An official website of the United States government
Computer-based job interview training, including virtual reality (VR) simulations, have gained popularity in recent years to support and aid autistic individuals, who face significant challenges and barriers in finding and maintaining employment. Although popular, these training systems often fail to resemble the complexity and dynamism of the employment interview, as the dialogue management for the virtual conversation agent either relies on choosing from a menu of prespecified answers, or dialogue processing is based on keyword extraction from the transcribed speech of the interviewee, which depends on the interview script. We address this limitation through automated dialogue act classification via transfer learning. This allows for recognizing intent from user speech, independent of the domain of the interview. We also redress the lack of training data for a domain general job interview dialogue act classifier by providing an original dataset with responses to interview questions within a virtual job interview platform from 22 autistic participants. Participants’ responses to a customized interview script were transcribed to text and annotated according to a custom 13-class dialogue act scheme. The best classifier was a fine-tuned bidirectional encoder representations from transformers (BERT) model, with an f1-score of 87%.
more »
« less
Annotating low-confidence questions improves classifier performance
This paper compares methods to select data for annotation in order to improve a classifier used in a question-answering dialogue system. With a classifier trained on 1,500 questions, adding 300 training questions on which the classifier is least confident results in consistently improved performance, whereas adding 300 arbitrarily selected training questions does not yield consistent improvement, and sometimes even degrades performance. The paper uses a new method for comparative evaluation of classifiers for dialogue, which scores each classifier based on the number of appropriate responses retrieved.
more »
« less
- Award ID(s):
- 1852583
- PAR ID:
- 10313591
- Date Published:
- Journal Name:
- Proceedings of the 25th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper compares different methods of using a large language model (GPT-3.5) for creating synthetic training data for a retrieval-based conversational character. The training data are in the form of linked questions and answers, which allow a classifier to retrieve a pre-recorded answer to an unseen question; the intuition is that a large language model could predict what human users might ask, thus saving the effort of collecting real user questions as training data. Results show small improvements in test performance for all synthetic datasets. However, a classifier trained on only small amounts of collected user data resulted in a higher F-score than the classifiers trained on much larger amounts of synthetic data generated using GPT-3.5. Based on these results, we see a potential in using large language models for generating training data, but at this point it is not as valuable as collecting actual user data for training.more » « less
-
Exploration of a design space is the first step in identifying sets of high-performing solutions to complex engineering problems. For this purpose, Bayesian network classifiers (BNCs) have been shown to be effective for mapping regions of interest in the design space, even when those regions of interest exhibit complex topologies. However, identifying sets of desirable solutions can be difficult with a BNC when attempting to map a space where high-performance designs are spread sparsely among a disproportionately large number of low-performance designs, resulting in an imbalanced classifier. In this paper, a method is presented that utilizes probabilities of class membership for known training points, combined with interpolation between those points, to generate synthetic high-performance points in a design space. By adding synthetic design points into the BNC training set, a designer can rebalance an imbalanced classifier and improve classification accuracy throughout the space. For demonstration, this approach is applied to an acoustics metamaterial design problem with a sparse design space characterized by a combination of discrete and continuous design variables. Paper No: DETC2018-85274more » « less
-
Endpoint threat detection research hinges on the availability of worthwhile evaluation benchmarks, but experimenters' understanding of the contents of benchmark datasets is often limited. Typically, attention is only paid to the realism of attack behaviors, which comprises only a small percentage of the audit logs in the dataset, while other characteristics of the data are inscrutable and unknown. We propose a new set of questions for what to talk about when we talk about logs (i.e., datasets): What activities are in the dataset? We introduce a novel visualization that succinctly represents the totality of 100+ GB datasets by plotting the occurrence of provenance graph neighborhoods in a time series. How synthetic is the background activity? We perform autocorrelation analysis of provenance neighborhoods in the training split to identify process behaviors that occur at predictable intervals in the test split. Finally, How conspicuous is the malicious activity? We quantify the proportion of attack behaviors that are observed as benign neighborhoods in the training split as compared to previously-unseen attack neighborhoods. We then validate these questions by profiling the classification performance of state-of-the-art intrusion detection systems (R-CAID, FLASH, KAIROS, GNN) against a battery of public benchmark datasets (DARPA Transparent Computing and OpTC, ATLAS, ATLASv2). We demonstrate that synthetic background activities dramatically inflate True Negative Rates, while conspicuous malicious activities artificially boost True Positive Rates. Further, by explicitly controlling for these factors, we provide a more holistic picture of classifier performance. This work will elevate the dialogue surrounding threat detection datasets and will increase the rigor of threat detection experiments.more » « less
-
null (Ed.)Communication between human and mobile agents is getting increasingly important as such agents are widely deployed in our daily lives. Vision-and-Dialogue Navigation is one of the tasks that evaluate the agent’s ability to interact with humans for assistance and navigate based on natural language responses. In this paper, we explore the Navigation from Dialogue History (NDH) task, which is based on the Cooperative Vision-and-Dialogue Navigation (CVDN) dataset, and present a state-of-the-art model which is built upon Vision-Language transformers. However, despite achieving competitive performance, we find that the agent in the NDH task is not evaluated appropriately by the primary metric – Goal Progress. By analyzing the performance mismatch between Goal Progress and other metrics (e.g., normalized Dynamic Time Warping) from our state-of-the-art model, we show that NDH’s sub-path based task setup (i.e., navigating partial trajectory based on its correspondent subset of the full dialogue) does not provide the agent with enough supervision signal towards the goal region. Therefore, we propose a new task setup called NDH-Full which takes the full dialogue and the whole navigation path as one instance. We present a strong baseline model and show initial results on this new task. We further describe several approaches that we try, in order to improve the model performance (based on curriculum learning, pre-training, and data-augmentation), suggesting potential useful training methods on this new NDH-Full task.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
