Articles

We describe experiments carried out with adaptive language and translation models in the context of an interactive computer-assisted translation program. We developed cache-based language models which were then extended to the bilingual case for a cache- based translation model. We present the improve- ments we obtained in two contexts: in …...

We present an approach to bounded constraint- relaxation for entropy maximization that corre- sponds to using a double-exponential prior or ℓ1 reg- ularizer in likelihood maximization for log-linear models. We show that a combined incremental fea- ture selection and regularization method can be es- tablished for maximum entropy modeling by …...

In this paper, we describe a resource-light system for the automatic morphological analysis and tag- ging of Russian. We eschew the use of extensive resources (particularly, large annotated corpora and lexicons), exploiting instead (i) pre-existing anno- tated corpora of Czech; (ii) an unannotated corpus of Russian. We show that our …...

We present a novel representation of parse trees as lists of paths (leaf projection paths) from leaves to the top level of the tree. This representation allows us to achieve significantly higher accuracy in the task of HPSG parse selection than standard models, and makes the application of string kernels …...

In most research on concept acquisition from corpora, concepts are modeled as vectors of relations extracted from syntactic structures. In the case of modifiers, these relations often specify values of attributes, as in (attr red); this is unlike what typically proposed in theories of knowledge representation, where concepts are typically …...

We propose a general model for joint inference in corre- lated natural language processing tasks when fully anno- tated training data is not available, and apply this model to the dual tasks of word sense disambiguation and verb subcategorization frame determination. The model uses the EM algorithm to simultaneously complete …...

We apply statistical machine translation (SMT) tools to generate novel paraphrases of input sentences in the same language. The system is trained on large volumes of sentence pairs automatically extracted from clustered news articles available on the World Wide Web. Alignment Error Rate (AER) is measured to gauge the quality …...

We are interested in the problem of modeling and evaluating spoken language systems in the context of human-machine dialogs. Spoken di- alog corpora allow for a multidimensional anal- ysis of speech recognition and language under- standing models of dialog systems. Therefore language models can be directly trained based either on …...

A method for automatic plot analysis of narrative texts that uses components of both traditional sym- bolic analysis of natural language and statistical machine-learning is presented for the story rewrit- ing task. In the story rewriting task, an exemplar story is read to the pupils and the pupils rewrite the …...

Alignment Hal Daum´e III and Daniel Marcu Information Sciences Institute University of Southern California 4676 Admiralty Way, Suite 1001 Marina del Rey, CA 90292 {hdaume,marcu}@isi.edu Abstract We describe a model for creating word-to-word and phrase-to-phrase alignments between documents and their human written abstracts. Such alignments are critical for the development …...

We present a data and error analysis for semantic role labelling. In a first experiment, we build a generic statis- tical model for semantic role assignment in the FrameNet paradigm and show that there is a high variance in perfor- mance across frames. The main hypothesis of our paper is …...

We present an unsupervised method for labelling the arguments of verbs with their semantic roles. Our bootstrapping algorithm makes initial unam- biguous role assignments, and then iteratively up- dates the probability model on which future assign- ments are based. A novel aspect of our approach is the use of verb, …...

We apply a novel variant of Random Forests (Breiman, 2001) to the shallow semantic parsing problem and show extremely promising results. The final system has a semantic role classification accuracy of 88.3% using PropBank gold-standard parses. These results are better than all others published except those of the Support Vector …...

In this paper we investigate whether paragraphs can be identifi ed automatically in different languages and domains. We propose a machine learning ap- proach which exploits textual and discourse cues and we assess how well humans perform on this task. Our best models achieve an accuracy that is signifi cantly …...

Accurate dependency recovery has recently been reported for a number of wide-coverage statistical parsers using Combinatory Categorial Grammar (CCG). However, overall figures give no indication of a parser’s performance on spe- cific constructions, nor how suitable a parser is for specific applications. In this paper we give a detailed evaluation …...

Previous works on question classification are based on complex natural language process- ing techniques: named entity extractors, parsers, chunkers, etc. While these ap- proaches have proven to be effective they have the disadvantage of being targeted to a particular language. We present here a sim- ple approach that exploits lexical …...

Identifying sentiments (the affective parts of opinions) is a challenging problem. We present a system that, given a topic, automatically finds the people who hold opinions about that topic and the sentiment of each opinion. The system contains a module for determining word sentiment and another for combining sentiments within …...

We present a learning-based method to identify single-snippet answers to definition questions in question answering systems for document collections. Our method combines and extends two previous techniques that were based mostly on manually crafted lexical patterns and WordNet hypernyms. We train a Support Vector Machine (SVM) on vectors comprising the …...

This paper deals with contextual aspects of loca- tive preposition processing. Firstly, accordingly to a study on the referential behavior of the pronominal adverb ”y” in its locative uses, we show that static locative prepositions are functions, not only at the conceptual level (as shown in previous studies), but also …...

This paper evaluates the accuracy of HPSG parsing in terms of the identification of predicate-argument relations. We could directly compare the output of HPSG parsing with Prop- Bank annotations, by assuming a unique map- ping from HPSG semantic representation into PropBank annotation. Even though PropBank was not used for the …...