相关论文: MICE: Mining Idioms with Contextual Embeddings

Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks. Contextual embeddings assign each word a…

Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and…

The same multi-word expressions may have different meanings in different sentences. They can be mainly divided into two categories, which are literal meaning and idiomatic meaning. Non-contextual-based methods perform poorly on this…

Despite their success in a variety of NLP tasks, pre-trained language models, due to their heavy reliance on compositionality, fail in effectively capturing the meanings of multiword expressions (MWEs), especially idioms. Therefore,…

Pre-trained language models such as BERT have been proved to be powerful in many natural language processing tasks. But in some text classification applications such as emotion recognition and sentiment analysis, BERT may not lead to…

Grammatical error detection (GED) in non-native writing requires systems to identify a wide range of errors in text written by language learners. Error detection as a purely supervised task can be challenging, as GED datasets are limited in…

Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these settings. Such…

Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this work, we investigate how two pretrained…

Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words…

We tackle the problem of identifying metaphors in text, treated as a sequence tagging task. The pre-trained word embeddings GloVe, ELMo and BERT have individually shown good performance on sequential metaphor identification. These…

Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddings are sense agnostic. In this work, we propose a novel…

Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning query-document relevance patterns, but few explorations…

Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many…

Pretraining deep neural network architectures with a language modeling objective has brought large improvements for many natural language processing tasks. Exemplified by BERT, a recently proposed such architecture, we demonstrate that…

We present a novel online algorithm that learns the essence of each dimension in word embeddings by minimizing the within-group distance of contextualized embedding groups. Three state-of-the-art neural-based language models are used,…

We study the settings for which deep contextual embeddings (e.g., BERT) give large improvements in performance relative to classic pretrained embeddings (e.g., GloVe), and an even simpler baseline---random word embeddings---focusing on the…

We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and…

Building machine learning prediction models for a specific NLP task requires sufficient training data, which can be difficult to obtain for less-resourced languages. Cross-lingual embeddings map word embeddings from a less-resourced…

Deep neural models, in particular Transformer-based pre-trained language models, require a significant amount of data to train. This need for data tends to lead to problems when dealing with idiomatic multiword expressions (MWEs), which are…

State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…