An official website of the United States government
Although models using contextual word embeddings have achieved state-of-the-art results on a host of NLP tasks, little is known about exactly what information these embeddings encode about the context words that they are understood to reflect. To address this question, we introduce a suite of probing tasks that enable fine-grained testing of contextual embeddings for encoding of information about surrounding words. We apply these tasks to examine the popular BERT, ELMo and GPT contextual encoders, and find that each of our tested information types is indeed encoded as contextual information across tokens, often with near-perfect recoverability -- but the encoders vary in which features they distribute to which tokens, how nuanced their distributions are, and how robust the encoding of each feature is to distance. We discuss implications of these results for how different types of models break down and prioritize word-level context information when constructing token embeddings.
more »
« less
Economic Worth-Aware Word Embeddings
Knowing the perceived economic value of words is often desirable for applications such as product naming and pricing. However, there is a lack of understanding on the underlying economic worths of words, even though we have seen some breakthrough on learning the semantics of words. In this work, we bridge this gap by proposing a joint-task neural network model, Word Worth Model (WWM), to learn word embedding that captures the underlying economic worths. Through the design of WWM, we incorporate contextual factors, e.g., product’s brand name and restaurant’s city, that may affect the aggregated monetary value of a textual item. Via a comprehensive evaluation, we show that, compared with other baselines, WWM accurately predicts missing words when given target words. We also show that the learned embeddings of both words and contextual factors reflect well the underlying economic worths through various visualization analyses.
more »
« less
- Award ID(s):
- 1717084
- PAR ID:
- 10303742
- Date Published:
- Journal Name:
- Proceedings of the 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA 2020)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Hacker forums provide malicious actors with a large database of tutorials, goods, and assets to leverage for cyber-attacks. Careful research of these forums can provide tremendous benefit to the cybersecurity community through trend identification and exploit categorization. This study aims to provide a novel static word embedding, Hack2Vec, to improve performance on hacker forum classification tasks. Our proposed Hack2Vec model distills contextual representations from the seminal pre-trained language model BERT to a continuous bag-of-words model to create a highly targeted hacker forum static word embedding. The results of our experimental design indicate that Hack2Vec improves performance over prominent embeddings in accuracy, precision, recall, and F1-score for a benchmark hacker forum classification task.more » « less
-
Sign words are the building blocks of any sign language. In this work, we present wSignGen, a word-conditioned 3D American Sign Language (ASL) generation model dedicated to synthesizing realistic and grammatically accurate motion sequences for sign words. Our approach leverages a transformer-based diffusion model, trained on a curated dataset of 3D motion meshes from word-level ASL videos. By integrating CLIP, wSignGen offers two advantages: image-based generation, which is particularly useful for children learning sign language but not yet able to read, and the ability to generalize to unseen synonyms. Experiments demonstrate that wSignGen significantly outperforms the baseline model in the task of sign word generation. Moreover, human evaluation experiments show that wSignGen can generate high-quality, grammatically correct ASL signs effectively conveyed through 3D avatars.more » « less
-
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 have been done on understanding the text content of a query or a document. This paper studies leveraging a recently-proposed contextual neural language model, BERT, to provide deeper text understanding for IR.Experimental results demonstrate that the contextual text representations from BERT are more effective than traditional word embed-dings. Compared to bag-of-words retrieval models, the contextual language model can better leverage language structures, bringing large improvements on queries written in natural languages. Combining the text understanding ability with search knowledge leads to an enhanced pre-trained BERT model that can benefit related search tasks where training data are limited.more » « less
-
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 have been done on understanding the text content of a query or a document. This paper studies leveraging a recently-proposed contextual neural language model, BERT, to provide deeper text understanding for IR.Experimental results demonstrate that the contextual text representations from BERT are more effective than traditional word embeddings. Compared to bag-of-words retrieval models, the contextual language model can better leverage language structures, bringing large improvements on queries written in natural languages. Combining the text understanding ability with search knowledge leads to an enhanced pre-trained BERT model that can benefit related search tasks where training data are limited.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/DSAA49011.2020.00048
