Articles

AbstractEntity disambiguation with Wikipedia relies on structured information from redirect pages, article text, inter-article links, and categories. We explore whether web links can replace a curated encyclopaedia, obtaining entity prior, name, context, and coherence models from a corpus of web pages with links to Wikipedia. Experiments compare web link models …...

AbstractMost approaches to relation extraction, the task of extracting ground facts from natural language text, are based on machine learning and thus starved by scarce training data. Manual annotation is too expensive to scale to a comprehensive set of relations. Distant supervision, which automatically creates training data, only works with …...

AbstractGrammars for machine translation can be materialized on demand by finding source phrases in an indexed parallel corpus and extracting their translations. This approach is limited in practical applications by the computational expense of online lookup and extraction. For phrase-based models, recent work has shown that on-demand grammar extraction can …...

AbstractNatural language meanings allow speakers to encode important real-world distinctions, but corpora of grounded language use also reveal that speakers categorize the world in different ways and describe situations with different terminology. To learn meanings from data, we therefore need to link underlying representations of meaning to models of speaker …...

AbstractOnline discussion forums and community question-answering websites provide one of the primary avenues for online users to share information. In this paper, we propose text mining techniques which aid users navigate troubleshooting-oriented data such as questions asked on forums and their suggested solutions. We introduce Bayesian generative models of the …...

AbstractWord sense induction (WSI) seeks to automatically discover the senses of a word in a corpus via unsupervised methods. We propose a sense-topic model for WSI, which treats sense and topic as two separate latent variables to be inferred jointly. Topics are informed by the entire document, while senses are …...

AbstractWe introduce Sprite, a family of topic models that incorporates structure into model priors as a function of underlying components. The structured priors can be constrained to model topic hierarchies, factorizations, correlations, and supervision, allowing Sprite to be tailored to particular settings. We demonstrate this flexibility by constructing a Sprite-based …...

AbstractInferring the information structure of scientific documents is useful for many NLP applications. Existing approaches to this task require substantial human effort. We propose a framework for constraint learning that reduces human involvement considerably. Our model uses topic models to identify latent topics and their key linguistic features in input …...

AbstractIdentifying and linking named entities across information sources is the basis of knowledge acquisition and at the heart of Web search, recommendations, and analytics. An important problem in this context is cross-document co-reference resolution (CCR): computing equivalence classes of textual mentions denoting the same entity, within and across documents. Prior …...

AbstractLittle work from the Natural Language Processing community has targeted the role of quantities in Natural Language Understanding. This paper takes some key steps towards facilitating reasoning about quantities expressed in natural language. We investigate two different tasks of numerical reasoning. First, we consider Quantity Entailment, a new task formulated …...

AbstractWe present a dynamic programming algorithm for efficient constrained inference in semantic role labeling. The algorithm tractably captures a majority of the structural constraints examined by prior work in this area, which has resorted to either approximate methods or off-the-shelf integer linear programming solvers. In addition, it allows training a …...

Organisations — including insurgent movements — harness social media to engage potential consumers. They evoke sympathetic (and antipathic) response; content sharing engenders affinity and community. We report on a pilot study of presumed rhetorical intent for statuses retweeted by a set of suspected Islamic State-sympathetic Twitter accounts. This annotation is …...

This study compared three topic models trained on three versions of a news cor- pus. The first model was generated from the raw news corpus, the second was gen- erated from the lemmatised version of the news corpus, and the third model was generated from the lemmatised news cor- pus …...

Some revisions of documents can change the meaning of passages, while others merely re-phrase or improve style. In a multi-author workflow, assisting readers to assess whether a revision changes mean- ing or not can be useful in prioritising re- vision. One challenge in this is how to de- tect and …...

The utility of using morphological features in part-of-speech (POS) tagging is well es- tablished in the literature. However, the usefulness of exploiting information about POS tags for morphological segmentation is less clear. In this paper we study the POS-dependent morphological segmenta- tion in the Adaptor Grammars framework. We experiment with …...

Risk assessment is a crucial activity for financial institutions because it helps them to determine the amount of capi- tal they should hold to assure their sta- bility. Flawed risk assessment models could return erroneous results that trigger a misuse of capital by banks and in the worst case, their …...

A central task in clinical information ex- traction is the classification of sentences to identify key information in publications, such as intervention and outcomes. Sur- face tokens and part-of-speech tags have been the most commonly used feature types for this task. In this paper we eval- uate the use of …...

Building comprehensive language models us- ing latent semantic analysis (LSA) requires substantial processing power. At the ideal pa- rameters suggested in the literature (for an overview, see Bradford, 2008) it can take up to several hours, or even days, to complete. For linguistic researchers, this extensive pro- cessing time is …...

Probabilistic topic models are widely used to discover latent topics in document col- lections, while latent feature word vec- tors have been used to obtain high per- formance in many natural language pro- cessing (NLP) tasks. In this paper, we present a new approach by incorporating word vectors to directly …...

Historical newspapers are an important resource in humanities research, provid- ing the source materials about people and places in historical context. The Trove col- lection in the National Library of Australia holds a large collection of digitised news- papers dating back to 1803. This paper re- ports on some work …...