Michele Banko

Bio: Michele Banko is an academic researcher from Cornell University. The author has contributed to research in topics: Information extraction & Automatic summarization. The author has an hindex of 21, co-authored 28 publications receiving 5662 citations. Previous affiliations of Michele Banko include University of Washington & Johns Hopkins University.

Open information extraction from the web

Abstract: Traditionally, Information Extraction (IE) has focused on satisfying precise, narrow, pre-specified requests from small homogeneous corpora (e.g., extract the location and time of seminars from a set of announcements). Shifting to a new domain requires the user to name the target relations and to manually create new extraction rules or hand-tag new training examples. This manual labor scales linearly with the number of target relations. This paper introduces Open IE (OIE), a new extraction paradigm where the system makes a single data-driven pass over its corpus and extracts a large set of relational tuples without requiring any human input. The paper also introduces TEXTRUNNER, a fully implemented, highly scalable OIE system where the tuples are assigned a probability and indexed to support efficient extraction and exploration via user queries. We report on experiments over a 9,000,000 Web page corpus that compare TEXTRUNNER with KNOWITALL, a state-of-the-art Web IE system. TEXTRUNNER achieves an error reduction of 33% on a comparable set of extractions. Furthermore, in the amount of time it takes KNOWITALL to perform extraction for a handful of pre-specified relations, TEXTRUNNER extracts a far broader set of facts reflecting orders of magnitude more relations, discovered on the fly. We report statistics on TEXTRUNNER's 11,000,000 highest probability tuples, and show that they contain over 1,000,000 concrete facts and over 6,500,000 more abstract assertions.

Scaling to Very Very Large Corpora for Natural Language Disambiguation

Abstract: The amount of readily available on-line text has reached hundreds of billions of words and continues to grow. Yet for most core natural language tasks, algorithms continue to be optimized, tested and compared after training on corpora consisting of only one million words or less. In this paper, we evaluate the performance of different learning methods on a prototypical natural language disambiguation task, confusion set disambiguation, when trained on orders of magnitude more labeled data than has previously been used. We are fortunate that for this particular application, correctly labeled training data is free. Since this will often not be the case, we examine methods for effectively exploiting very large corpora when labeled data comes at a cost.

Open information extraction from the web

Abstract: To implement open information extraction, a new extraction paradigm has been developed in which a system makes a single data-driven pass over a corpus of text, extracting a large set of relational tuples without requiring any human input. Using training data, a Self-Supervised Learner employs a parser and heuristics to determine criteria that will be used by an extraction classifier (or other ranking model) for evaluating the trustworthiness of candidate tuples that have been extracted from the corpus of text, by applying heuristics to the corpus of text. The classifier retains tuples with a sufficiently high probability of being trustworthy. A redundancy-based assessor assigns a probability to each retained tuple to indicate a likelihood that the retained tuple is an actual instance of a relationship between a plurality of objects comprising the retained tuple. The retained tuples comprise an extraction graph that can be queried for information.

An Analysis of the AskMSR Question-Answering System

Abstract: We describe the architecture of the AskMSR question answering system and systematically evaluate contributions of different system components to accuracy. The system differs from most question answering systems in its dependency on data redundancy rather than sophisticated linguistic analyses of either questions or candidate answers. Because a wrong answer is often worse than no answer, we also explore strategies for predicting when the question answering system is likely to give an incorrect answer.

The Tradeoffs Between Open and Traditional Relation Extraction

Abstract: Traditional Information Extraction (IE) takes a relation name and hand-tagged examples of that relation as input. Open IE is a relationindependent extraction paradigm that is tailored to massive and heterogeneous corpora such as the Web. An Open IE system extracts a diverse set of relational tuples from text without any relation-specific input. How is Open IE possible? We analyze a sample of English sentences to demonstrate that numerous relationships are expressed using a compact set of relation-independent lexico-syntactic patterns, which can be learned by an Open IE system. What are the tradeoffs between Open IE and traditional IE? We consider this question in the context of two tasks. First, when the number of relations is massive, and the relations themselves are not pre-specified, we argue that Open IE is necessary. We then present a new model for Open IE called O-CRF and show that it achieves increased precision and nearly double the recall than the model employed by TEXTRUNNER, the previous stateof-the-art Open IE system. Second, when the number of target relations is small, and their names are known in advance, we show that O-CRF is able to match the precision of a traditional extraction system, though at substantially lower recall. Finally, we show how to combine the two types of systems into a hybrid that achieves higher precision than a traditional extractor, with comparable recall.

SQuAD: 100,000+ Questions for Machine Comprehension of Text

Abstract: We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research. The dataset is freely available at this https URL

SQuAD: 100,000+ Questions for Machine Comprehension of Text

Abstract: We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research. The dataset is freely available at this https URL

Speech and Language Processing

Abstract: is one of the most recognizablecharacters in 20th century cinema. HAL is an artificial agent capable of such advancedlanguage behavior as speaking and understanding English, and at a crucial moment inthe plot, even reading lips. It is now clear that HAL’s creator, Arthur C. Clarke, wasa little optimistic in predicting when an artificial agent such as HAL would be avail-able. But just how far off was he? What would it take to create at least the language-relatedpartsofHAL?WecallprogramslikeHALthatconversewithhumansinnatural

Distant supervision for relation extraction without labeled data

Abstract: Modern models of relation extraction for tasks like ACE are based on supervised learning of relations from small hand-labeled corpora. We investigate an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size. Our experiments use Freebase, a large semantic database of several thousand relations, to provide distant supervision. For each pair of entities that appears in some Freebase relation, we find all sentences containing those entities in a large unlabeled corpus and extract textual features to train a relation classifier. Our algorithm combines the advantages of supervised IE (combining 400,000 noisy pattern features in a probabilistic classifier) and unsupervised IE (extracting large numbers of relations from large corpora of any domain). Our model is able to extract 10,000 instances of 102 relations at a precision of 67.6%. We also analyze feature performance, showing that syntactic parse features are particularly helpful for relations that are ambiguous or lexically distant in their expression.

From frequency to meaning: vector space models of semantics

Abstract: Computers understand very little of the meaning of human language. This profoundly limits our ability to give instructions to computers, the ability of computers to explain their actions to us, and the ability of computers to analyse and process text. Vector space models (VSMs) of semantics are beginning to address these limits. This paper surveys the use of VSMs for semantic processing of text. We organize the literature on VSMs according to the structure of the matrix in a VSM. There are currently three broad classes of VSMs, based on term-document, word-context, and pair-pattern matrices, yielding three classes of applications. We survey a broad range of applications in these three categories and we take a detailed look at a specific open source project in each category. Our goal in this survey is to show the breadth of applications of VSMs for semantics, to provide a new perspective on VSMs for those who are already familiar with the area, and to provide pointers into the literature for those who are less familiar with the field.