Articles

Datasets annotated with semantic roles are an important prerequisite to developing high- performance role labeling systems. Unfortu- nately, the reliance on manual annotations, which are both difficult and highly expen- sive to produce, presents a major obstacle to the widespread application of these systems across different languages and text genres. …...

We describe a cross-lingual method for the in- duction of selectional preferences for resource- poor languages, where no accurate monolin- gual models are available. The method uses bilingual vector spaces to “translate” foreign language predicate-argument structures into a resource-rich language like English. The only prerequisite for constructing the bilin- gual …...

We treat the text summarization problem as maximizing a submodular function under a budget constraint. We show, both theoretically and empirically, a modified greedy algorithm can efficiently solve the budgeted submodu- lar maximization problem near-optimally, and we derive new approximation bounds in do- ing so. Experiments on DUC’04 task show …...

Automatically finding email messages that contain requests for action can provide valu- able assistance to users who otherwise strug- gle to give appropriate attention to the ac- tionable tasks in their inbox. As a speech act classification task, however, automatically recognising requests in free text is particularly challenging. The problem …...

This paper analyzes the topic identification stage of single-document automatic text sum- marization across four different domains, con- sisting of newswire, literary, scientific and le- gal documents. We present a study that ex- plores the summary space of each domain via an exhaustive search strategy, and finds the probability density …...

ing Conversations Gabriel Murray gabrielm@cs.ubc.ca Giuseppe Carenini carenini@cs.ubc.ca Department of Computer Science, University of British Columbia Vancouver, Canada Raymond Ng rng@cs.ubc.ca Abstract We address the challenge of automatically ab- stracting conversations such as face-to-face meetings and emails. We focus here on the stages of interpretation, where sentences are mapped to …...

This paper presents efficient algorithms for expected similarity maximization, which co- incides with minimum Bayes decoding for a similarity-based loss function. Our algorithms are designed for similarity functions that are sequence kernels in a general class of posi- tive definite symmetric kernels. We discuss both a general algorithm and a …...

We present a new method that compresses sentences by removing words. In a first stage, it generates candidate compressions by re- moving branches from the source sentence’s dependency tree using a Maximum Entropy classifier. In a second stage, it chooses the best among the candidate compressions using a Support Vector …...

Synchronous tree substitution grammars are a translation model that is used in syntax-based machine translation. They are investigated in a formal setting and compared to a competi- tor that is at least as expressive. The competi- tor is the extended multi bottom-up tree trans- ducer, which is the bottom-up analogue …...

The distortion cost function used in Moses- style machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increas- ing search errors. Second, all distortion is penalized linearly, even when appropriate re- orderings are performed. Because the cost function does not …...

We describe a class of translation model in which a set of input variants encoded as a context-free forest is translated using a finite- state translation model. The forest structure of the input is well-suited to representing word order alternatives, making it straightforward to model translation as a two step …...

This paper presents a direct word reordering model with novel syntax-based features for sta- tistical machine translation. Reordering models address the problem of reordering source lan- guage into the word order of the target language. IBM Models 3 through 5 have reordering com- ponents that use surface word information but …...

In a Wizard-of-Oz experiment with multiple wizard subjects, each wizard viewed automated speech recognition (ASR) results for utterances whose interpretation is critical to task success: requests for books by title from a library data- base. To avoid non-understandings, the wizard directly queried the application database with the ASR hypothesis (voice …...

Image annotation, the task of automatically generating description words for a picture, is a key component in various image search and retrieval applications. Creating image databases for model development is, however, costly and time consuming, since the key- words must be hand-coded and the process repeated for new collections. In …...

In evidence-based medicine, clinical questions involve four aspects: Patient/Problem (P), In- tervention (I), Comparison (C) and Outcome (O), known as PICO elements. In this pa- per we present a method that extends the lan- guage modeling approach to incorporate both document structure and PICO query formu- lation. We present an …...

Speaking both as an experienced independent technical translator and on behalf of the 11,000 members of the American Translators Association (ATA), the Association's presi- dent will explain the training, standards, ob- jectives and working methods of the people who convey meaning from one language into another as their chosen profession. …...

We propose the notion of a structural bias inherent in a parsing system with respect to the language it is aiming to parse. This structural bias characterizes the behaviour of a parsing system in terms of structures it tends to under- and over- produce. We propose a Boosting-based method for …...

In this paper, we provide a theoretical framework for feature selection in tree ker- nel spaces based on gradient-vector com- ponents of kernel-based machines. We show that a huge number of features can be discarded without a significant decrease in accuracy. Our selection algorithm is as accurate as and much …...

Recent speed-ups for training large-scale models like those found in statistical NLP exploit distributed computing (either on multicore or “cloud” architectures) and rapidly converging online learning algo- rithms. Here we aim to combine the two. We focus on distributed, “mini-batch” learners that make frequent updates asyn- chronously (Nedic et al., …...

Both entity and relation extraction can benefit from being performed jointly, al- lowing each task to correct the errors of the other. We present a new method for joint entity and relation extraction using a graph we call a “card-pyramid.” This graph compactly encodes all possible en- tities and relations …...