Arrow Research search

Author name cluster

Randy Goebel

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

20 papers
2 author rows

Possible papers

20

ECAI Conference 2023 Conference Paper

From Intermediate Representations to Explanations: Exploring Hierarchical Structures in NLP

  • Housam Khalifa Bashier Babiker
  • Mi-Young Kim
  • Randy Goebel

Interpretation methods for learned models used in natural language processing (NLP) applications usually provide support for local (specific) explanations, such as quantifying the contribution of each word to the predicted class. But they typically ignore the potential interaction amongst those word tokens. Unlike currently popular methods, we propose a deep model which uses feature attribution and identification of dependencies to support the learning of interpretable representations that will support creation of hierarchical explanations. In addition, hierarchical explanations provide a basis for visualizing how words and phrases are combined at different levels of abstraction, which enables end-users to better understand the prediction process of a deep network. Our study uses multiple well-known datasets to demonstrate the effectiveness of our approach, and provides both automatic and human evaluation.

Details

AAAI Conference 2023 Conference Paper

The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure

  • Xing Chen
  • Dongcui Diao
  • Hechang Chen
  • Hengshuai Yao
  • Haiyin Piao
  • Zhixiao Sun
  • Zhiwei Yang
  • Randy Goebel

The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the sigmoid function (which provides an interesting way of exploration), we found that the answer is "YES", and the better policies are in fact located very far from the clipped space. We show that PPO is insufficient in "off-policyness", according to an off-policy metric called DEON. Our algorithm explores in a much larger policy space than PPO, and it maximizes the Conservative Policy Iteration (CPI) objective better than PPO during training. To the best of our knowledge, all current PPO methods have the clipping operation and optimize in the clipped policy space. Our method is the first of this kind, which advances the understanding of CPI optimization and policy gradient methods. Code is available at https://github.com/raincchio/P3O.

PDF Details DOI

AAAI Conference 2019 Short Paper

A Multi-Task Learning Framework for Abstractive Text Summarization

  • Yao Lu
  • Linqing Liu
  • Zhile Jiang
  • Min Yang
  • Randy Goebel

We propose a Multi-task learning approach for Abstractive Text Summarization (MATS), motivated by the fact that humans have no difficulty performing such task because they have the capabilities of multiple domains. Specifically, MATS consists of three components: (i) a text categorization model that learns rich category-specific text representations using a bi-LSTM encoder; (ii) a syntax labeling model that learns to improve the syntax-aware LSTM decoder; and (iii) an abstractive text summarization model that shares its encoder and decoder with the text categorization and the syntax labeling tasks, respectively. In particular, the abstractive text summarization model enjoys significant benefit from the additional text categorization and syntax knowledge. Our experimental results show that MATS outperforms the competitors. 1

PDF Details

TIST Journal 2015 Journal Article

Recognition of Patient-Related Named Entities in Noisy Tele-Health Texts

  • Mi-Young Kim
  • Ying Xu
  • Osmar R. Zaiane
  • Randy Goebel

We explore methods for effectively extracting information from clinical narratives that are captured in a public health consulting phone service called HealthLink. Our research investigates the application of state-of-the-art natural language processing and machine learning to clinical narratives to extract information of interest. The currently available data consist of dialogues constructed by nurses while consulting patients by phone. Since the data are interviews transcribed by nurses during phone conversations, they include a significant volume and variety of noise. When we extract the patient-related information from the noisy data, we have to remove or correct at least two kinds of noise: explicit noise, which includes spelling errors, unfinished sentences, omission of sentence delimiters, and variants of terms, and implicit noise, which includes non-patient information and patient's untrustworthy information. To filter explicit noise, we propose our own biomedical term detection/normalization method: it resolves misspelling, term variations, and arbitrary abbreviation of terms by nurses. In detecting temporal terms, temperature, and other types of named entities (which show patients’ personal information such as age and sex), we propose a bootstrapping-based pattern learning process to detect a variety of arbitrary variations of named entities. To address implicit noise, we propose a dependency path-based filtering method. The result of our denoising is the extraction of normalized patient information, and we visualize the named entities by constructing a graph that shows the relations between named entities. The objective of this knowledge discovery task is to identify associations between biomedical terms and to clearly expose the trends of patients’ symptoms and concern; the experimental results show that we achieve reasonable performance with our noise reduction methods.

Details DOI

IJCAI Conference 2009 Conference Paper

  • Shane Bergsma
  • Dekang Lin
  • Randy Goebel

Web-scale data has been used in a diverse range of language research. Most of this research has used web counts for only short, fixed spans of context. We present a unified view of using web counts for lexical disambiguation. Unlike previous approaches, our supervised and unsupervised systems combine information from multiple and overlapping segments of context. On the tasks of preposition selection and context-sensitive spelling correction, the supervised system reduces disambiguation error by 20-24% over the current state-of-the-art.

PDF Details

IJCAI Conference 2007 Conference Paper

  • Abhaya C. Nayak
  • Randy Goebel
  • Mehmet A. Orgun

Importance of contraction for belief change notwithstanding, literature on iterated belief change has by and large centered around the issue of iterated belief revision, ignoring the problem of iterated belief contraction. In this paper we examine iterated belief contraction in a principled way, starting with Qualified Insertion, a proposal by Hans Rott. We show that a judicious combination of Qualified Insertion with a well-known Factoring principle leads to what is arguably a pivotal principle of iterated belief contraction. We show that this principle is satisfied by the account of iterated belief contraction modelled by Lexicographic State Contraction, and outline its connection with Lexicographic Revision, Darwiche-Pearl's account of revision as well as Spohn's Ordinal ranking theory. Keywords: Belief Change, Information State Change, Iterated Belief Contraction.

PDF Details

UAI Conference 1990 Conference Paper

Integrating probabilistic, taxonomic and causal knowledge in abductive diagnosis

  • Dekang Lin
  • Randy Goebel

We propose an abductive diagnosis theory that integrates probabilistic, causal and taxonomic knowledge. Probabilistic knowledge allows us to select the most likely explanation; causal knowledge allows us to make reasonable independence assumptions; taxonomic knowledge allows causation to be modeled at different levels of detail, and allows observations be described in different levels of precision. Unlike most other approaches where a causal explanation is a hypothesis that one or more causative events occurred, we define an explanation of a set of observations to be an occurrence of a chain of causation events. These causation events constitute a scenario where all the observations are true. We show that the probabilities of the scenarios can be computed from the conditional probabilities of the causation events. Abductive reasoning is inherently complex even if only modest expressive power is allowed. However, our abduction algorithm is exponential only in the number of observations to be explained, and is polynomial in the size of the knowledge base. This contrasts with many other abduction procedures that are exponential in the size of the knowledge base.

Details

NMR Workshop 1989 Conference Paper

Non-Monotonic Reasoning in Temporal Domains: The Knowledge Independence Problem

  • Scott D. Goodwin
  • Randy Goebel

Abstract Much interest has been focused on nonmonotonic reasoning in temporal domains since Hanks and McDermott discovered that intuitive temporal representations give rise to the multiple extension problem. Here we consider nonmonotonic reasoning in temporal domains from the perspective of the Theorist hypothetical reasoning framework. We show how this framework can be applied to temporal reasoning in a simple and intuitive way to solve many of the problems posed in the recent literature, such as the Yale Shooting problem, Kautz's Vanishing Car problem, Haugh's Assassin problem, and Haugh's Robot problem. The basis of our solution to these problems is the characterization of the notion that the past is independent of the future ( temporal independence ) and the provision of two additional modes of reasoning: conditional explanation and prediction. The problem of representing and reasoning about temporal independence is an instance of a more general problem which we call the knowledge independence problem. In this paper, we provide a preliminary definition of the knowledge independence problem; we leave to future work further development of the obvious connections with statistical independence. Using our preliminary definition, we show how to represent and reason about temporal independence and how this solves many temporal reasoning problems.

Details