相关论文: Will it Unblend?

Transformer classifiers such as BERT deliver impressive closed-set accuracy, yet they remain brittle when confronted with inputs from unseen categories--a common scenario for deployed NLP systems. We investigate Open-Set Recognition (OSR)…

Although pre-trained contextualized language models such as BERT achieve significant performance on various downstream tasks, current language representation still only focuses on linguistic objective at a specific granularity, which may…

Open-text (or open-domain) semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR). Unfortunately, large scale systems cannot be easily machine-learned due to…

Word embeddings are a key component of high-performing natural language processing (NLP) systems, but it remains a challenge to learn good representations for novel words on the fly, i.e., for words that did not occur in the training data.…

Natural Language Processing (NLP) for low-resource languages, which lack large annotated datasets, faces significant challenges due to limited high-quality data and linguistic resources. The selection of embeddings plays a critical role in…

Self-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…

Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent…

Open-Vocabulary Semantic Segmentation (OVSS) has advanced with recent vision-language models (VLMs), enabling segmentation beyond predefined categories through various learning schemes. Notably, training-free methods offer scalable, easily…

Unsupervised sentence representation learning aims to transform input sentences into fixed-length vectors enriched with intricate semantic information while obviating the reliance on labeled data. Recent strides within this domain have been…

Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks. However, their excessive amount of parameters hinders them from efficient deployment on edge devices. Binarization of the BERT models can…

One of the biggest challenges in Multimedia information retrieval and understanding is to bridge the semantic gap by properly modeling concept semantics in context. The presence of out of vocabulary (OOV) concepts exacerbates this…

The standard BERT adopts subword-based tokenization, which may break a word into two or more wordpieces (e.g., converting "lossless" to "loss" and "less"). This will bring inconvenience in following situations: (1) what is the best way to…

Neural language models learn word representations that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models. We show that translation-based embeddings outperform…

Due to the dynamic nature of human language, automatic speech recognition (ASR) systems need to continuously acquire new vocabulary. Out-Of-Vocabulary (OOV) words, such as trending words and new named entities, pose problems to modern ASR…

We propose a new technique for computational language representation called elementwise embedding, in which a material (semantic unit) is abstracted into a horizontal concatenation of lower-dimensional element (character) embeddings. While…

We describe an "interpretability illusion" that arises when analyzing the BERT model. Activations of individual neurons in the network may spuriously appear to encode a single, simple concept, when in fact they are encoding something far…

Compositionality is a key aspect of human intelligence, essential for reasoning and generalization. While transformer-based models have become the de facto standard for many language modeling tasks, little is known about how they represent…

A growing body of research in natural language processing (NLP) and natural language understanding (NLU) is investigating human-like knowledge learned or encoded in the word embeddings from large language models. This is a step towards…

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…

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa…