Articles

This paper reports experiments which pCRU — a generation frameworkin that combines probabilistic generation methodology with a comprehensive model of the generation space — is used to semi-automatically create sev- eral versions of a weather forecast text generator. The generators are evaluated in terms of output quality, development time and …...

This paper introduces an unsupervised morphological segmentation algorithm that shows robust performance for four languages with different levels of mor- phological complexity. In particular, our algorithm outperforms Goldsmith’s Lin- guistica and Creutz and Lagus’s Mor- phessor for English and Bengali, and achieves performance that is comparable to the best results …...

We relate the problem of finding the best application of a Synchronous Context- Free Grammar (SCFG) rule during pars- ing to a Markov Random Field. This representation allows us to use the the- ory of expander graphs to show that the complexity of SCFG parsing of an input sentence of …...

In this paper, we empirically demonstrate what we call the domain restriction hy- pothesis, claiming that semantically re- lated terms extracted from a corpus tend to be semantically coherent. We apply this hypothesis to define a post-processing module for the output of Espresso, a state of the art relation extraction …...

This paper addresses the problem of clas- sifying Chinese unknown words into fine-grained semantic categories defined in a Chinese thesaurus. We describe three novel knowledge-based models that capture the relationship between the se- mantic categories of an unknown word and those of its component characters in three different ways. We …...

The task of identifying synonymous re- lations and objects, or Synonym Resolu- tion (SR), is critical for high-quality infor- mation extraction. The bulk of previous SR work assumed strong domain knowl- edge or hand-tagged training examples. This paper investigates SR in the con- text of unsupervised information extrac- tion, where …...

Relation extraction is the task of find- ing semantic relations between entities from text. The state-of-the-art methods for relation extraction are mostly based on statistical learning, and thus all have to deal with feature selection, which can significantly affect the classification per- formance. In this paper, we systemat- ically explore …...

A novel random text generation model is introduced. Unlike in previous random text models, that mainly aim at producing a Zipfian distribution of word frequencies, our model also takes the properties of neighboring co-occurrence into account and introduces the notion of sentences in random text. After pointing out the defi- …...

We introduce a novel ranking algorithm called GRASSHOPPER, which ranks items with an emphasis on diversity. That is, the top items should be different from each other in order to have a broad coverage of the whole item set. Many natural lan- guage processing tasks can benefit from such diversity …...

This paper presents two Markov chain Monte Carlo (MCMC) algorithms for Bayesian inference of probabilistic con- text free grammars (PCFGs) from ter- minal strings, providing an alternative to maximum-likelihood estimation using the Inside-Outside algorithm. We illus- trate these methods by estimating a sparse grammar describing the morphology of the Bantu …...

We explore the problem of retrieving semi-structured documents from a real- world collection using a structured query. We formally develop Structured Rele- vance Models (SRM), a retrieval model that is based on the idea that plausible values for a given field could be inferred from the context provided by the …...

Traditional noun phrase coreference res- olution systems represent features only of pairs of noun phrases. In this paper, we propose a machine learning method that enables features over sets of noun phrases, resulting in a first-order proba- bilistic model for coreference. We out- line a set of approximations that make …...

Conditional Random Fields (CRFs) have shown great success for problems involving structured out- put variables. However, for many real-world NLP applications, exact maximum-likelihood training is intractable because computing the global normal- ization factor even approximately can be extremely hard. In addition, optimizing likelihood often does not correlate with maximizing task-specific …...

This paper presents a maximum entropy ma- chine translation system using a minimal set of translation blocks (phrase-pairs). While recent phrase-based statistical machine trans- lation (SMT) systems achieve significant im- provement over the original source-channel sta- tistical translation models, they 1) use a large inventory of blocks which have significant …...

We study the use of rich syntax-based statistical models for generating gram- matical case for the purpose of machine translation from a language which does not indicate case explicitly (English) to a language with a rich system of surface case markers (Japanese). We propose an extension of n-best re-ranking as …...

We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence re- ordering metrics, and discriminative un- igram precision, as well as a method of learning linear feature weights to directly maximize correlation with human judg- ments. By aligning both the hypothe- sis and the reference with the …...

The quality of a sentence translated by a machine translation (MT) system is dif- ficult to evaluate. We propose a method for automatically evaluating the quality of each translation. In general, when translating a given sentence, one or more conditions should be satisfied to maintain a high translation quality. In …...

This study addresses the problem of au- tomatically detecting decisions in conver- sational speech. We formulate the prob- lem as classifying decision-making units at two levels of granularity: dialogue acts and topic segments. We conduct an em- pirical analysis to determine the charac- teristic features of decision-making dia- logue acts, …...

In this paper, we report on an empirical study on initiative conflicts in human-human conver- sation. We examined these conflicts in two corpora of task-oriented dialogues. The re- sults show that conversants try to avoid initia- tive conflicts, but when these conflicts occur, they are efficiently resolved by linguistic de- …...

The immense prosodic variation of natural con- versational speech makes it challenging to pre- dict which words are prosodically prominent in this genre. In this paper, we examine a new fea- ture, accent ratio, which captures how likely it is that a word will be realized as prominent or not. …...