Өзін-өзі оқыту

This paper investigates booststrapping part-of- speech taggers using co-training, in which two taggers are iteratively re-trained on each other’s output. Since the output of the taggers is noisy, there is …...

This paper investigates the application of co- training and self-training to word sense disam- biguation. Optimal and empirical parameter se- lection methods for co-training and self-training are investigated, with various …...

Creating large amounts of annotated data to train statistical PCFG parsers is expensive, and the performance of such parsers declines when training and test data are taken from different domains. …...

We study self-training with products of latent variable grammars in this paper. We show that increasing the quality of the automatically parsed data used for self-training gives higher accuracy self-trained …...

Argumentative Zoning (AZ) – analysis of the argumentative structure of a scientific paper – has proved useful for a number of informa- tion access tasks. Current approaches to AZ rely …...

Current approaches for semantic parsing take a supervised approach requiring a consider- able amount of training data which is expen- sive and difficult to obtain. This supervision bottleneck is one …...

We investigate the use of Semi-Supervised Learning (SSL) in opinion detection both in sparse data situations and for domain adapta- tion. We show that co-training reaches the best results in …...

We introduce and describe ongoing work in our Indonesian dependency treebank. We de- scribed characteristics of the source data as well as describe our annotation guidelines for creating the dependency …...

This paper proposes a simple yet effective framework for semi-supervised dependency parsing at entire tree level, referred to as ambiguity-aware ensemble training. Instead of only using 1- best parse trees …...

In this paper, we propose an automatic identification model, capable of extract- ing expressions of locations (EoLs) within Twitter messages. Moreover, we partici- pated in the competition of ALTA Shared …...

AbstractThe work presented in this article takes place in the field of opinion mining and aims more particularly at finding the polarity of a text by relying on machine learning …...

AbstractIn this study, we tackle the problem of self-training a feature-rich discriminative constituency parser. We approach the self-training problem with the assumption that while the full sentence parse tree produced …...

We present novel experiments in model- ing the rise and fall of story characteristics within narrative, leading up to the Most Reportable Event (MRE), the compelling event that is the …...

Model combination techniques have con- sistently shown state-of-the-art perfor- mance across multiple tasks, including syntactic parsing. However, they dramat- ically increase runtime and can be diffi- cult to employ in …...

We present a self-training approach to unsu- pervised dependency parsing that reuses exist- ing supervised and unsupervised parsing algo- rithms. Our approach, called ‘iterated rerank- ing’ (IR), starts with dependency …...

We seek to address the lack of labeled data (and high cost of annotation) for textual entailment in some domains. To that end, we first create (for experimental purposes) an …...

AbstractThe ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these …...

AbstractBuilding curious machines that can answer as well as ask questions is an important challenge for AI. The two tasks of question answering and question generation are usually tackled separately …...

AbstractSelf-training is a semi-supervised learning approach for utilizing unlabeled data to create better learners. The efficacy of self-training algorithms depends on their data sampling techniques. The majority of current sampling …...

AbstractLack of labelled data in the target domain for training is a common problem in domain adaptation. To overcome this problem, we propose a novel unsupervised domain adaptation method that …...

AbstractThis paper presents the winning system for the propaganda Technique Classification (TC) task and the second-placed system for the propaganda Span Identification (SI) task. The purpose of TC task was …...

AbstractRecent advances of multilingual word representations weaken the input divergences across languages, making cross-lingual transfer similar to the monolingual cross-domain and semi-supervised settings. Thus self-training, which is effective for these …...

AbstractAdapting pre-trained language models (PrLMs) (e.g., BERT) to new domains has gained much attention recently. Instead of fine-tuning PrLMs as done in most previous work, we investigate how to adapt …...

AbstractSelf-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word embeddings …...

AbstractThis paper describes Octanove Labs’ submission to the IWSLT 2020 open domain translation challenge. In order to build a high-quality Japanese-Chinese neural machine translation (NMT) system, we use a combination …...

AbstractWe analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce …...

AbstractIn this paper, we propose a neural architecture and a set of training methods for ordering events by predicting temporal relations. Our proposed models receive a pair of events within …...

AbstractCurrent text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification …...

AbstractWe tackle the task of building supervised event trigger identification models which can generalize better across domains. Our work leverages the adversarial domain adaptation (ADA) framework to introduce domain-invariance. ADA …...

AbstractZero-shot learning has been a tough problem since no labeled data is available for unseen classes during training, especially for classes with low similarity. In this situation, transferring from seen …...

AbstractDomain adaption for word segmentation and POS tagging is a challenging problem for Chinese lexical processing. Self-training is one promising solution for it, which struggles to construct a set of …...

AbstractThis paper describes our contribution to SemEval-2021 Task 5: Toxic Spans Detection. Our solution is built upon RoBERTa language model and Conditional Random Fields (CRF). We pre-trained RoBERTa on Civil …...

AbstractIn this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA). While self-training generates synthetic training data where natural inputs are aligned with noisy outputs, back-training …...

AbstractDomain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such assumption is rarely plausible in the real-world and may causes data-privacy …...

AbstractZero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English. While the advance of …...

AbstractThis paper presents an empirical study to efficiently build named entity recognition (NER) systems when a small amount of in-domain labeled data is available. Based upon recent Transformer-based self-supervised pre-trained …...

AbstractExisting work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision. However, the reliance on KB means this …...

AbstractA common approach in many machine learning algorithms involves self-supervised learning on large unlabeled data before fine-tuning on downstream tasks to further improve performance. A new approach for language modelling, …...

AbstractSemantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been acknowledged …...

AbstractMuch of the existing linguistic data in many languages of the world is locked away in non- digitized books and documents. Optical character recognition (OCR) can be used to produce …...

AbstractCross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple ‘direct transfer’ of a learned model based on a multilingual input encoding has …...

AbstractAspect term extraction aims to extract aspect terms from a review sentence that users have expressed opinions on. One of the remaining challenges for aspect term extraction resides in the …...

AbstractAs unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this …...

AbstractThe SemEval 2021 task 5: Toxic Spans Detection is a task of identifying considered-toxic spans in text, which provides a valuable, automatic tool for moderating online contents. This paper represents …...

AbstractAs the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, …...

AbstractUnsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain …...

AbstractA sufficient amount of annotated data is usually required to fine-tune pre-trained language models for downstream tasks. Unfortunately, attaining labeled data can be costly, especially for multiple language varieties and …...

AbstractSelf-training has proven effective for improving NMT performance by augmenting model training with synthetic parallel data. The common practice is to construct synthetic data based on a randomly sampled subset …...

AbstractSemi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternatively predict unlabeled texts as their pseudo-labels …...

AbstractThe prevalence of the COVID-19 pandemic in day-to-day life has yielded large amounts of stance detection data on social media sites, as users turn to social media to share their …...

AbstractDespite their recent successes in tackling many NLP tasks, large-scale pre-trained language models do not perform as well in few-shot settings where only a handful of training examples are available. …...

AbstractWhile we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific …...

AbstractThis paper describes our systems for negation detection and time expression recognition in SemEval 2021 Task 10, Source-Free Domain Adaptation for Semantic Processing. We show that self-training, active learning and …...

AbstractTransfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks. However, annotated data for every target task in every target language is rare, especially for low-resource languages. We …...

AbstractData sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, …...

AbstractSuccinctly summarizing dialogue is a task of growing interest, but inherent challenges, such as insufficient training data and low information density impede our ability to train abstractive models. In this …...

AbstractWhile the prompt-based fine-tuning methods had advanced few-shot natural language understanding tasks, self-training methods are also being explored. This work revisits the consistency regularization in self-training and presents explicit and …...

AbstractThis paper presents the submissions of Huawei Translate Services Center (HW-TSC) to the WMT 2022 General Machine Translation Shared Task. We participate in 6 language pairs, including Zh↔En, Ru↔En, Uk↔En, …...

AbstractData-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs). Such representations are compositional and it is costly to collect responses for all possible combinations of …...

AbstractThis paper considers the task of parsing low-resource languages in a scenario where parallel English data and also a limited seed of annotated sentences in the target language are available, …...

AbstractTargeted Sentiment Analysis (TSA) is a central task for generating insights from consumer reviews. Such content is extremely diverse, with sites like Amazon or Yelp containing reviews on products and …...

AbstractSpoken language understanding (SLU) tasks involve mapping from speech signals to semantic labels. Given the complexity of such tasks, good performance is expected to require large labeled datasets, which are …...

AbstractDiscourse parsing has been studied for decades. However, it still remains challenging to utilize discourse parsing for real-world applications because the parsing accuracy degrades significantly on out-of-domain text. In this …...

AbstractState-of-the-art classification and regression models are often not well calibrated, and cannot reliably provide uncertainty estimates, limiting their utility in safety-critical applications such as clinical decision-making. While recent work has …...

AbstractSelf-training emerges as an important research line on domain adaptation. By taking the model’s prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances …...

AbstractEntailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, …...

AbstractCurrent self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training …...

Previous work has demonstrated that multilin- gual fine-tuning of a pretrained multilingual speech representation model can lead to im- proved speech recognition accuracy when there is extremely little target language …...

AbstractIn cross-lingual named entity recognition (NER), self-training is commonly used to bridge the linguistic gap by training on pseudo-labeled target-language data. However, due to sub-optimal performance on target languages, the …...

AbstractThe performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource …...

AbstractOnline social media is rife with offensive and hateful comments, prompting the need for their automatic detection given the sheer amount of posts created every second. Creating high-quality human-labelled datasets …...

AbstractIn simultaneous translation, the retranslation approach has the advantage of requiring no modifications to the inference engine. However, in order to reduce the undesirable flicker in the output, previous work …...