Google Inc.

Keith Hall

Ryan T McDonald

Enrique Alfonseca

Massimiliano Ciaramita

Slav Petrov

Fernando Pereira

Dipanjan Das

Terry Yang-Hoe Koo

Jason Katz-Brown

Katja Filippova

Systems and techniques are provided for training a natural language processing model with information retrieval model annotations. A natural language processing model may be trained, through machine learning, using training examples that include part-of-speech tagging and annotations added by an information retrieval model. The natural language processing model may generate part-of-speech, parse-tree, beginning, inside, and outside label, mention chunking, and named-entity recognition predictions with confidence scores for text in the training examples. The information retrieval model annotations and part-of-speech tagging in the training example may be used to determine the accuracy of the predictions, and the natural language processing model may be adjusted. After training, the natural language processing model may be used to make predictions for novel input, such as search queries and potential search results. The search queries and potential search results may have information retrieval model annotations.

Training a natural language processing model with information retrieval model annotations

A source language sentence is tagged with non-lexical tags, such as part-of-speech tags and is parsed using a lexicalized parser trained in the source language. A target language sentence that is a translation of the source language sentence is tagged with non-lexical labels (e.g., part-of speech tags) and is parsed using a delexicalized parser that has been trained in the source language to produce k-best parses. The best parse is selected based on the parse's alignment with lexicalized parse of the source language sentence. The selected best parse can be used to update the parameter vector of a lexicalized parser for the target language.

Multi-source transfer of delexicalized dependency parsers

A classifier learning module trains video classifiers associated with a stored set of concepts derived from textual metadata of a plurality of videos. Specifically, a first type of classifier (e.g., a content-based classifier) and a second type of classifier (e.g., a text-based classifier) are trained, the classifiers when applied to a video indicating a likelihood that the video represents one or more concepts corresponding to the classifier. The first type of classifier can be used to determine the training set for the second type of classifier. The learning process does not require any concepts to be known a priori, nor does it require a training set of videos having training labels manually applied by human experts. Scores from the first type of classifier are combined with scores from the second type of classifier to obtain video classification of enhanced accuracy.

Accurate video concept recognition via classifier combination

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining query suggestions from multiple correlation measures. In one aspect, a method includes receiving a first query and second queries, each of the first and second queries including one or more terms; for each second query and a linear model, receiving correlation scores measuring the correlation between the first query and the respective second query, each correlation score received from a respective correlation process, and each respective correlation process being different from the other respective correlation processes, and applying the linear model to the plurality of correlation scores to determine a combined correlation score that quantifies a combined correlation between the first query and the respective second query based on the plurality of correlation scores. The second queries are ranked in an order according to their respective combined correlations scores.

Multiple correlation measures for measuring query similarity

A plurality of highest intrinsically-ranked parser outputs are scored using an extrinsic metric that is relevant to one or more downstream applications. The parser can be trained by using an extrinsically highly-ranked parse selected from among the intrinsically highly-ranked parses. The selected parse need not be the highest intrinsically-ranked parse. In this way, a parser can be trained to produce better results for downstream applications.

Growing community of inventors

Zurich, Switzerland

Keith Hall