paper-with-me

홈 › Papers

Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling

2017-04-23 · ACL 2017 7 · Kazuya Kawakami, Chris Dyer, Phil Blunsom

Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution in that they can create word types not attested in the training corpus, they do not capture the "bursty" distribution of such words. In this paper, we augment a hierarchical LSTM language model that generates sequences of word tokens character by character with a caching mechanism that learns to reuse previously generated words. To validate our model we construct a new open-vocabulary language modeling corpus (the Multilingual Wikipedia Corpus, MWC) from comparable Wikipedia articles in 7 typologically diverse languages and demonstrate the effectiveness of our model across this range of languages.

📄 PDF Abstract BibTeX arXiv:1704.06986

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Taboo Wordnet

2021-01-01 · EACL (GWC) 2021 1 · Francis Bond, Merrick Yeu Herng Choo

This paper describes the development of an online lexical resource to help detection systems regulate and curb the use of offensive words online. With the growing prevalence of social media platforms, many conversations …

Spell Once, Summon Anywhere: A Two-Level Open-Vocabulary Language Model

2018-04-23 · Sabrina J. Mielke, Jason Eisner

We show how the spellings of known words can help us deal with unknown words in open-vocabulary NLP tasks. The method we propose can be used to extend any closed-vocabulary generative model, but in this paper we specific…

Language ModelingLanguage ModellingSentenceVocal Bursts Valence Prediction

Context encoders as a simple but powerful extension of word2vec

2017-06-08 · WS 2017 8 · Franziska Horn

With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+1

Using Morphological Knowledge in Open-Vocabulary Neural Language Models

2018-06-01 · NAACL 2018 6 · Austin Matthews, Graham Neubig, Chris Dyer

Languages with productive morphology pose problems for language models that generate words from a fixed vocabulary. Although character-based models allow any possible word type to be generated, they are linguistically na…

Language ModelingLanguage ModellingMorphological Disambiguation

Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian

2024-08-07 · Amirhosein Chahe, Lifeng Zhou

This paper introduces a novel method for open-vocabulary 3D scene querying in autonomous driving by combining Language Embedded 3D Gaussians with Large Language Models (LLMs). We propose utilizing LLMs to generate both c…

Autonomous Drivingobject-detectionObject DetectionOpen Vocabulary Object Detection+2