Matching Items (8)
Filtering by
- All Subjects: deep learning
- All Subjects: Evaluation
- Creators: Baral, Chitta
Description
There is a serious need for early childhood intervention practices for children who are living at or below the poverty line. Since 1965 Head Start has provided a federally funded, free preschool program for children in this population. The City of Phoenix Head Start program consists of nine delegate agencies, seven of which reside in school districts. These agencies are currently not conducting local longitudinal evaluations of their preschool graduates. The purpose of this study was to recommend initial steps the City of Phoenix grantee and the delegate agencies can take to begin a longitudinal evaluation process of their Head Start programs. Seven City of Phoenix Head Start agency directors were interviewed. These interviews provided information about the attitudes of the directors when considering longitudinal evaluations and how Head Start already evaluates their programs through internal assessments. The researcher also took notes on the Third Grade Follow-Up to the Head Start Executive Summary in order to make recommendations to the City of Phoenix Head Start programs about the best practices for longitudinal student evaluations.
ContributorsArmfield, Jessica Ann (Author) / Duggan, Mary Anne (Thesis director) / Dumka, Larry (Committee member) / Barrett, The Honors College (Contributor) / T. Denny Sanford School of Social and Family Dynamics (Contributor) / School of International Letters and Cultures (Contributor)
Created2014-05
Description
Medical records are increasingly being recorded in the form of electronic health records (EHRs), with a significant amount of patient data recorded as unstructured natural language text. Consequently, being able to extract and utilize clinical data present within these records is an important step in furthering clinical care. One important aspect within these records is the presence of prescription information. Existing techniques for extracting prescription information — which includes medication names, dosages, frequencies, reasons for taking, and mode of administration — from unstructured text have focused on the application of rule- and classifier-based methods. While state-of-the-art systems can be effective in extracting many types of information, they require significant effort to develop hand-crafted rules and conduct effective feature engineering. This paper presents the use of a bidirectional LSTM with CRF tagging model initialized with precomputed word embeddings for extracting prescription information from sentences without requiring significant feature engineering. The experimental results, run on the i2b2 2009 dataset, achieve an F1 macro measure of 0.8562, and scores above 0.9449 on four of the six categories, indicating significant potential for this model.
ContributorsRawal, Samarth Chetan (Author) / Baral, Chitta (Thesis director) / Anwar, Saadat (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Science instructors need questions for use in exams, homework assignments, class discussions, reviews, and other instructional activities. Textbooks never have enough questions, so instructors must find them from other sources or generate their own questions. In order to supply instructors with biology questions, a semantic network approach was developed for generating open response biology questions. The generated questions were compared to professional authorized questions.
To boost students’ learning experience, adaptive selection was built on the generated questions. Bayesian Knowledge Tracing was used as embedded assessment of the student’s current competence so that a suitable question could be selected based on the student’s previous performance. A between-subjects experiment with 42 participants was performed, where half of the participants studied with adaptive selected questions and the rest studied with mal-adaptive order of questions. Both groups significantly improved their test scores, and the participants in adaptive group registered larger learning gains than participants in the control group.
To explore the possibility of generating rich instructional feedback for machine-generated questions, a question-paragraph mapping task was identified. Given a set of questions and a list of paragraphs for a textbook, the goal of the task was to map the related paragraphs to each question. An algorithm was developed whose performance was comparable to human annotators.
A multiple-choice question with high quality distractors (incorrect answers) can be pedagogically valuable as well as being much easier to grade than open-response questions. Thus, an algorithm was developed to generate good distractors for multiple-choice questions. The machine-generated multiple-choice questions were compared to human-generated questions in terms of three measures: question difficulty, question discrimination and distractor usefulness. By recruiting 200 participants from Amazon Mechanical Turk, it turned out that the two types of questions performed very closely on all the three measures.
To boost students’ learning experience, adaptive selection was built on the generated questions. Bayesian Knowledge Tracing was used as embedded assessment of the student’s current competence so that a suitable question could be selected based on the student’s previous performance. A between-subjects experiment with 42 participants was performed, where half of the participants studied with adaptive selected questions and the rest studied with mal-adaptive order of questions. Both groups significantly improved their test scores, and the participants in adaptive group registered larger learning gains than participants in the control group.
To explore the possibility of generating rich instructional feedback for machine-generated questions, a question-paragraph mapping task was identified. Given a set of questions and a list of paragraphs for a textbook, the goal of the task was to map the related paragraphs to each question. An algorithm was developed whose performance was comparable to human annotators.
A multiple-choice question with high quality distractors (incorrect answers) can be pedagogically valuable as well as being much easier to grade than open-response questions. Thus, an algorithm was developed to generate good distractors for multiple-choice questions. The machine-generated multiple-choice questions were compared to human-generated questions in terms of three measures: question difficulty, question discrimination and distractor usefulness. By recruiting 200 participants from Amazon Mechanical Turk, it turned out that the two types of questions performed very closely on all the three measures.
ContributorsZhang, Lishang (Author) / VanLehn, Kurt (Thesis advisor) / Baral, Chitta (Committee member) / Hsiao, Ihan (Committee member) / Wright, Christian (Committee member) / Arizona State University (Publisher)
Created2015
Description
Artificial Intelligence, as the hottest research topic nowadays, is mostly driven by data. There is no doubt that data is the king in the age of AI. However, natural high-quality data is precious and rare. In order to obtain enough and eligible data to support AI tasks, data processing is always required. To be even worse, the data preprocessing tasks are often dull and heavy, which require huge human labors to deal with. Statistics show 70% - 80% of the data scientists' time is spent on data integration process. Among various reasons, schema changes that commonly exist in the data warehouse are one significant obstacle that impedes the automation of the end-to-end data integration process. Traditional data integration applications rely on data processing operators such as join, union, aggregation and so on. Those operations are fragile and can be easily interrupted by schema changes. Whenever schema changes happen, the data integration applications will require human labors to solve the interruptions and downtime. The industries as well as the data scientists need a new mechanism to handle the schema changes in data integration tasks. This work proposes a new direction of data integration applications based on deep learning models. The data integration problem is defined in the scenario of integrating tabular-format data with natural schema changes, using the cell-based data abstraction. In addition, data augmentation and adversarial learning are investigated to boost the model robustness to schema changes. The experiments are tested on two real-world data integration scenarios, and the results demonstrate the effectiveness of the proposed approach.
ContributorsWang, Zijie (Author) / Zou, Jia (Thesis advisor) / Baral, Chitta (Committee member) / Candan, K. Selcuk (Committee member) / Arizona State University (Publisher)
Created2021
Description
In natural language processing, language models have achieved remarkable success over the last few years. The Transformers are at the core of most of these models. Their success can be mainly attributed to an enormous amount of curated data they are trained on. Even though such language models are trained on massive curated data, they often need specific extracted knowledge to understand better and reason. This is because often relevant knowledge may be implicit or missing, which hampers machine reasoning. Apart from that, manual knowledge curation is time-consuming and erroneous. Hence, finding fast and effective methods to extract such knowledge from data is important for improving language models. This leads to finding ideal ways to utilize such knowledge by incorporating them into language models. Successful knowledge extraction and integration lead to an important question of knowledge evaluation of such models by developing tools or introducing challenging test suites to learn about their limitations and improve them further. So to improve the transformer-based models, understanding the role of knowledge becomes important. In the pursuit to improve language models with knowledge, in this dissertation I study three broad research directions spanning across the natural language, biomedical and cybersecurity domains: (1) Knowledge Extraction (KX) - How can transformer-based language models be leveraged to extract knowledge from data? (2) Knowledge Integration (KI) - How can such specific knowledge be used to improve such models? (3) Knowledge Evaluation (KE) - How can language models be evaluated for specific skills and understand their limitations?
I propose methods to extract explicit textual, implicit structural, missing textual, and missing structural knowledge from natural language and binary programs using transformer-based language models. I develop ways to improve the language model’s multi-step and commonsense reasoning abilities using external knowledge. Finally, I develop challenging datasets which assess their numerical reasoning skills in both in-domain and out-of-domain settings.
ContributorsPal, Kuntal Kumar (Author) / Baral, Chitta (Thesis advisor) / Wang, Ruoyu (Committee member) / Blanco, Eduardo (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2023
Description
In this thesis, I present two new datasets and a modification to the existing models in the form of a novel attention mechanism for Natural Language Inference (NLI). The new datasets have been carefully synthesized from various existing corpora released for different tasks.
The task of NLI is to determine the possibility of a sentence referred to as “Hypothesis” being true given that another sentence referred to as “Premise” is true. In other words, the task is to identify whether the “Premise” entails, contradicts or remains neutral with regards to the “Hypothesis”. NLI is a precursor to solving many Natural Language Processing (NLP) tasks such as Question Answering and Semantic Search. For example, in Question Answering systems, the question is paraphrased to form a declarative statement which is treated as the hypothesis. The options are treated as the premise. The option with the maximum entailment score is considered as the answer. Considering the applications of NLI, the importance of having a strong NLI system can't be stressed enough.
Many large-scale datasets and models have been released in order to advance the field of NLI. While all of these models do get good accuracy on the test sets of the datasets they were trained on, they fail to capture the basic understanding of “Entities” and “Roles”. They often make the mistake of inferring that “John went to the market.” from “Peter went to the market.” failing to capture the notion of “Entities”. In other cases, these models don't understand the difference in the “Roles” played by the same entities in “Premise” and “Hypothesis” sentences and end up wrongly inferring that “Peter drove John to the stadium.” from “John drove Peter to the stadium.”
The lack of understanding of “Roles” can be attributed to the lack of such examples in the various existing datasets. The reason for the existing model’s failure in capturing the notion of “Entities” is not just due to the lack of such examples in the existing NLI datasets. It can also be attributed to the strict use of vector similarity in the “word-to-word” attention mechanism being used in the existing architectures.
To overcome these issues, I present two new datasets to help make the NLI systems capture the notion of “Entities” and “Roles”. The “NER Changed” (NC) dataset and the “Role-Switched” (RS) dataset contains examples of Premise-Hypothesis pairs that require the understanding of “Entities” and “Roles” respectively in order to be able to make correct inferences. This work shows how the existing architectures perform poorly on the “NER Changed” (NC) dataset even after being trained on the new datasets. In order to help the existing architectures, understand the notion of “Entities”, this work proposes a modification to the “word-to-word” attention mechanism. Instead of relying on vector similarity alone, the modified architectures learn to incorporate the “Symbolic Similarity” as well by using the Named-Entity features of the Premise and Hypothesis sentences. The new modified architectures not only perform significantly better than the unmodified architectures on the “NER Changed” (NC) dataset but also performs as well on the existing datasets.
The task of NLI is to determine the possibility of a sentence referred to as “Hypothesis” being true given that another sentence referred to as “Premise” is true. In other words, the task is to identify whether the “Premise” entails, contradicts or remains neutral with regards to the “Hypothesis”. NLI is a precursor to solving many Natural Language Processing (NLP) tasks such as Question Answering and Semantic Search. For example, in Question Answering systems, the question is paraphrased to form a declarative statement which is treated as the hypothesis. The options are treated as the premise. The option with the maximum entailment score is considered as the answer. Considering the applications of NLI, the importance of having a strong NLI system can't be stressed enough.
Many large-scale datasets and models have been released in order to advance the field of NLI. While all of these models do get good accuracy on the test sets of the datasets they were trained on, they fail to capture the basic understanding of “Entities” and “Roles”. They often make the mistake of inferring that “John went to the market.” from “Peter went to the market.” failing to capture the notion of “Entities”. In other cases, these models don't understand the difference in the “Roles” played by the same entities in “Premise” and “Hypothesis” sentences and end up wrongly inferring that “Peter drove John to the stadium.” from “John drove Peter to the stadium.”
The lack of understanding of “Roles” can be attributed to the lack of such examples in the various existing datasets. The reason for the existing model’s failure in capturing the notion of “Entities” is not just due to the lack of such examples in the existing NLI datasets. It can also be attributed to the strict use of vector similarity in the “word-to-word” attention mechanism being used in the existing architectures.
To overcome these issues, I present two new datasets to help make the NLI systems capture the notion of “Entities” and “Roles”. The “NER Changed” (NC) dataset and the “Role-Switched” (RS) dataset contains examples of Premise-Hypothesis pairs that require the understanding of “Entities” and “Roles” respectively in order to be able to make correct inferences. This work shows how the existing architectures perform poorly on the “NER Changed” (NC) dataset even after being trained on the new datasets. In order to help the existing architectures, understand the notion of “Entities”, this work proposes a modification to the “word-to-word” attention mechanism. Instead of relying on vector similarity alone, the modified architectures learn to incorporate the “Symbolic Similarity” as well by using the Named-Entity features of the Premise and Hypothesis sentences. The new modified architectures not only perform significantly better than the unmodified architectures on the “NER Changed” (NC) dataset but also performs as well on the existing datasets.
ContributorsShrivastava, Ishan (Author) / Baral, Chitta (Thesis advisor) / Anwar, Saadat (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
Significance of real-world knowledge for Natural Language Understanding(NLU) is well-known for decades. With advancements in technology, challenging tasks like question-answering, text-summarizing, and machine translation are made possible with continuous efforts in the field of Natural Language Processing(NLP). Yet, knowledge integration to answer common sense questions is still a daunting task. Logical reasoning has been a resort for many of the problems in NLP and has achieved considerable results in the field, but it is difficult to resolve the ambiguities in a natural language. Co-reference resolution is one of the problems where ambiguity arises due to the semantics of the sentence. Another such problem is the cause and result statements which require causal commonsense reasoning to resolve the ambiguity. Modeling these type of problems is not a simple task with rules or logic. State-of-the-art systems addressing these problems use a trained neural network model, which claims to have overall knowledge from a huge trained corpus. These systems answer the questions by using the knowledge embedded in their trained language model. Although the language models embed the knowledge from the data, they use occurrences of words and frequency of co-existing words to solve the prevailing ambiguity. This limits the performance of language models to solve the problems in common-sense reasoning task as it generalizes the concept rather than trying to answer the problem specific to its context. For example, "The painting in Mark's living room shows an oak tree. It is to the right of a house", is a co-reference resolution problem which requires knowledge. Language models can resolve whether "it" refers to "painting" or "tree", since "house" and "tree" are two common co-occurring words so the models can resolve "tree" to be the co-reference. On the other hand, "The large ball crashed right through the table. Because it was made of Styrofoam ." to resolve for "it" which can be either "table" or "ball", is difficult for a language model as it requires more information about the problem.
In this work, I have built an end-to-end framework, which uses the automatically extracted knowledge based on the problem. This knowledge is augmented with the language models using an explicit reasoning module to resolve the ambiguity. This system is built to improve the accuracy of the language models based approaches for commonsense reasoning. This system has proved to achieve the state of the art accuracy on the Winograd Schema Challenge.
In this work, I have built an end-to-end framework, which uses the automatically extracted knowledge based on the problem. This knowledge is augmented with the language models using an explicit reasoning module to resolve the ambiguity. This system is built to improve the accuracy of the language models based approaches for commonsense reasoning. This system has proved to achieve the state of the art accuracy on the Winograd Schema Challenge.
ContributorsPrakash, Ashok (Author) / Baral, Chitta (Thesis advisor) / Devarakonda, Murthy (Committee member) / Anwar, Saadat (Committee member) / Arizona State University (Publisher)
Created2019
Description
Emotion recognition in conversation has applications within numerous domains such as affective computing and medicine. Recent methods for emotion recognition jointly utilize conversational data over several modalities including audio, video, and text. However, state-of-the-art frameworks for this task do not focus on the feature extraction and feature fusion steps of this process. This thesis aims to improve the state-of-the-art method by incorporating two components to better accomplish these steps. By doing so, we are able to produce improved representations for the text modality and better model the relationships between all modalities. This paper proposes two methods which focus on these concepts and provide improved accuracy over the state-of-the-art framework for multimodal emotion recognition in dialogue.
ContributorsRawal, Siddharth (Author) / Baral, Chitta (Thesis director) / Shah, Shrikant (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05