Many real-world applications produce networked data such as the world-wide web (hypertext documents connected via hyperlinks), social networks (for example, people connected by friendship links), communication networks (computers connected via communication links) and biological networks (for example, protein interaction networks). A recent focus in machine learning research has been to extend traditional machine learning classification techniques to classify nodes in such networks. In this article, we provide a brief introduction to this area of research and how it has progressed during the past decade. We introduce four of the most widely used inference algorithms for classifying networked data and empirically compare them on both synthetic and real-world data.

/pdf/collective-classification-in-network-data-ao4inwtwyv.pdf

Collective Classification in Network Data

Introduction to linear and nonlinear programming

Knowledge graph (KG) embedding is to embed components of a KG including entities and relations into continuous vector spaces, so as to simplify the manipulation while preserving the inherent structure of the KG. It can benefit a variety of downstream tasks such as KG completion and relation extraction, and hence has quickly gained massive attention. In this article, we provide a systematic review of existing techniques, including not only the state-of-the-arts but also those with latest trends. Particularly, we make the review based on the type of information used in the embedding task. Techniques that conduct embedding using only facts observed in the KG are first introduced. We describe the overall framework, specific model design, typical training procedures, as well as pros and cons of such techniques. After that, we discuss techniques that further incorporate additional information besides facts. We focus specifically on the use of entity types, relation paths, textual descriptions, and logical rules. Finally, we briefly introduce how KG embedding can be applied to and benefit a wide variety of downstream tasks such as KG completion, relation extraction, question answering, and so forth.

Knowledge Graph Embedding: A Survey of Approaches and Applications

Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these models are not aligned with their users. In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback. Starting with a set of labeler-written prompts and prompts submitted through the OpenAI API, we collect a dataset of labeler demonstrations of the desired model behavior, which we use to fine-tune GPT-3 using supervised learning. We then collect a dataset of rankings of model outputs, which we use to further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT. In human evaluations on our prompt distribution, outputs from the 1.3B parameter InstructGPT model are preferred to outputs from the 175B GPT-3, despite having 100x fewer parameters. Moreover, InstructGPT models show improvements in truthfulness and reductions in toxic output generation while having minimal performance regressions on public NLP datasets. Even though InstructGPT still makes simple mistakes, our results show that fine-tuning with human feedback is a promising direction for aligning language models with human intent.

Training language models to follow instructions with human feedback

Recent years have witnessed a proliferation of large-scale knowledge bases, including Wikipedia, Freebase, YAGO, Microsoft's Satori, and Google's Knowledge Graph. To increase the scale even further, we need to explore automatic methods for constructing knowledge bases. Previous approaches have primarily focused on text-based extraction, which can be very noisy. Here we introduce Knowledge Vault, a Web-scale probabilistic knowledge base that combines extractions from Web content (obtained via analysis of text, tabular data, page structure, and human annotations) with prior knowledge derived from existing knowledge repositories. We employ supervised machine learning methods for fusing these distinct information sources. The Knowledge Vault is substantially bigger than any previously published structured knowledge repository, and features a probabilistic inference system that computes calibrated probabilities of fact correctness. We report the results of multiple studies that explore the relative utility of the different information sources and extraction methods.

/pdf/knowledge-vault-a-web-scale-approach-to-probabilistic-23hsir1ibs.pdf

Knowledge vault: a web-scale approach to probabilistic knowledge fusion

Over the past few years, massive amounts of world knowledge have been accumulated in publicly available knowledge bases, such as Freebase, NELL, and YAGO. Yet despite their seemingly huge size, these knowledge bases are greatly incomplete. For example, over 70% of people included in Freebase have no known place of birth, and 99% have no known ethnicity. In this paper, we propose a way to leverage existing Web-search-based question-answering technology to fill in the gaps in knowledge bases in a targeted way. In particular, for each entity attribute, we learn the best set of queries to ask, such that the answer snippets returned by the search engine are most likely to contain the correct value for that attribute. For example, if we want to find Frank Zappa's mother, we could ask the query `who is the mother of Frank Zappa'. However, this is likely to return `The Mothers of Invention', which was the name of his band. Our system learns that it should (in this case) add disambiguating terms, such as Zappa's place of birth, in order to make it more likely that the search results contain snippets mentioning his mother. Our system also learns how many different queries to ask for each attribute, since in some cases, asking too many can hurt accuracy (by introducing false positives). We discuss how to aggregate candidate answers across multiple queries, ultimately returning probabilistic predictions for possible values for each attribute. Finally, we evaluate our system and show that it is able to extract a large number of facts with high confidence.

/pdf/knowledge-base-completion-via-search-based-question-2teaco44zg.pdf

Knowledge base completion via search-based question answering

Many real-life applications depend on databases automatically curated from unstructured sources through imperfect structure extraction tools. Such databases are best treated as imprecise representations of multiple extraction possibli-ties. State-of-the-art statistical models of extraction provide a sound probability distribution over extractions but are not easy to represent and query in a relational framework. In this paper we address the challenge of approximating such distributions as imprecise data models. In particular, we investigate a model that captures both row-level and column-level uncertainty and show that this representation provides significantly better approximation compared to models that use only row or only column level uncertainty. We present efficient algorithms for finding the best approximating parameters for such a model: our algorithm exploits the structure of the model to avoid enumerating the exponential number of extraction possibilities.

/pdf/creating-probabilistic-databases-from-information-extraction-5b56imrdds.pdf

Creating probabilistic databases from information extraction models

A system and method for managing group policy objects in a network, including interfaces that allow access by programs or a user interface component to functions of a group policy management console that performs management tasks on group policy objects and other related objects. The interfaces abstract the underlying data storage and retrieval, thereby facilitating searching for objects, and providing the ability to delegate, view, change and permissions on those objects, and check and save those permissions. Modeling and other test simulations are facilitated by other interfaces. Other interfaces provide dynamic and interactive features, such as to convey progress and rich status messages, and allow canceling of an ongoing operation. Still other interfaces provide methods for operating on group policy related data, including group policy object backup, restore, import, copy and create methods, and methods for linking group policy objects to scope of management objects.

Interfaces and methods for group policy management

We present the design of a system for assembling a table from a few example rows by harnessing the huge corpus of information-rich but unstructured lists on the web. We developed a totally unsupervised end to end approach which given the sample query rows --- (a) retrieves HTML lists relevant to the query from a pre-indexed crawl of web lists, (b) segments the list records and maps the segments to the query schema using a statistical model, (c) consolidates the results from multiple lists into a unified merged table, (d) and presents to the user the consolidated records ranked by their estimated membership in the target relation.The key challenges in this task include construction of new rows from very few examples, and an abundance of noisy and irrelevant lists that swamp the consolidation and ranking of rows. We propose modifications to statistical record segmentation models, and present novel consolidation and ranking techniques that can process input tables of arbitrary schema without requiring any human supervision.Experiments with Wikipedia target tables and 16 million unstructured lists show that even with just three sample rows, our system is very effective at recreating Wikipedia tables, with a mean runtime of around 20s.

/pdf/answering-table-augmentation-queries-from-unstructured-lists-1uiyrnukmp.pdf

Answering table augmentation queries from unstructured lists on the web

The variable forms of clinical complaints, findings and time interval of presentation in 27 cases of mucormycosis have been described, which were encountered over a span of 8 years. The previous concept about this fungal infection attacking chronic, debilitated, immunocompromised patients does not appear to hold true. Seven of the 27 patients (22.2%) did not reveal any predisposing factors and their outcome of 42.9% survival seems to be poorer than the total outcome (66.7%). 'Chronic form' of disease presentation, the definition of which is still not delineated, was encountered in four patients (14.8%). Again, the outcome was not significantly different from the total survival. Burr-hole tap of an intracranial abscess revealing mucor in a 2-month-old infant has been described. Even in the present era, extranasal exenteration of sinuses along with disfiguring orbital exenteration is required to ensure satisfactory surgical debridement. Control of the underlying predisposing illness, along with the aggressive surgical debridement and the parenteral administration of amphotericin B, remains the treatment essentials even today.

Rahul Gupta

Papers

Knowledge base completion via search-based question answering

Creating probabilistic databases from information extraction models

Interfaces and methods for group policy management

Answering table augmentation queries from unstructured lists on the web

Rhinocerebral mucormycosis: the disease spectrum in 27 patients.