paper-with-me

Papers

Deconstructing Supertagging into Multi-Task Sequence Prediction

2019-11-01 · CONLL 2019 11 · Zhenqi Zhu, Anoop Sarkar

Supertagging is a sequence prediction task where each word is assigned a piece of complex syntactic structure called a supertag. We provide a novel approach to multi-task learning for Tree Adjoining Grammar (TAG) supertagging by deconstructing these complex supertags in order to define a set of related but auxiliary sequence prediction tasks. Our multi-task prediction framework is trained over the exactly same training data used to train the original supertagger where each auxiliary task provides an alternative view on the original prediction task. Our experimental results show that our multi-task approach significantly improves TAG supertagging with a new state-of-the-art accuracy score of 91.39{\%} on the Penn Treebank supertagging dataset.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task LearningPredictionTAG

Similar Papers 제목 키워드 기반

Supertagging with CCG primitives

2020-07-01 · WS 2020 7 · Aditya Bhargava, Gerald Penn

In CCG and other highly lexicalized grammars, supertagging a sentence{'}s words with their lexical categories is a critical step for efficient parsing. Because of the high degree of lexicalization in these grammars, the …

CCG SupertaggingSentence

Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks

2020-10-13 · EMNLP 2020 11 · Yuanhe Tian, Yan Song, Fei Xia

Supertagging is conventionally regarded as an important task for combinatory categorial grammar (CCG) parsing, where effective modeling of contextual information is highly important to this task. However, existing studie…

CCG Supertagging

A Dynamic Window Neural Network for CCG Supertagging

2016-10-10 · Huijia Wu, Jiajun Zhang, Cheng-qing Zong

Combinatory Category Grammar (CCG) supertagging is a task to assign lexical categories to each word in a sentence. Almost all previous methods use fixed context window sizes as input features. However, it is obvious that…

CCG SupertaggingSentenceWord Embeddings

German and French Neural Supertagging Experiments for LTAG Parsing

2018-07-01 · ACL 2018 7 · Tatiana Bladier, Andreas van Cranenburgh, Younes Samih, Laura Kallmeyer

We present ongoing work on data-driven parsing of German and French with Lexicalized Tree Adjoining Grammars. We use a supertagging approach combined with deep learning. We show the challenges of extracting LTAG supertag…

Dependency ParsingSemantic ParsingSemantic Role Labeling

Supertagging-based Parsing with Linear Context-free Rewriting Systems

2020-10-20 · NAACL 2021 4 · Richard Mörbitz, Thomas Ruprecht

We present the first supertagging-based parser for LCFRS. It utilizes neural classifiers and tremendously outperforms previous LCFRS-based parsers in both accuracy and parsing speed. Moreover, our results keep up with th…