Jiro Katto

Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by…

Computation and Language · Computer Science 2016-10-04 Gurvan L'Hostis , David Grangier , Michael Auli

This paper proposes a polar code construction scheme that reduces constituent-code supplemented decoding latency. Constituent codes are the sub-codewords with specific patterns. They are used to accelerate the successive cancellation…

Information Theory · Computer Science 2017-09-22 Tiben Che , Gwan Choi
‹ Prev 1 2 3 10 Next ›