Wlodek Zadrozny

Seethalakshmi Gopalakrishnan, Luciana Garbayo, Wlodek Zadrozny

This study explores the potential of natural language models, including large language models, to extract causal relations from medical texts, specifically from Clinical Practice Guidelines (CPGs). The outcomes causality extraction from Clinical Practice Guidelines for gestational diabetes are presented, marking a first in the field. We report on a set of experiments using variants of BERT (BioBERT, DistilBERT, and BERT) and using Large Language Models (LLMs), namely GPT-4 and LLAMA2. Our experiments show that BioBERT performed better than other models, including the Large Language Models, with an average F1-score of 0.72. GPT-4 and LLAMA2 results show similar performance but less consistency. We also release the code and an annotated a corpus of causal statements within the Clinical Practice Guidelines for gestational diabetes.

Swapn Shah, Wlodek Zadrozny

The unification of symbolic reasoning and neural networks remains a central challenge in artificial intelligence. Symbolic systems offer reliability and interpretability but lack scalability, while neural networks provide learning capabilities but sacrifice transparency. Tensor Logic, proposed by Domingos, suggests that logical rules and Einstein summation are mathematically equivalent, offering a principled path toward unification. This paper provides empirical validation of this framework through three experiments. First, we demonstrate the equivalence between recursive Datalog rules and iterative tensor contractions by computing the transitive closure of a biblical genealogy graph containing 1,972 individuals and 1,727 parent-child relationships, converging in 74 iterations to discover 33,945 ancestor relationships. Second, we implement reasoning in embedding space by training a neural network with learnable transformation matrices, demonstrating successful zero-shot compositional inference on held-out queries. Third, we validate the Tensor Logic superposition construction on FB15k-237, a large-scale knowledge graph with 14,541 entities and 237 relations. Using Domingos's relation matrix formulation $R_r = E^\top A_r E$, we achieve MRR of 0.3068 on standard link prediction and MRR of 0.3346 on a compositional reasoning benchmark where direct edges are removed during training, demonstrating that matrix composition enables multi-hop inference without direct training examples.

Sean Gallagher, Wlodek Zadrozny, Walid Shalaby et al.

The objective of the project is to design and run a system similar to Watson, designed to answer Jeopardy questions. In the course of a semester, we developed an open source question answering system using the Indri, Lucene, Bing and Google search engines, Apache UIMA, Open- and CoreNLP, and Weka among additional modules. By the end of the semester, we achieved 18% accuracy on Jeopardy questions, and work has not stopped since then.

Victor Zitian Chen, Felipe Montano-Campos, Wlodek Zadrozny et al.

The volume of scientific publications in organizational research becomes exceedingly overwhelming for human researchers who seek to timely extract and review knowledge. This paper introduces natural language processing (NLP) models to accelerate the discovery, extraction, and organization of theoretical developments (i.e., hypotheses) from social science publications. We illustrate and evaluate NLP models in the context of a systematic review of stakeholder value constructs and hypotheses. Specifically, we develop NLP models to automatically 1) detect sentences in scholarly documents as hypotheses or not (Hypothesis Detection), 2) deconstruct the hypotheses into nodes (constructs) and links (causal/associative relationships) (Relationship Deconstruction ), and 3) classify the features of links in terms causality (versus association) and direction (positive, negative, versus nonlinear) (Feature Classification). Our models have reported high performance metrics for all three tasks. While our models are built in Python, we have made the pre-trained models fully accessible for non-programmers. We have provided instructions on installing and using our pre-trained models via an R Shiny app graphic user interface (GUI). Finally, we suggest the next paths to extend our methodology for computer-assisted knowledge synthesis.

Hossein Hematialam, Luciana Garbayo, Seethalakshmi Gopalakrishnan et al.

Using natural language processing tools, we investigate the differences of recommendations in medical guidelines for the same decision problem -- breast cancer screening. We show that these differences arise from knowledge brought to the problem by different medical societies, as reflected in the conceptual vocabularies used by the different groups of authors.The computational models we build and analyze agree with the near-peer epistemic model of expert disagreement proposed by Garbayo. Even though the article is a case study focused on one set of guidelines, the proposed methodology is broadly applicable. In addition to proposing a novel graph-based similarity model for comparing collections of documents, we perform an extensive analysis of the model performance. In a series of a few dozen experiments, in three broad categories, we show, at a very high statistical significance level of 3-4 standard deviations for our best models, that the high similarity between expert annotated model and our concept based, automatically created, computational models is not accidental. Our best model achieves roughly 70% similarity. We also describe possible extensions of this work.

Victor Zitian Chen, Felipe Montano-Campos, Wlodek Zadrozny

The scale and scope of scholarly articles today are overwhelming human researchers who seek to timely digest and synthesize knowledge. In this paper, we seek to develop natural language processing (NLP) models to accelerate the speed of extraction of relationships from scholarly papers in social sciences, identify hypotheses from these papers, and extract the cause-and-effect entities. Specifically, we develop models to 1) classify sentences in scholarly documents in business and management as hypotheses (hypothesis classification), 2) classify these hypotheses as causal relationships or not (causality classification), and, if they are causal, 3) extract the cause and effect entities from these hypotheses (entity extraction). We have achieved high performance for all the three tasks using different modeling techniques. Our approach may be generalizable to scholarly documents in a wide range of social sciences, as well as other types of textual materials.

Shafie Gholizadeh, Ketki Savle, Armin Seyeditabari et al.

While the strength of Topological Data Analysis has been explored in many studies on high dimensional numeric data, it is still a challenging task to apply it to text. As the primary goal in topological data analysis is to define and quantify the shapes in numeric data, defining shapes in the text is much more challenging, even though the geometries of vector spaces and conceptual spaces are clearly relevant for information retrieval and semantics. In this paper, we examine two different methods of extraction of topological features from text, using as the underlying representations of words the two most popular methods, namely word embeddings and TF-IDF vectors. To extract topological features from the word embedding space, we interpret the embedding of a text document as high dimensional time series, and we analyze the topology of the underlying graph where the vertices correspond to different embedding dimensions. For topological data analysis with the TF-IDF representations, we analyze the topology of the graph whose vertices come from the TF-IDF vectors of different blocks in the textual document. In both cases, we apply homological persistence to reveal the geometric structures under different distance resolutions. Our results show that these topological features carry some exclusive information that is not captured by conventional text mining methods. In our experiments we observe adding topological features to the conventional features in ensemble models improves the classification results (up to 5\%). On the other hand, as expected, topological features by themselves may be not sufficient for effective classification. It is an open problem to see whether TDA features from word embeddings might be sufficient, as they seem to perform within a range of few points from top results obtained with a linear support vector classifier.

Shafie Gholizadeh, Armin Seyeditabari, Wlodek Zadrozny

In recent years, topological data analysis has been utilized for a wide range of problems to deal with high dimensional noisy data. While text representations are often high dimensional and noisy, there are only a few work on the application of topological data analysis in natural language processing. In this paper, we introduce a novel algorithm to extract topological features from word embedding representation of text that can be used for text classification. Working on word embeddings, topological data analysis can interpret the embedding high-dimensional space and discover the relations among different embedding dimensions. We will use persistent homology, the most commonly tool from topological data analysis, for our experiment. Examining our topological algorithm on long textual documents, we will show our defined topological features may outperform conventional text mining features.

Sai Krishna Telukuntla, Aditya Kapri, Wlodek Zadrozny

In this paper, we detail our submission to the 2019, 7th year, BioASQ competition. We present our approach for Task-7b, Phase B, Exact Answering Task. These Question Answering (QA) tasks include Factoid, Yes/No, List Type Question answering. Our system is based on a contextual word embedding model. We have used a Bidirectional Encoder Representations from Transformers(BERT) based system, fined tuned for biomedical question answering task using BioBERT. In the third test batch set, our system achieved the highest MRR score for Factoid Question Answering task. Also, for List type question answering task our system achieved the highest recall score in the fourth test batch set. Along with our detailed approach, we present the results for our submissions, and also highlight identified downsides for our current approach and ways to improve them in our future experiments.

Armin Seyeditabari, Narges Tabari, Shafie Gholizadeh et al.

In recent years, emotion detection in text has become more popular due to its vast potential applications in marketing, political science, psychology, human-computer interaction, artificial intelligence, etc. In this work, we argue that current methods which are based on conventional machine learning models cannot grasp the intricacy of emotional language by ignoring the sequential nature of the text, and the context. These methods, therefore, are not sufficient to create an applicable and generalizable emotion detection methodology. Understanding these limitations, we present a new network based on a bidirectional GRU model to show that capturing more meaningful information from text can significantly improve the performance of these models. The results show significant improvement with an average of 26.8 point increase in F-measure on our test data and 38.6 increase on the totally new dataset.

Armin Seyeditabari, Narges Tabari, Shafie Gholizade et al.

Word embeddings are one of the most useful tools in any modern natural language processing expert's toolkit. They contain various types of information about each word which makes them the best way to represent the terms in any NLP task. But there are some types of information that cannot be learned by these models. Emotional information of words are one of those. In this paper, we present an approach to incorporate emotional information of words into these models. We accomplish this by adding a secondary training stage which uses an emotional lexicon and a psychological model of basic emotions. We show that fitting an emotional model into pre-trained word vectors can increase the performance of these models in emotional similarity metrics. Retrained models perform better than their original counterparts from 13% improvement for Word2Vec model, to 29% for GloVe vectors. This is the first such model presented in the literature, and although preliminary, these emotion sensitive models can open the way to increase performance in variety of emotion detection techniques.

Shafie Gholizadeh, Wlodek Zadrozny

Topological Data Analysis (TDA) is the collection of mathematical tools that capture the structure of shapes in data. Despite computational topology and computational geometry, the utilization of TDA in time series and signal processing is relatively new. In some recent contributions, TDA has been utilized as an alternative to the conventional signal processing methods. Specifically, TDA is been considered to deal with noisy signals and time series. In these applications, TDA is used to find the shapes in data as the main properties, while the other properties are assumed much less informative. In this paper, we will review recent developments and contributions where topological data analysis especially persistent homology has been applied to time series analysis, dynamical systems and signal processing. We will cover problem statements such as stability determination, risk analysis, systems behaviour, and predicting critical transitions in financial markets.

Armin Seyeditabari, Narges Tabari, Wlodek Zadrozny

In recent years, emotion detection in text has become more popular due to its vast potential applications in marketing, political science, psychology, human-computer interaction, artificial intelligence, etc. Access to a huge amount of textual data, especially opinionated and self-expression text also played a special role to bring attention to this field. In this paper, we review the work that has been done in identifying emotion expressions in text and argue that although many techniques, methodologies, and models have been created to detect emotion in text, there are various reasons that make these methods insufficient. Although, there is an essential need to improve the design and architecture of current systems, factors such as the complexity of human emotions, and the use of implicit and metaphorical language in expressing it, lead us to think that just re-purposing standard methodologies will not be enough to capture these complexities, and it is important to pay attention to the linguistic intricacies of emotion expression.

Wlodek Zadrozny, Luciana Garbayo

We introduce a new formal model -- based on the mathematical construct of sheaves -- for representing contradictory information in textual sources. This model has the advantage of letting us (a) identify the causes of the inconsistency; (b) measure how strong it is; (c) and do something about it, e.g. suggest ways to reconcile inconsistent advice. This model naturally represents the distinction between contradictions and disagreements. It is based on the idea of representing natural language sentences as formulas with parameters sitting on lattices, creating partial orders based on predicates shared by theories, and building sheaves on these partial orders with products of lattices as stalks. Degrees of disagreement are measured by the existence of global and local sections. Limitations of the sheaf approach and connections to recent work in natural language processing, as well as the topics of contextuality in physics, data fusion, topological data analysis and epistemology are also discussed.

Walid Shalaby, Wlodek Zadrozny, Hongxia Jin

Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these methods are limited to textual knowledge bases (e.g., Wikipedia). In this paper, we propose a novel and simple technique for integrating the knowledge about concepts from two large scale knowledge bases of different structure (Wikipedia and Probase) in order to learn concept representations. We adapt the efficient skip-gram model to seamlessly learn from the knowledge in Wikipedia text and Probase concept graph. We evaluate our concept embedding models on two tasks: (1) analogical reasoning, where we achieve a state-of-the-art performance of 91% on semantic analogies, (2) concept categorization, where we achieve a state-of-the-art performance on two benchmark datasets achieving categorization accuracy of 100% on one and 98% on the other. Additionally, we present a case study to evaluate our model on unsupervised argument type identification for neural semantic parsing. We demonstrate the competitive accuracy of our unsupervised method and its ability to better generalize to out of vocabulary entity mentions compared to the tedious and error prone methods which depend on gazetteers and regular expressions.

Walid Shalaby, BahaaEddin AlAila, Mohammed Korayem et al.

Online job boards are one of the central components of modern recruitment industry. With millions of candidates browsing through job postings everyday, the need for accurate, effective, meaningful, and transparent job recommendations is apparent more than ever. While recommendation systems are successfully advancing in variety of online domains by creating social and commercial value, the job recommendation domain is less explored. Existing systems are mostly focused on content analysis of resumes and job descriptions, relying heavily on the accuracy and coverage of the semantic analysis and modeling of the content in which case, they end up usually suffering from rigidity and the lack of implicit semantic relations that are uncovered from users' behavior and could be captured by Collaborative Filtering (CF) methods. Few works which utilize CF do not address the scalability challenges of real-world systems and the problem of cold-start. In this paper, we propose a scalable item-based recommendation system for online job recommendations. Our approach overcomes the major challenges of sparsity and scalability by leveraging a directed graph of jobs connected by multi-edges representing various behavioral and contextual similarity signals. The short lived nature of the items (jobs) in the system and the rapid rate in which new users and jobs enter the system make the cold-start a serious problem hindering CF methods. We address this problem by harnessing the power of deep learning in addition to user behavior to serve hybrid recommendations. Our technique has been leveraged by CareerBuilder.com which is one of the largest job boards in the world to generate high-quality recommendations for millions of users.

Wlodek Zadrozny, Hossein Hematialam, Luciana Garbayo

We introduce a formal distinction between contradictions and disagreements in natural language texts, motivated by the need to formally reason about contradictory medical guidelines. This is a novel and potentially very useful distinction, and has not been discussed so far in NLP and logic. We also describe a NLP system capable of automated finding contradictory medical guidelines; the system uses a combination of text analysis and information retrieval modules. We also report positive evaluation results on a small corpus of contradictory medical recommendations.

Hossein Hematialam, Wlodek Zadrozny

This paper advances the state of the art in text understanding of medical guidelines by releasing two new annotated clinical guidelines datasets, and establishing baselines for using machine learning to extract condition-action pairs. In contrast to prior work that relies on manually created rules, we report experiment with several supervised machine learning techniques to classify sentences as to whether they express conditions and actions. We show the limitations and possible extensions of this work on text mining of medical guidelines.

Walid Shalaby, Wlodek Zadrozny

Explicit concept space models have proven efficacy for text representation in many natural language and text mining applications. The idea is to embed textual structures into a semantic space of concepts which captures the main ideas, objects, and the characteristics of these structures. The so called Bag of Concepts (BoC) representation suffers from data sparsity causing low similarity scores between similar texts due to low concept overlap. To address this problem, we propose two neural embedding models to learn continuous concept vectors. Once they are learned, we propose an efficient vector aggregation method to generate fully continuous BoC representations. We evaluate our concept embedding models on three tasks: 1) measuring entity semantic relatedness and ranking where we achieve 1.6% improvement in correlation scores, 2) dataless concept categorization where we achieve state-of-the-art performance and reduce the categorization error rate by more than 5% compared to five prior word and entity embedding models, and 3) dataless document classification where our models outperform the sparse BoC representations. In addition, by exploiting our efficient linear time vector aggregation method, we achieve better accuracy scores with much less concept dimensions compared to previous BoC densification methods which operate in polynomial time and require hundreds of dimensions in the BoC representation.

Walid Shalaby, Wlodek Zadrozny

With the ever increasing number of filed patent applications every year, the need for effective and efficient systems for managing such tremendous amounts of data becomes inevitably important. Patent Retrieval (PR) is considered the pillar of almost all patent analysis tasks. PR is a subfield of Information Retrieval (IR) which is concerned with developing techniques and methods that effectively and efficiently retrieve relevant patent documents in response to a given search request. In this paper we present a comprehensive review on PR methods and approaches. It is clear that, recent successes and maturity in IR applications such as Web search cannot be transferred directly to PR without deliberate domain adaptation and customization. Furthermore, state-of-the-art performance in automatic PR is still around average in terms of recall. These observations motivate the need for interactive search tools which provide cognitive assistance to patent professionals with minimal effort. These tools must also be developed in hand with patent professionals considering their practices and expectations. We additionally touch on related tasks to PR such as patent valuation, litigation, licensing, and highlight potential opportunities and open directions for computational scientists in these domains.

Walid Shalaby, Wlodek Zadrozny

Mined Semantic Analysis (MSA) is a novel concept space model which employs unsupervised learning to generate semantic representations of text. MSA represents textual structures (terms, phrases, documents) as a Bag of Concepts (BoC) where concepts are derived from concept rich encyclopedic corpora. Traditional concept space models exploit only target corpus content to construct the concept space. MSA, alternatively, uncovers implicit relations between concepts by mining for their associations (e.g., mining Wikipedia's "See also" link graph). We evaluate MSA's performance on benchmark datasets for measuring semantic relatedness of words and sentences. Empirical results show competitive performance of MSA compared to prior state-of-the-art methods. Additionally, we introduce the first analytical study to examine statistical significance of results reported by different semantic relatedness methods. Our study shows that, the nuances of results across top performing methods could be statistically insignificant. The study positions MSA as one of state-of-the-art methods for measuring semantic relatedness, besides the inherent interpretability and simplicity of the generated semantic representation.