scholarly journals When Low Resource NLP Meets Unsupervised Language Model: Meta-Pretraining then Meta-Learning for Few-Shot Text Classification (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13773-13774
Author(s):  
Shumin Deng ◽  
Ningyu Zhang ◽  
Zhanlin Sun ◽  
Jiaoyan Chen ◽  
Huajun Chen
Keyword(s):  
Text Classification ◽  
State Of The Art ◽  
Language Model ◽  
Language Models ◽  
Generic Model ◽  
Effective Strategy ◽  
Linguistic Features ◽  
Meta Learning ◽  
Promising Solution ◽  
Model Initialization

Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating implicit common linguistic features across tasks. This paper addresses such problems using meta-learning and unsupervised language models. Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks. We show that our approach is not only simple but also produces a state-of-the-art performance on a well-studied sentiment classification dataset. It can thus be further suggested that pretraining could be a promising solution for few-shot learning of many other NLP tasks. The code and the dataset to replicate the experiments are made available at https://github.com/zxlzr/FewShotNLP.

scholarly journals MSA Transformer

2021 ◽  
Author(s):  
Roshan Rao ◽  
Jason Liu ◽  
Robert Verkuil ◽  
Joshua Meier ◽  
John F. Canny ◽  
...  
Keyword(s):  
Structure Learning ◽  
State Of The Art ◽  
Language Model ◽  
Language Modeling ◽  
Language Models ◽  
Multiple Sequence ◽  
Wide Margin ◽  
Current State ◽  
Individual Sequences ◽  
And Function

AbstractUnsupervised protein language models trained across millions of diverse sequences learn structure and function of proteins. Protein language models studied to date have been trained to perform inference from individual sequences. The longstanding approach in computational biology has been to make inferences from a family of evolutionarily related sequences by fitting a model to each family independently. In this work we combine the two paradigms. We introduce a protein language model which takes as input a set of sequences in the form of a multiple sequence alignment. The model interleaves row and column attention across the input sequences and is trained with a variant of the masked language modeling objective across many protein families. The performance of the model surpasses current state-of-the-art unsupervised structure learning methods by a wide margin, with far greater parameter efficiency than prior state-of-the-art protein language models.

scholarly journals Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees

2016 ◽  
Vol 4 ◽  
pp. 477-490 ◽  
Author(s):  
Ehsan Shareghi ◽  
Matthias Petri ◽  
Gholamreza Haffari ◽  
Trevor Cohn
Keyword(s):  
Infinite Order ◽  
State Of The Art ◽  
Language Model ◽  
Language Models ◽  
Memory Usage ◽  
Suffix Trees ◽  
Construction Time ◽  
Modest Increase ◽  
Order Language ◽  
Language Modelling

Efficient methods for storing and querying are critical for scaling high-order m-gram language models to large corpora. We propose a language model based on compressed suffix trees, a representation that is highly compact and can be easily held in memory, while supporting queries needed in computing language model probabilities on-the-fly. We present several optimisations which improve query runtimes up to 2500×, despite only incurring a modest increase in construction time and memory usage. For large corpora and high Markov orders, our method is highly competitive with the state-of-the-art KenLM package. It imposes much lower memory requirements, often by orders of magnitude, and has runtimes that are either similar (for training) or comparable (for querying).

Spelling Check Combined Language Models and Knowledge Resources for Printer Drivers

2015 ◽  
Vol 764-765 ◽  
pp. 955-959
Author(s):  
Jui Feng Yeh ◽  
Cheng Hsien Lee ◽  
Yun Yun Lu ◽  
Guan Huei Wu ◽  
Yao Yi Wang
Keyword(s):  
Error Detection ◽  
Detection Rate ◽  
Language Model ◽  
Knowledge Bases ◽  
Language Models ◽  
Spelling Error ◽  
Linguistic Features ◽  
Knowledge Resources ◽  
Error Detection And Correction ◽  
New Feature

This paper proposed a spelling error detection and correction using the linguistic features and knowledge resource. The linguistic features mainly come from language model that describes the probability of a sentence. In practice, the formal document with typos is defective and fall short of the specifications, since typos and error hidden in printed document are frequent, rework will cause the waste of paper and ink. This paper proposed an approach that addresses the spelling errors and before printing. In this method, the linguistic features are used in this research to compare and increase a new feature additionally that is a function of Internet search based on knowledge bases. Combining these research manners, this paper expect to achieve the goals of confirming, improving the detection rate of typos, and reducing the waste of resources. Experimental results shows, the proposed method is practicable and efficient for users to detect the typos in the printed documents.

scholarly journals Text Classification in Law Area: a Systematic Review

2021 ◽  
Author(s):  
V. S. Martins ◽  
C. D. Silva
Keyword(s):  
Systematic Review ◽  
Text Classification ◽  
English Language ◽  
Search Strategy ◽  
Language Model ◽  
Brazilian Portuguese ◽  
Language Models ◽  
Automatic Text Classification ◽  
Research Questions ◽  
Automatic Text

Automatic Text Classification represents a great improvement in law area workflow, mainly in the migration of physical to electronic lawsuits. A systematic review of studies on text classification in law area from January 2017 up to February 2020 was conducted. The search strategy identified 20 studies, that were analyzed and compared. The review investigates from research questions: what are the state-of-art language models, its application of text classification in English and Brazilian Portuguese datasets from legal area, if there are available language models trained on Brazilian Portuguese, and datasets in Brazilian law area. It concludes that there are applications of automatic text classification in Brazil, although there is a gap on the use of language models when compared with English language dataset studies, also the importance of language model in domain pre-training to improve results, as well as there are two studies making available Brazilian Portuguese language models, and one introducing a dataset in Brazilian law area.

scholarly journals An Empirical Study of Korean Sentence Representation with Various Tokenizations

Electronics ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 845
Author(s):  
Danbi Cho ◽  
Hyunyoung Lee ◽  
Seungshik Kang
Keyword(s):  
Empirical Study ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Machine Translation ◽  
Text Classification ◽  
State Of The Art ◽  
Language Models ◽  
Vocabulary Size ◽  
Analysis Task ◽  
Natural Language Process

It is important how the token unit is defined in a sentence in natural language process tasks, such as text classification, machine translation, and generation. Many studies recently utilized the subword tokenization in language models such as BERT, KoBERT, and ALBERT. Although these language models achieved state-of-the-art results in various NLP tasks, it is not clear whether the subword tokenization is the best token unit for Korean sentence embedding. Thus, we carried out sentence embedding based on word, morpheme, subword, and submorpheme, respectively, on Korean sentiment analysis. We explored the two-sentence representation methods for sentence embedding: considering the order of tokens in a sentence and not considering the order. While inputting a sentence, which is decomposed by token unit, to the two-sentence representation methods, we construct the sentence embedding with various tokenizations to find the most effective token unit for Korean sentence embedding. In our work, we confirmed: the robustness of the subword unit for out-of-vocabulary (OOV) problems compared to other token units, the disadvantage of replacing whitespace with a particular symbol in the sentiment analysis task, and that the optimal vocabulary size is 16K in subword and submorpheme tokenization. We empirically noticed that the subword, which was tokenized by a vocabulary size of 16K without replacement of whitespace, was the most effective for sentence embedding on the Korean sentiment analysis task.

scholarly journals Active Learning for Effectively Fine-Tuning Transfer Learning to Downstream Task

2021 ◽  
Vol 12 (2) ◽  
pp. 1-24
Author(s):  
Md Abul Bashar ◽  
Richi Nayak
Keyword(s):  
Active Learning ◽  
Transfer Learning ◽  
Language Processing ◽  
State Of The Art ◽  
Language Model ◽  
Ensemble Classifier ◽  
Classification Performance ◽  
Fine Tuning ◽  
Linguistic Features ◽  
Better Than

Language model (LM) has become a common method of transfer learning in Natural Language Processing (NLP) tasks when working with small labeled datasets. An LM is pretrained using an easily available large unlabelled text corpus and is fine-tuned with the labelled data to apply to the target (i.e., downstream) task. As an LM is designed to capture the linguistic aspects of semantics, it can be biased to linguistic features. We argue that exposing an LM model during fine-tuning to instances that capture diverse semantic aspects (e.g., topical, linguistic, semantic relations) present in the dataset will improve its performance on the underlying task. We propose a Mixed Aspect Sampling (MAS) framework to sample instances that capture different semantic aspects of the dataset and use the ensemble classifier to improve the classification performance. Experimental results show that MAS performs better than random sampling as well as the state-of-the-art active learning models to abuse detection tasks where it is hard to collect the labelled data for building an accurate classifier.

Backward and trigger-based language models for statistical machine translation

2013 ◽  
Vol 21 (2) ◽  
pp. 201-226 ◽  
Author(s):  
DEYI XIONG ◽  
MIN ZHANG
Keyword(s):  
Mutual Information ◽  
Machine Translation ◽  
State Of The Art ◽  
Statistical Machine Translation ◽  
Language Model ◽  
Experimental Results ◽  
Language Models ◽  
Knowledge Sources ◽  
Long Distance ◽  
Translation Quality

AbstractThe language model is one of the most important knowledge sources for statistical machine translation. In this article, we present two extensions to standard n-gram language models in statistical machine translation: a backward language model that augments the conventional forward language model, and a mutual information trigger model which captures long-distance dependencies that go beyond the scope of standard n-gram language models. We introduce algorithms to integrate the two proposed models into two kinds of state-of-the-art phrase-based decoders. Our experimental results on Chinese/Spanish/Vietnamese-to-English show that both models are able to significantly improve translation quality in terms of BLEU and METEOR over a competitive baseline.

scholarly journals CloudLM: a Cloud-based Language Model for Machine Translation

2016 ◽  
Vol 105 (1) ◽  
pp. 51-61 ◽  
Author(s):  
Jorge Ferrández-Tordera ◽  
Sergio Ortiz-Rojas ◽  
Antonio Toral
Keyword(s):  
Big Data ◽  
Natural Language Processing ◽  
Machine Translation ◽  
Language Processing ◽  
State Of The Art ◽  
Language Model ◽  
Essential Element ◽  
Language Models ◽  
Language Modelling ◽  
Statistical Approaches

Abstract Language models (LMs) are an essential element in statistical approaches to natural language processing for tasks such as speech recognition and machine translation (MT). The advent of big data leads to the availability of massive amounts of data to build LMs, and in fact, for the most prominent languages, using current techniques and hardware, it is not feasible to train LMs with all the data available nowadays. At the same time, it has been shown that the more data is used for a LM the better the performance, e.g. for MT, without any indication yet of reaching a plateau. This paper presents CloudLM, an open-source cloud-based LM intended for MT, which allows to query distributed LMs. CloudLM relies on Apache Solr and provides the functionality of state-of-the-art language modelling (it builds upon KenLM), while allowing to query massive LMs (as the use of local memory is drastically reduced), at the expense of slower decoding speed.

Dependency-based n-gram models for general purpose sentence realisation

2010 ◽  
Vol 17 (4) ◽  
pp. 455-483 ◽  
Author(s):  
YUQING GUO ◽  
HAIFENG WANG ◽  
JOSEF VAN GENABITH
Keyword(s):  
State Of The Art ◽  
Structural Information ◽  
General Purpose ◽  
Language Models ◽  
Semantic Representations ◽  
Linguistic Features ◽  
Word Forms ◽  
Grammar Rules ◽  
Series Of Experiments ◽  
N Gram

AbstractThis paper presents a general-purpose, wide-coverage, probabilistic sentence generator based on dependency n-gram models. This is particularly interesting as many semantic or abstract syntactic input specifications for sentence realisation can be represented as labelled bi-lexical dependencies or typed predicate-argument structures. Our generation method captures the mapping between semantic representations and surface forms by linearising a set of dependencies directly, rather than via the application of grammar rules as in more traditional chart-style or unification-based generators. In contrast to conventional n-gram language models over surface word forms, we exploit structural information and various linguistic features inherent in the dependency representations to constrain the generation space and improve the generation quality. A series of experiments shows that dependency-based n-gram models generalise well to different languages (English and Chinese) and representations (LFG and CoNLL). Compared with state-of-the-art generation systems, our general-purpose sentence realiser is highly competitive with the added advantages of being simple, fast, robust and accurate.

scholarly journals Where do Clinical Language Models Break Down? A Critical Behavioural Exploration of the ClinicalBERT Deep Transformer Model

2021 ◽  
Vol 6 (1) ◽  
pp. 1-4
Author(s):  
Alexander MacLean ◽  
Alexander Wong
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
Language Model ◽  
Language Models ◽  
Clinical Knowledge ◽  
Language Understanding ◽  
Improved Performance ◽  
Transformer Model ◽  
Clinical Domain

The introduction of Bidirectional Encoder Representations from Transformers (BERT) was a major breakthrough for transfer learning in natural language processing, enabling state-of-the-art performance across a large variety of complex language understanding tasks. In the realm of clinical language modeling, the advent of BERT led to the creation of ClinicalBERT, a state-of-the-art deep transformer model pretrained on a wealth of patient clinical notes to facilitate for downstream predictive tasks in the clinical domain. While ClinicalBERT has been widely leveraged by the research community as the foundation for building clinical domain-specific predictive models given its overall improved performance in the Medical Natural Language inference (MedNLI) challenge compared to the seminal BERT model, the fine-grained behaviour and intricacies of this popular clinical language model has not been well-studied. Without this deeper understanding, it is very challenging to understand where ClinicalBERT does well given its additional exposure to clinical knowledge, where it doesn't, and where it can be improved in a meaningful manner. Motivated to garner a deeper understanding, this study presents a critical behaviour exploration of the ClinicalBERT deep transformer model using MedNLI challenge dataset to better understanding the following intricacies: 1) decision-making similarities between ClinicalBERT and BERT (leverage a new metric we introduce called Model Alignment), 2) where ClinicalBERT holds advantages over BERT given its clinical knowledge exposure, and 3) where ClinicalBERT struggles when compared to BERT. The insights gained about the behaviour of ClinicalBERT will help guide towards new directions for designing and training clinical language models in a way that not only addresses the remaining gaps and facilitates for further improvements in clinical language understanding performance, but also highlights the limitation and boundaries of use for such models.

Sign in / Sign up

Export Citation Format

Share Document