Articles

We created a dataset of syntactic-ngrams (counted dependency-tree fragments) based on a corpus of 3.5 million English books. The dataset includes over 10 billion distinct items covering a wide range of syntactic configura- tions. It also includes temporal information, facilitating new kinds of research into lexical semantics over time. This …...

This article provides a detailed overview of the CPN text-to-text similarity system that we par- ticipated with in the Semantic Textual Similar- ity task evaluations hosted at *SEM 2013. In addition to more traditional components, such as knowledge-based and corpus-based met- rics leveraged in a machine learning frame- work, we …...

Existing semantic parsing research has steadily improved accuracy on a few domains and their corresponding databases. This paper introduces FreeParser, a system that trains on one domain and one set of predicate and con- stant symbols, and then can parse sentences for any new domain, including sentences that refer to …...

In Statistical Machine Translation we often have to combine different sources of parallel training data to build a good system. One way of doing this is to build separate translation models from each data set and linearly inter- polate them, and to date the main method for optimising the interpolation …...

We present a new hierarchical Bayesian model for unsupervised topic segmentation. This new model integrates a point-wise boundary sam- pling algorithm used in Bayesian segmenta- tion into a structured topic model that can cap- ture a simple hierarchical topic structure latent in documents. We develop an MCMC infer- ence algorithm …...

We propose a novel framework for topic la- beling that assigns the most representative phrases for a given set of sentences cover- ing the same topic. We build an entailment graph over phrases that are extracted from the sentences, and use the entailment relations to identify and select the most …...

Multi-dimensional latent text models, such as factorial LDA (f-LDA), capture multiple fac- tors of corpora, creating structured output for researchers to better understand the contents of a corpus. We consider such models for clinical research of new recreational drugs and trends, an important application for mining current information for healthcare …...

Topics generated automatically, e.g. using LDA, are now widely used in Computational Linguistics. Topics are normally represented as a set of keywords, often the n terms in a topic with the highest marginal probabilities. We introduce an alternative approach in which topics are represented using images. Candi- date images for …...

Latent-variable PCFGs (L-PCFGs) are highly successful model for natural languagea parsing. Recent work (Cohen et al., 2012) has introduced a spectral algorithm for param- eter estimation of L-PCFGs, which—unlike the EM algorithm—is guaranteed to give con- sistent parameter estimates (it has PAC-style guarantees of sample complexity). This paper describes experiments …...

Most work on weakly-supervised learning for part-of-speech taggers has been based on un- realistic assumptions about the amount and quality of training data. For this paper, we attempt to create true low-resource scenarios by allowing a linguist just two hours to anno- tate data and evaluating on the languages Kin- …...

We consider the problem of training a sta- tistical parser in the situation when there are multiple treebanks available, and these tree- banks are annotated according to different lin- guistic conventions. To address this problem, we present two simple adaptation methods: the first method is based on the idea of …...

We propose a new approach to identifying semantically similar words across languages. The approach is based on an idea that two words in different languages are similar if they are likely to generate similar words (which in- cludes both source and target language words) as their top semantic word responses. …...

The frequency of words and syntactic con- structions has been observed to have a sub- stantial effect on language processing. This begs the question of what causes certain con- structions to be more or less frequent. A the- ory of grounding (Phillips, 2010) would sug- gest that cognitive limitations might …...

We develop a method for effective extraction of linguistic patterns that are differentially ex- pressed based on the native language of the author. This method uses multiple corpora to allow for the removal of data set specific patterns, and addresses both feature relevancy and redundancy. We evaluate different rel- evancy …...

Traditional relation extraction predicts rela- tions within some fixed and finite target schema. Machine learning approaches to this task require either manual annotation or, in the case of distant supervision, existing struc- tured sources of the same schema. The need for existing datasets can be avoided by us- ing a …...

The primary way of providing real-time cap- tioning for deaf and hard of hearing people is to employ expensive professional stenogra- phers who can type as fast as natural speak- ing rates. Recent work has shown that a feasible alternative is to combine the partial captions of ordinary typists, each …...

We propose a minimally supervised method for multilingual paraphrase extraction from definition sentences on the Web. Hashimoto et al. (2011) extracted paraphrases from Japanese definition sentences on the Web, as- suming that definition sentences defining the same concept tend to contain paraphrases. However, their method requires manually an- notated data …...

Different languages contain complementary cues about entities, which can be used to im- prove Named Entity Recognition (NER) sys- tems. We propose a method that formu- lates the problem of exploring such signals on unannotated bilingual text as a simple Inte- ger Linear Program, which encourages entity tags to agree …...

Humans identify word boundaries in continu- ous speech by combining multiple cues; exist- ing state-of-the-art models, though, look at a single cue. We extend the generative model of Goldwater et al (2006) to segment using sylla- ble stress as well as phonemic form. Our new model treats identification of word …...

Identifying documents that describe a specific type of event is challenging due to the high complexity and variety of event descriptions. We propose a multi-faceted event recognition approach, which identifies documents about an event using event phrases as well as defin- ing characteristics of the event. Our research focuses on …...