An official website of the United States government
The complex and interdisciplinary nature of scientific concepts presents formidable challenges for students in developing their knowledge-in-use skills. The utilization of computerized analysis for evaluating students’ contextualized constructed responses offers a potential avenue for educators to develop personalized and scalable interventions, thus supporting the current teaching and learning of science. While prior research in artificial intelligence has demonstrated the effectiveness of algorithms, including Bidirectional Encoder Representations from Transformers (BERT), in tasks like automated classifications of constructed responses, these efforts have predominantly leaned towards text-level features, often overlooking the exploration of conceptual ideas embedded in students’ responses from a cognitive perspective. Despite BERT’s performance in downstream tasks, challenges may arise in domain-specific tasks, particularly in establishing knowledge connections between specialized and open domains. These challenges become pronounced in small-scale and imbalanced educational datasets, where the available information for fine-tuning is frequently inadequate to capture task-specific nuances and contextual details. The primary objective of the present study is to investigate the effectiveness of a pretrained language model, when integrated with an ontological framework aligned with a contextualized science assessment, in classifying students’ expertise levels in scientific explanation. Our findings indicate that while pretrained language models, such as BERT, contribute to enhanced performance in language-related tasks within educational contexts, the incorporation of identifying domain-specific terms and extracting and substituting with their associated sibling terms in sentences through ontology-based systems can significantly improve classification model performance. Further, we qualitatively examined student responses and found that, as expected, the ontology framework identified and substituted key domain-specific terms in student responses that led to more accurate predictive scores. The study explores the practical implementation of ontology in assessment evaluation to facilitate formative assessment and formulate instructional strategies.
more »
« less
Table Search Using a Deep Contextualized Language Model
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
- Award ID(s):
- 1816325
- PAR ID:
- 10164856
- Date Published:
- Journal Name:
- 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Existing work on tabular representation-learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT. While this joint pretraining improves tasks involving paired tables and text (e.g., answering questions about tables), we show that it underperforms on tasks that operate over tables without any associated text (e.g., populating missing cells). We devise a simple pretraining objective (corrupt cell detection) that learns exclusively from tabular data and reaches the state-of-the-art on a suite of table-based prediction tasks. Unlike competing approaches, our model (TABBIE) provides embeddings of all table substructures (cells, rows, and columns), and it also requires far less compute to train. A qualitative analysis of our model’s learned cell, column, and row representations shows that it understands complex table semantics and numerical trends.more » « less
-
Abstract Background Natural language processing (NLP) tasks in the health domain often deal with limited amount of labeled data due to high annotation costs and naturally rare observations. To compensate for the lack of training data, health NLP researchers often have to leverage knowledge and resources external to a task at hand. Recently, pretrained large-scale language models such as the Bidirectional Encoder Representations from Transformers (BERT) have been proven to be a powerful way of learning rich linguistic knowledge from massive unlabeled text and transferring that knowledge to downstream tasks. However, previous downstream tasks often used training data at such a large scale that is unlikely to obtain in the health domain. In this work, we aim to study whether BERT can still benefit downstream tasks when training data are relatively small in the context of health NLP. Method We conducted a learning curve analysis to study the behavior of BERT and baseline models as training data size increases. We observed the classification performance of these models on two disease diagnosis data sets, where some diseases are naturally rare and have very limited observations (fewer than 2 out of 10,000). The baselines included commonly used text classification models such as sparse and dense bag-of-words models, long short-term memory networks, and their variants that leveraged external knowledge. To obtain learning curves, we incremented the amount of training examples per disease from small to large, and measured the classification performance in macro-averaged $$F_{1}$$ F 1 score. Results On the task of classifying all diseases, the learning curves of BERT were consistently above all baselines, significantly outperforming them across the spectrum of training data sizes. But under extreme situations where only one or two training documents per disease were available, BERT was outperformed by linear classifiers with carefully engineered bag-of-words features. Conclusion As long as the amount of training documents is not extremely few, fine-tuning a pretrained BERT model is a highly effective approach to health NLP tasks like disease classification. However, in extreme cases where each class has only one or two training documents and no more will be available, simple linear models using bag-of-words features shall be considered.more » « less
-
null (Ed.)Ad hoc table retrieval is the problem of identifying the most relevant datasets to a user's query. We present an approach to the problem that builds a knowledge graph by combining information about the collection of tables with external sources such as WordNet and pretrained Glove embeddings. We apply multi-relational graph convolutional networks to learn embeddings for the knowledge graph nodes and utilize three different methods to create vectors representing the tables and queries from these embeddings. We create a novel learning-to-rank neural architecture that incorporates the multiple embeddings in order to improve table retrieval results. We evaluate our approach using two large collections of tables from public WikiTables and Web tables data, demonstrating substantial improvements over state-of-the-art methods in table retrieval.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
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.1145/3397271.3401044
