Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.

/pdf/teaching-machines-to-read-and-comprehend-381zg0jrq1.pdf

Teaching machines to read and comprehend

In this paper, we train a semantic parser that scales up to Freebase. Instead of relying on annotated logical forms, which is especially expensive to obtain at large scale, we learn from question-answer pairs. The main challenge in this setting is narrowing down the huge number of possible logical predicates for a given question. We tackle this problem in two ways: First, we build a coarse mapping from phrases to predicates using a knowledge base and a large text corpus. Second, we use a bridging operation to generate additional predicates based on neighboring predicates. On the dataset of Cai and Yates (2013), despite not having annotated logical forms, our system outperforms their state-of-the-art parser. Additionally, we collected a more realistic and challenging dataset of question-answer pairs and improves over a natural baseline.

/pdf/semantic-parsing-on-freebase-from-question-answer-pairs-y7fve0pp42.pdf

Semantic Parsing on Freebase from Question-Answer Pairs

Open Information Extraction (IE) is the task of extracting assertions from massive corpora without requiring a pre-specified vocabulary. This paper shows that the output of state-of-the-art Open IE systems is rife with uninformative and incoherent extractions. To overcome these problems, we introduce two simple syntactic and lexical constraints on binary relations expressed by verbs. We implemented the constraints in the ReVerb Open IE system, which more than doubles the area under the precision-recall curve relative to previous extractors such as TextRunner and woepos. More than 30% of ReVerb's extractions are at precision 0.8 or higher---compared to virtually none for earlier systems. The paper concludes with a detailed analysis of ReVerb's errors, suggesting directions for future work.

/pdf/identifying-relations-for-open-information-extraction-34r41253j3.pdf

Identifying Relations for Open Information Extraction

The human brain has some capabilities that the brains of other animals lack. It is to these distinctive capabilities that our species owes its dominant position. Other animals have stronger muscles or sharper claws, but we have cleverer brains. If machine brains one day come to surpass human brains in general intelligence, then this new superintelligence could become very powerful. As the fate of the gorillas now depends more on us humans than on the gorillas themselves, so the fate of our species then would come to depend on the actions of the machine superintelligence. But we have one advantage: we get to make the first move. Will it be possible to construct a seed AI or otherwise to engineer initial conditions so as to make an intelligence explosion survivable? How could one achieve a controlled detonation? To get closer to an answer to this question, we must make our way through a fascinating landscape of topics and considerations. Read the book and learn about oracles, genies, singletons; about boxing methods, tripwires, and mind crime; about humanity's cosmic endowment and differential technological development; indirect normativity, instrumental convergence, whole brain emulation and technology couplings; Malthusian economics and dystopian evolution; artificial intelligence, and biological cognitive enhancement, and collective intelligence. This profoundly ambitious and original book picks its way carefully through a vast tract of forbiddingly difficult intellectual terrain. Yet the writing is so lucid that it somehow makes it all seem easy. After an utterly engrossing journey that takes us to the frontiers of thinking about the human condition and the future of intelligent life, we find in Nick Bostrom's work nothing less than a reconceptualization of the essential task of our time.

Superintelligence: Paths, Dangers, Strategies

Relation triples produced by open domain information extraction (open IE) systems are useful for question answering, inference, and other IE tasks. Traditionally these are extracted using a large set of patterns; however, this approach is brittle on out-of-domain text and long-range dependencies, and gives no insight into the substructure of the arguments. We replace this large pattern set with a few patterns for canonically structured sentences, and shift the focus to a classifier which learns to extract self-contained clauses from longer sentences. We then run natural logic inference over these short clauses to determine the maximally specific arguments for each candidate triple. We show that our approach outperforms a state-of-the-art open IE system on the end-to-end TAC-KBP 2013 Slot Filling task.

/pdf/leveraging-linguistic-structure-for-open-domain-information-cxpwf6jduy.pdf

Leveraging Linguistic Structure For Open Domain Information Extraction

Entity linking systems link noun-phrase mentions in text to their corresponding Wikipedia articles. However, NLP applications would gain from the ability to detect and type all entities mentioned in text, including the long tail of entities not prominent enough to have their own Wikipedia articles. In this paper we show that once the Wikipedia entities mentioned in a corpus of textual assertions are linked, this can further enable the detection and fine-grained typing of the unlinkable entities. Our proposed method for detecting unlinkable entities achieves 24% greater accuracy than a Named Entity Recognition baseline, and our method for fine-grained typing is able to propagate over 1,000 types from linked Wikipedia entities to unlinkable entities. Detection and typing of unlinkable entities can increase yield for NLP applications such as typed question answering.

/pdf/no-noun-phrase-left-behind-detecting-and-typing-unlinkable-rqmr9ukvo5.pdf

No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities

This paper investigates entity linking over millions of high-precision extractions from a corpus of 500 million Web documents, toward the goal of creating a useful knowledge base of general facts. This paper is the first to report on entity linking over this many extractions, and describes new opportunities (such as corpus-level features) and challenges we found when entity linking at Web scale. We present several techniques that we developed and also lessons that we learned. We envision a future where information extraction and entity linking are paired to automatically generate knowledge bases with billions of assertions over millions of linked entities.

/pdf/entity-linking-at-web-scale-33cuids56e.pdf

Entity Linking at Web Scale

We introduce an entity-centric search experience, called Active Objects, in which entity-bearing queries are paired with actions that can be performed on the entities. For example, given a query for a specific flashlight, we aim to present actions such as reading reviews, watching demo videos, and finding the best price online. In an annotation study conducted over a random sample of user query sessions, we found that a large proportion of queries in query logs involve actions on entities, calling for an automatic approach to identifying relevant actions for entity-bearing queries. In this paper, we pose the problem of finding actions that can be performed on entities as the problem of probabilistic inference in a graphical model that captures how an entity bearing query is generated. We design models of increasing complexity that capture latent factors such as entity type and intended actions that determine how a user writes a query in a search box, and the URL that they click on. Given a large collection of real-world queries and clicks from a commercial search engine, the models are learned efficiently through maximum likelihood estimation using an EM algorithm. Given a new query, probabilistic inference enables recommendation of a set of pertinent actions and hosts. We propose an evaluation methodology for measuring the relevance of our recommended actions, and show empirical evidence of the quality and the diversity of the discovered actions.

/pdf/active-objects-actions-for-entity-centric-search-3hetpey1r6.pdf

Active objects: actions for entity-centric search

One or more techniques and/or systems are provided for facilitating task completion. For example, a natural language input (e.g., "where should we eat") may be received from a user of a client device. The natural language input may be evaluated using a set of user contextual signals, opted-in for exposure by the user for facilitating task completion, to identify a user task intent. For example, a user task intent of viewing a local Mexican restaurant menu may be identified based upon a social network post of the user indicating that the user is meeting a friend for Mexican food. Task completion functionality may be exposed to the user based upon the user task intent. For example, a restaurant app may be deep launched to display a menu of a local Mexican restaurant.

Task completion for natural language input

We predict entity type distributions in Web search queries via probabilistic inference in graphical models that capture how entity-bearing queries are generated. We jointly model the interplay between latent user intents that govern queries and unobserved entity types, leveraging observed signals from query formulations and document clicks. We apply the models to resolve entity types in new queries and to assign prior type distributions over an existing knowledge base. Our models are efficiently trained using maximum likelihood estimation over millions of real-world Web search queries. We show that modeling user intent significantly improves entity type resolution for head queries over the state of the art, on several metrics, without degradation in tail query performance.

/pdf/mining-entity-types-from-query-logs-via-user-intent-modeling-4sswgam0e9.pdf

Thomas Lin

Papers

No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities

Entity Linking at Web Scale

Active objects: actions for entity-centric search

Task completion for natural language input

Mining Entity Types from Query Logs via User Intent Modeling