Таңбаланбаған деректер

We present a new semi-supervised training procedure for conditional random fields (CRFs) that can be used to train sequence segmentors and labelers from a combina- tion of labeled and unlabeled …...

In this paper we explore robustness and domain adaptation issues for Word Sense Disambiguation (WSD) using Singular Value Decomposition (SVD) and unlabeled data. We focus on the semi-supervised do- main …...

English pronouns like he and they reliably re- flect the gender and number of the entities to which they refer. Pronoun resolution systems can use this fact to filter noun …...

This paper describes our participation in the message polarity classification task of SemEval 2014. We focused on exploiting unlabeled data to improve accuracy, com- bining features leveraging word represen- tations …...

In this paper, we apply a weakly-supervised learning approach for slot tagging using con- ditional random fields by exploiting web search click logs. We extend the constrained lattice training of …...

In this work, we propose a semi- supervised method for short text clus- tering, where we represent texts as dis- tributed vectors with neural networks, and use a small amount …...

We describe TweeTIME, a temporal tagger for recognizing and normalizing time expres- sions in Twitter. Most previous work in so- cial media analysis has to rely on tempo- ral resolvers …...

AbstractWe address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input …...

AbstractWe present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data. The goal is to enable robust transfer to highly specialized domains, …...

AbstractData augmentation techniques have been widely used to improve machine learning performance as they facilitate generalization. In this work, we propose a novel augmentation method to generate high quality synthetic …...

AbstractDeep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to using them in …...

AbstractNeural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. …...

AbstractTransformer-based language models trained on large natural language corpora have been very useful in downstream entity extraction tasks. However, they often result in poor performances when applied to domains that …...

AbstractTraining language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on …...

AbstractLabeling large amounts of extractive summarization data is often prohibitive expensive due to time, financial, and expertise constraints, which poses great challenges to incorporating summarization system in practical applications. This …...

AbstractDiscovering new intents is of great significance for establishing the Task-Oriented Dialogue System. Most existing methods either cannot transfer prior knowledge contained in known intents or fall into the dilemma …...