Collaborating Authors


David Webb sounds off on 'hypocrisy' of Dick Durbin using word 'token' to criticize Tim Scott

FOX News

Senate Minority Whip Dick Durbin apologizes to Sen. Tim Scott for the remark on the Republican police reform plan. Fox Nation host David Webb on Thursday blasted Senate Minority Whip Dick Durbin for calling Sen. Tim Scott's role in crafting the GOP-led police reform bill a "token approach." "I don't know what's in Dick Durbin's heart," Webb told "Fox & Friends." "But it's the hypocrisy that if anyone had used that word'token,' which is a legitimate word in the English language, in any way, pointed toward blacks from the right, they [the left] would have gone crazy. They would have been protesting. They would have been claiming the egregious nature of its use."

Trump Lashes Out at Spell-Check for Treating Him Unfairly

The New Yorker

WASHINGTON (The Borowitz Report)--Accusing it of treating him "very unfairly," Donald Trump lashed out on Wednesday at the widely used spelling tool spell-check. "Almost every time I type a word, spell-check puts a red squiggly line under it," he tweeted. "It never put a red squiggly line under Obama's words." "Spell-check is rigged against conservatives," he charged. Trump accused spell-check of infringing on his First Amendment rights by interfering with what he called "freedom of spelling."

Visual Question Answering Using Semantic Information from Image Descriptions Artificial Intelligence

Visual question answering (VQA) is a task that requires AI systems to display multi-modal understanding. A system must be able to reason over the question being asked as well as the image itself to determine reasonable answers to the questions posed. In many cases, simply reasoning over the image itself and the question is not enough to achieve good performance. As an aid of the task, other than region based visual information and natural language questions, external textual knowledge extracted from images can also be used to generate correct answers for questions. Considering these, we propose a deep neural network model that uses an attention mechanism which utilizes image features, the natural language question asked and semantic knowledge extracted from the image to produce open-ended answers for the given questions. The combination of image features and contextual information about the image bolster a model to more accurately respond to questions and potentially do so with less required training data. We evaluate our proposed architecture on a VQA task against a strong baseline and show that our method achieves excellent results on this task.

Spatial Priming for Detecting Human-Object Interactions Artificial Intelligence

The relative spatial layout of a human and an object is an important cue for determining how they interact. However, until now, spatial layout has been used just as side-information for detecting human-object interactions (HOIs). In this paper, we present a method for exploiting this spatial layout information for detecting HOIs in images. The proposed method consists of a layout module which primes a visual module to predict the type of interaction between a human and an object. The visual and layout modules share information through lateral connections at several stages. The model uses predictions from the layout module as a prior to the visual module and the prediction from the visual module is given as the final output. It also incorporates semantic information about the object using word2vec vectors. The proposed model reaches an mAP of 24.79% for HICO-Det dataset which is about 2.8% absolute points higher than the current state-of-the-art.

Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision Artificial Intelligence

We created this CORD-19-NER dataset with comprehensive named entity recognition (NER) on the COVID-19 Open Research Dataset Challenge (CORD-19) corpus (2020- 03-13). This CORD-19-NER dataset covers 74 fine-grained named entity types. It is automatically generated by combining the annotation results from four sources: (1) pre-trained NER model on 18 general entity types from Spacy, (2) pre-trained NER model on 18 biomedical entity types from SciSpacy, (3) knowledge base (KB)-guided NER model on 127 biomedical entity types with our distantly-supervised NER method, and (4) seed-guided NER model on 8 new entity types (specifically related to the COVID-19 studies) with our weakly-supervised NER method. We hope this dataset can help the text mining community build downstream applications. We also hope this dataset can bring insights for the COVID- 19 studies, both on the biomedical side and on the social side.

Software Language Comprehension using a Program-Derived Semantic Graph Artificial Intelligence

Traditional code transformation structures, such as an abstract syntax tree, may have limitations in their ability to extract semantic meaning from code. Others have begun to work on this issue, such as the state-of-the-art Aroma system and its simplified parse tree (SPT). Continuing this research direction, we present a new graphical structure to capture semantics from code using what we refer to as a program-derived semantic graph (PSG). The principle behind the PSG is to provide a single structure that can capture program semantics at many levels of granularity. Thus, the PSG is hierarchical in nature. Moreover, because the PSG may have cycles due to dependencies in semantic layers, it is a graph, not a tree. In this paper, we describe the PSG and its fundamental structural differences to the Aroma's SPT. Although our work in the PSG is in its infancy, our early results indicate it is a promising new research direction to explore to automatically extract program semantics.

Common-Knowledge Concept Recognition for SEVA Machine Learning

We build a common-knowledge concept recognition system for a Systems Engineer's Virtual Assistant (SEVA) which can be used for downstream tasks such as relation extraction, knowledge graph construction, and question-answering. The problem is formulated as a token classification task similar to named entity extraction. With the help of a domain expert and text processing methods, we construct a dataset annotated at the word-level by carefully defining a labelling scheme to train a sequence model to recognize systems engineering concepts. We use a pre-trained language model and fine-tune it with the labeled dataset of concepts. In addition, we also create some essential datasets for information such as abbreviations and definitions from the systems engineering domain. Finally, we construct a simple knowledge graph using these extracted concepts along with some hyponym relations.

Joint Event Extraction along Shortest Dependency Paths using Graph Convolutional Networks Artificial Intelligence

Event extraction (EE) is one of the core information extraction tasks, whose purpose is to automatically identify and extract information about incidents and their actors from texts. This may be beneficial to several domains such as knowledge bases, question answering, information retrieval and summarization tasks, to name a few. The problem of extracting event information from texts is longstanding and usually relies on elaborately designed lexical and syntactic features, which, however, take a large amount of human effort and lack generalization. More recently, deep neural network approaches have been adopted as a means to learn underlying features automatically. However, existing networks do not make full use of syntactic features, which play a fundamental role in capturing very long-range dependencies. Also, most approaches extract each argument of an event separately without considering associations between arguments which ultimately leads to low efficiency, especially in sentences with multiple events. To address the two above-referred problems, we propose a novel joint event extraction framework that aims to extract multiple event triggers and arguments simultaneously by introducing shortest dependency path (SDP) in the dependency graph. We do this by eliminating irrelevant words in the sentence, thus capturing long-range dependencies. Also, an attention-based graph convolutional network is proposed, to carry syntactically related information along the shortest paths between argument candidates that captures and aggregates the latent associations between arguments; a problem that has been overlooked by most of the literature. Our results show a substantial improvement over state-of-the-art methods.

Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings Machine Learning

In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT) on medical notes from the MIMIC-III hospital dataset, and quantify potential disparities using two approaches. First, we identify dangerous latent relationships that are captured by the contextual word embeddings using a fill-in-the-blank method with text from real clinical notes and a log probability bias score quantification. Second, we evaluate performance gaps across different definitions of fairness on over 50 downstream clinical prediction tasks that include detection of acute and chronic conditions. We find that classifiers trained from BERT representations exhibit statistically significant differences in performance, often favoring the majority group with regards to gender, language, ethnicity, and insurance status. Finally, we explore shortcomings of using adversarial debiasing to obfuscate subgroup information in contextual word embeddings, and recommend best practices for such deep embedding models in clinical settings.

Ecological Semantics: Programming Environments for Situated Language Understanding Artificial Intelligence

Large-scale natural language understanding (NLU) systems have made impressive progress: they can be applied flexibly across a variety of tasks, and employ minimal structural assumptions. However, extensive empirical research has shown this to be a double-edged sword, coming at the cost of shallow understanding: inferior generalization, grounding and explainability. Grounded language learning approaches offer the promise of deeper understanding by situating learning in richer, more structured training environments, but are limited in scale to relatively narrow, predefined domains. How might we enjoy the best of both worlds: grounded, general NLU? Following extensive contemporary cognitive science, we propose treating environments as ``first-class citizens'' in semantic representations, worthy of research and development in their own right. Importantly, models should also be partners in the creation and configuration of environments, rather than just actors within them, as in existing approaches. To do so, we argue that models must begin to understand and program in the language of affordances (which define possible actions in a given situation) both for online, situated discourse comprehension, as well as large-scale, offline common-sense knowledge mining. To this end we propose an environment-oriented ecological semantics, outlining theoretical and practical approaches towards implementation. We further provide actual demonstrations building upon interactive fiction programming languages.