Articles

The N400 is a human neuroelectric response to semantic incongruity in on-line sentence processing, and implausibility in context has been identified as one of the factors that influ- ence the size of the N400. In this paper we in- vestigate whether predictors derived from La- tent Semantic Analysis, language models, …...

This paper introduces tree transducers as a unifying theory for semantic parsing models based on tree transformations. Many exist- ing models use tree transformations, but im- plement specialized training and smoothing methods, which makes it difficult to mod- ify or extend the models. By connecting to the rich literature on …...

The ALTA shared tasks are programming competitions where all participants attempt to solve the same problem, and the winner is the system with the best results. The 2011 ALTA shared task is the second in the series and it focuses on trying to automatically grade the level of clinical evidence …...

We apply the graph-structured stack (GSS) to shift-reduce parsing in a Combinatory Cate- gorial Grammar (CCG) parser. This allows the shift-reduce parser to explore all possible parses in polynomial time without resorting to heuristics, such as beam search. The GSS- based shift-reduce parser is 34% slower than CKY in the …...

Bayesian models are usually learned using batch algorithms that have to iterate multiple times over the full dataset. This is both com- putationally expensive and, from a cognitive point of view, highly implausible. We present a novel online algorithm for the word segmen- tation models of Goldwater et al. (2009) …...

Unsupervised approaches to multi-document summarization consist of two steps: find- ing a content model of the documents to be summarized, and then generating a summary that best represents the most salient informa- tion of the documents. In this paper, we present a sentence selection objective for ex- tractive summarization in …...

ive Summarization of Line Graphs from Popular Media Charles F. Greenbacker Peng Wu Sandra Carberry Kathleen F. McCoy Stephanie Elzer* Department of Computer and Information Sciences University of Delaware, Newark, Delaware, USA [charlieg|pwu|carberry|mccoy]@cis.udel.edu *Department of Computer Science Millersville University, Millersville, Pennsylvania, USA elzer@cs.millersville.edu Abstract Information graphics (bar charts, line graphs, …...

We establish a novel task in the spirit of news sum- marization and topic detection and tracking (TDT): daily determination of the topics newly popular with Wikipedia readers. Central to this effort is a new public dataset consisting of the hourly page view statistics of all Wikipedia articles over the …...

ive summarization has been a long- standing and long-term goal in automatic sum- marization, because systems that can generate abstracts demonstrate a deeper understanding of language and the meaning of documents than systems that merely extract sentences from those documents. Genest (2009) showed that summaries from the top automatic sum- …...

This paper addresses the problem of summa- rizing decisions in spoken meetings: our goal is to produce a concise decision abstract for each meeting decision. We explore and com- pare token-level and dialogue act-level au- tomatic summarization methods using both unsupervised and supervised learning frame- works. In the supervised summarization …...

We present a novel unsupervised approach to the problem of multi-document summariza- tion of scientific articles, in which the doc- ument collection is a list of papers cited to- gether within the same source article, other- wise known as a co-citation. At the heart of the approach is a topic …...

We describe the beginning stages of our work on summarizing chat, which is motivated by our observations concerning the information overload of US Navy watchstanders. We de- scribe the challenges of summarizing chat and focus on two chat-specific types of summa- rizations we are interested in: thread sum- maries and …...

Current metrics for evaluating machine trans- lation quality have the huge drawback that they require human-quality reference transla- tions. We propose a truly automatic evalua- tion metric based on IBM1 lexicon probabili- ties which does not need any reference transla- tions. Several variants of IBM1 scores are sys- tematically explored …...

This paper proposes a novel method for long distance, clause-level reordering in statistical machine translation (SMT). The proposed method separately translates clauses in the source sentence and recon- structs the target sentence using the clause translations with non-terminals. The non- terminals are placeholders of embedded clauses, by which we reduce …...

We present a method for incorporat- ing arbitrary context-informed word at- tributes into statistical machine trans- lation by clustering attribute-quali ed source words, and smoothing their word translation probabilities using bi- nary decision trees. We describe two ways in which the decision trees are used in machine translation: by us- …...

We present a new translation model that include undecorated hierarchical-style phrase rules, decorated source-syntax rules, and partially decorated rules. Results show an increase in translation performance of up to 0.8% BLEU for German–English translation when trained on the news-commentary corpus, using syntactic annotation from a source lan- guage parser. We …...

This paper proposes an unsupervised word segmentation algorithm that identi- fies word boundaries in continuous source language text in order to improve the translation quality of statistical machine translation (SMT) approaches. The method can be applied to any language pair where the source language is unseg- mented and the target …...

The translation model of statistical ma- chine translation systems is trained on par- allel data coming from various sources and domains. These corpora are usually con- catenated, word alignments are calculated and phrases are extracted. This means that the corpora are not weighted accord- ing to their importance to the …...

Structured perceptrons are attractive due to their simplicity and speed, and have been used successfully for tuning the weights of binary features in a machine translation system. In attempting to apply them to tuning the weights of real-valued features with highly skewed distributions, we found that they did not work …...

We propose a new framework for N-best reranking on sparse feature sets. The idea is to reformulate the reranking problem as a Multitask Learning problem, where each N-best list corresponds to a distinct task. This is motivated by the observation that N-best lists often show significant differ- ences in feature …...