Articles

Previous work in referring expression gen- eration has explored general purpose tech- niques for attribute selection and surface realization. However, most of this work did not take into account: a) stylistic dif- ferences between speakers; or b) trainable surface realization approaches that com- bine semantic and word order information. In …...

Though phrase-based SMT has achieved high translation quality, it still lacks of generaliza- tion ability to capture word order differences between languages. In this paper we describe a general method for tree-to-string phrase- based SMT. We study how syntactic trans- formation is incorporated into phrase-based SMT and its effectiveness. We …...

In this paper, we present a novel morphol- ogy preprocessing technique for Arabic- English translation. We exploit the Arabic morphology-English alignment to learn a model removing nonaligned Arabic mor- phemes. The model is an instance of the Conditional Random Field (Lafferty et al., 2001) model; it deletes a morpheme based …...

We propose a data-driven method for au- tomatically analyzing the morphology of ancient Greek. This method improves on existing ancient Greek analyzers in two ways. First, through the use of a nearest- neighbor machine learning framework, the analyzer requires no hand-crafted rules. Second, it is able to predict novel roots, …...

Pictorial communication systems convert natural language text into pictures to as- sist people with limited literacy. We define a novel and challenging problem: picture layout optimization. Given an input sen- tence, we seek the optimal way to lay out word icons such that the resulting picture best conveys the meaning …...

Catchwords refer to those popular words or phrases in a time period. In this paper, we propose a novel approach for automatic extraction of Chinese catchwords. By analyzing features of catchwords, we define three aspects to describe Popular Degree of catchwords. Then we use curve fitting in Time Series Analysis …...

s a text into a set of entity transition sequences and records distributional, syntactic, and referential information about discourse entities. We re-conceptualize coherence assessment as a learning task and show that our entity-based representation is well-suited for ranking-based generation and text classification tasks. Using the proposed representation, we achieve good …...

We present a novel approach to weakly super- vised semantic class learning from the web, using a single powerful hyponym pattern com- bined with graph structures, which capture two properties associated with pattern-based extractions: popularity and productivity. In- tuitively, a candidate is popular if it was dis- covered many times …...

In this paper we present a supervised method for back-of-the-book index construction. We introduce a novel set of features that goes be- yond the typical frequency-based analysis, in- cluding features based on discourse compre- hension, syntactic patterns, and information drawn from an online encyclopedia. In exper- iments carried out on …...

Detecting conflicting statements is a foun- dational text understanding task with appli- cations in information analysis. We pro- pose an appropriate definition of contradiction for NLP tasks and develop available corpora, from which we construct a typology of con- tradictions. We demonstrate that a system for contradiction needs to make …...

This paper proposes a novel method that ex- ploits multiple resources to improve statisti- cal machine translation (SMT) based para- phrasing. In detail, a phrasal paraphrase ta- ble and a feature function are derived from each resource, which are then combined in a log-linear SMT model for sentence-level para- phrase …...

This paper studies textual inference by inves- tigating comma structures, which are highly frequent elements whose major role in the ex- traction of semantic relations has not been hitherto recognized. We introduce the prob- lem of comma resolution, defined as under- standing the role of commas and extracting the relations …...

Word lattice decoding has proven useful in spoken language translation; we argue that it provides a compelling model for translation of text genres, as well. We show that prior work in translating lattices using finite state tech- niques can be naturally extended to more ex- pressive synchronous context-free grammar- based …...

Documents in languages such as Chinese, Japanese and Korean sometimes annotate terms with their translations in English inside a pair of parentheses. We present a method to extract such translations from a large collec- tion of web documents by building a partially parallel corpus and use a word alignment al- …...

In adding syntax to statistical MT, there is a tradeoff between taking advantage of lin- guistic analysis, versus allowing the model to exploit linguistically unmotivated mappings learned from parallel training data. A num- ber of previous efforts have tackled this trade- off by starting with a commitment to linguisti- cally …...

Automatic word alignment is a key step in training statistical machine translation sys- tems. Despite much recent work on word alignment methods, alignment accuracy in- creases often produce little or no improve- ments in machine translation quality. In this work we analyze a recently proposed agreement-constrained EM algorithm for un- …...

This paper evaluates the LinGO Grammar Ma- trix, a cross-linguistic resource for the de- velopment of precision broad coverage gram- mars, by applying it to the Australian language Wambaya. Despite large typological differ- ences between Wambaya and the languages on which the development of the resource was based, the Grammar …...

Previous studies of data-driven dependency parsing have shown that the distribution of parsing errors are correlated with theoretical properties of the models used for learning and inference. In this paper, we show how these results can be exploited to improve parsing accuracy by integrating a graph-based and a transition-based model. …...

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by gen- erative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sen- tences, we present the first general, feature- rich discriminative parser, based on a condi- tional …...

This paper describes a computational ap- proach to resolving the true referent of a named mention of a person in the body of an email. A generative model of mention gener- ation is used to guide mention resolution. Re- sults on three relatively small collections indi- cate that the accuracy …...