Articles

We evaluate the Berkeley parser on text from an online discussion forum. We evaluate the parser output with and without gold tokens and spellings (using Sparseval and Parseval), and we compile a list of problematic phenom- ena for this domain. The Parseval f-score for a small development set is 77.56. …...

Several methods for automatically gen- erating labeled examples that can be used as training data for WSD systems have been proposed, including a semi- supervised approach based on relevance feedback (Stevenson et al., 2008a). This approach was shown to generate examples that improved the performance of a WSD system for …...

Hierarchical phrase-based translation (Hiero, (Chiang, 2005)) provides an attractive frame- work within which both short- and long- distance reorderings can be addressed consis- tently and ef�ciently. However, Hiero is gen- erally implemented with a constraint prevent- ing the creation of rules with adjacent nonter- minals, because such rules introduce compu- …...

The class of Linear Inversion Transduction Grammars (LITGs) is introduced, and used to induce a word alignment over a parallel cor- pus. We show that alignment via Stochas- tic Bracketing LITGs is considerably faster than Stochastic Bracketing ITGs, while still yielding alignments superior to the widely- used heuristic of intersecting …...

Named entity recognition systems sometimes have difficulty when applied to data from do- mains that do not closely match the training data. We first use a simple rule-based tech- nique for domain adaptation. Data for robust validation of the technique is then generated, and we use crowdsourcing techniques to show …...

There are many misconceptions about de- pendency representations and phrase structure representations for syntax. They are partly due to terminological confusion, partly due to a lack of meta-scientific clarity about the roles of representations and linguistic theories. This opinion piece argues for a simple but clear view of syntactic representation. …...

Generating expository dialogue from mono- logue is a task that poses an interesting and re- warding challenge for Natural Language Pro- cessing. This short paper has three aims: firstly, to motivate the importance of this task, both in terms of the benefits of ex- pository dialogue as a way to …...

This paper presents an empirical comparison of similarity measures for pairs of concepts based on Information Content. It shows that using modest amounts of untagged text to de- rive Information Content results in higher cor- relation with human similarity judgments than using the largest available corpus of manually annotated sense–tagged …...

Sentence fusion enables summarization and question-answering systems to produce out- put by combining fully formed phrases from different sentences. Yet there is little data that can be used to develop and evaluate fu- sion techniques. In this paper, we present a methodology for collecting fusions of simi- lar sentence pairs …...

This paper investigates cross-lingual textual entailment as a semantic relation between two text portions in different languages, and pro- poses a prospective research direction. We argue that cross-lingual textual entailment (CLTE) can be a core technology for sev- eral cross-lingual NLP applications and tasks. Through preliminary experiments, we aim at …...

In this paper we examine different linguistic features for sentimental polarity classification, and perform a comparative study on this task between blog and re- view data. We found that results on blog are much worse than reviews and investigated two methods to improve the performance on blogs. First we ex- …...

We investigate methods of generating addi- tional bilingual phrase pairs for a phrase- based decoder by translating short sequences of source text. Because our translation task is more constrained, we can use a model that employs more linguistically rich features than a traditional decoder. We have implemented an example of …...

We consider the problem of predicting a movie’s opening weekend revenue. Previous work on this problem has used metadata about a movie—e.g., its genre, MPAA rating, and cast—with very limited work making use of text about the movie. In this paper, we use the text of film critics’ reviews from …...

We describe a utility evaluation to determine whether cross-document information extrac- tion (IE) techniques measurably improve user performance in news summary writing. Two groups of subjects were asked to perform the same time-restricted summary writing tasks, reading news under different conditions: with no IE results at all, with traditional single- …...

We identify some problems of the evaluation metrics used for the English Lexical Substitu- tion Task of SemEval-2007, and propose al- ternative metrics that avoid these problems, which we hope will better guide the future de- velopment of lexical substitution systems. 1...

The use of well-nested linear context-free rewriting systems has been empirically moti- vated for modeling of the syntax of languages with discontinuous constituents or relatively free word order. We present a chart-based pars- ing algorithm that asymptotically improves the known running time upper bound for this class of rewriting systems. …...

A variety of query systems have been devel- oped for interrogating parsed corpora, or tree- banks. With the arrival of efficient, wide- coverage parsers, it is feasible to create very large databases of trees. However, existing ap- proaches that use in-memory search, or rela- tional or XML database technologies, do …...

We describe a synchronous parsing algorithm that is based on two successive monolingual parses of an input sentence pair. Although the worst-case complexity of this algorithm is and must be O(n6) for binary SCFGs, its average-case run-time is far better. We demonstrate that for a number of common synchronous parsing …...

I briefly describe a system for automatically creating an implemented grammar of a natu- ral language based on answers to a web-based questionnaire, then present a grammar of Sa- haptin, a language of the Pacific Northwest with complex argument-marking and agree- ment patterns, that was developed to test the system. …...

This work represents an initial attempt to move beyond “single-shot” summarization to interactive summarization. We present an ex- tension to the classic Maximal Marginal Rel- evance (MMR) algorithm that places a user “in the loop” to assist in candidate selec- tion. Experiments in the complex interac- tive Question Answering (ciQA) …...