paper-with-me

Papers

Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks

2019-02-03 · Jenna Kanerva, Filip Ginter, Tapio Salakoski

In this paper we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 62 out of 76 treebanks reducing errors on average by 19% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license.

📄 PDF Abstract BibTeX arXiv:1902.00972

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationLEMMALemmatization

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Learning to Lemmatize in the Word Representation Space

2021-05-01 · NoDaLiDa 2021 5 · Jarkko Lagus, Arto Klami

Lemmatization is often used with morphologically rich languages to address issues caused by morphological complexity, performed by grammar-based lemmatizers. We propose an alternative for this, in form of a tool that per…

LemmatizationWord Embeddings

LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNs

2018-08-10 · Daniel Kondratyuk, Tomáš Gavenčiak, Milan Straka, Jan Hajič

We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with character-level and word-level embeddings. We demonstrat…

LemmatizationPart-Of-Speech TaggingTAG

LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNs

2018-10-01 · EMNLP 2018 10 · Daniel Kondratyuk, Tom{\'a}{\v{s}} Gaven{\v{c}}iak, Milan Straka, Jan Haji{\v{c}}

We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with character-level and word-level embeddings. We demonstrat…

LemmatizationMachine TranslationPart-Of-Speech TaggingSemantic Role Labeling+2

POS tagging, lemmatization and dependency parsing of West Frisian

2021-07-16 · LREC 2022 6 · Wilbert Heeringa, Gosse Bouma, Martha Hofman, Eduard Drenth 외

We present a lemmatizer/POS-tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependency version 2. POS tags were ass…

Dependency ParsingLEMMALemmatizationPOS+3

Universal Approximation with Softmax Attention

2025-04-22 · Jerry Yao-Chieh Hu, Hude Liu, Hong-Yu Chen, Weimin Wu 외

We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for continuous sequence-to-sequence functions on c…