An official website of the United States government
Pretrained contextualized language models such as BERT have achieved impressive results on various natural language processing benchmarks. Benefiting from multiple pretraining tasks and large scale training corpora, pretrained models can capture complex syntactic word relations. In this paper, we use the deep contextualized language model BERT for the task of ad hoc table retrieval. We investigate how to encode table content considering the table structure and input length limit of BERT. We also propose an approach that incorporates features from prior literature on table retrieval and jointly trains them with BERT. In experiments on public datasets, we show that our best approach can outperform the previous state-of-the-art method and BERT baselines with a large margin under different evaluation metrics.
more »
« less
Estimating word co-occurrence probabilities from pretrained static embeddings using a log-bilinear model
We investigate how to use pretrained static word embeddings to deliver improved estimates of bilexical co-occurrence probabilities: conditional probabilities of one word given a single other word in a specific relationship. Such probabilities play important roles in psycholinguistics, corpus linguistics, and usage-based cognitive modeling of language more generally. We propose a log-bilinear model taking pretrained vector representations of the two words as input, enabling generalization based on the distributional information contained in both vectors. We show that this model outperforms baselines in estimating probabilities of adjectives given nouns that they attributively modify, and probabilities of nominal direct objects given their head verbs, given limited training data in Arabic, English, Korean, and Spanish.
more »
« less
- Award ID(s):
- 1947307
- PAR ID:
- 10336257
- Date Published:
- Journal Name:
- Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
- Page Range / eLocation ID:
- 54 to 60
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Clinical notes present a wealth of information for applications in the clinical domain, but heterogeneity across clinical institutions and settings presents challenges for their processing. The clinical natural language processing field has made strides in overcoming domain heterogeneity, while pretrained deep learning models present opportunities to transfer knowledge from one task to another. Pretrained models have performed well when transferred to new tasks; however, it is not well understood if these models generalize across differences in institutions and settings within the clinical domain. We explore if institution or setting specific pretraining is necessary for pretrained models to perform well when transferred to new tasks. We find no significant performance difference between models pretrained across institutions and settings, indicating that clinically pretrained models transfer well across such boundaries. Given a clinically pretrained model, clinical natural language processing researchers may forgo the time-consuming pretraining step without a significant performance drop.more » « less
-
We follow up on recent work demonstrating clear advantages of lexical-to-sublexical feedback in the TRACE model of spoken word recognition. The prior work compared accuracy and recognition times in TRACE with feedback on or off as progressively more noise was added to inputs. Recognition times were faster with feedback at every level of noise, and there was an accuracy advantage for feedback with noise added to inputs. However, a recent article claims that those results must be an artifact of converting activations to response probabilities, because feedback could only reinforce the “status quo.” That is, the claim is that given noisy inputs, feedback must reinforce all inputs equally, whether driven by signal or noise. We demonstrate that the feedback advantage replicates with raw activations. We also demonstrate that lexical feedback selectively reinforces lexically-coherent input patterns – that is, signal over noise – and explain how that behavior emerges naturally in interactive activation.more » « less
-
As we begin to see low-powered computing paradigms (Neuromorphic Computing, Spiking Neural Networks, etc.) becoming more popular, learning binary word embeddings has become increasingly important for supporting NLP applications at the edge. Existing binary word embeddings are mostly derived from pretrained real-valued embeddings through different simple transformations, which often break the semantic consistency and the so-called ``arithmetic'' properties learned by the original, real-valued embeddings. This paper aims to address this limitation by introducing a new approach to learn binary embeddings from scratch, preserving the semantic relationships between words as well as the arithmetic properties of the embeddings themselves. To achieve this, we propose a novel genetic algorithm to learn the relationships between words from existing word analogy data-sets, carefully making sure that the arithmetic properties of the relationships are preserved. Evaluating our generated 16, 32, and 64-bit binary word embeddings on Mikolov's word analogy task shows that more than 95% of the time, the best fit for the analogy is ranked in the top 5 most similar words in terms of cosine similarity."more » « less
-
Computer vision often uses highly accurate Convolutional Neural Networks (CNNs), but these deep learning models are associated with ever-increasing energy and computation requirements. Producing more energy-efficient CNNs often requires model training which can be cost-prohibitive. We propose a novel, automated method to make a pretrained CNN more energyefficient without re-training. Given a pretrained CNN, we insert a threshold layer that filters activations from the preceding layers to identify regions of the image that are irrelevant, i.e. can be ignored by the following layers while maintaining accuracy. Our modified focused convolution operation saves inference latency (by up to 25%) and energy costs (by up to 22%) on various popular pretrained CNNs, with little to no loss in accuracymore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2022.cmcl-1.6
