Articles

In a world where information is increasingly delivered to users via different devices with dramatically different constraints and capabilities, it is becoming crucial to consider how the presentation of information must be adapted to suit specific devices and user contexts. To avoid confusing and disorienting the users as they switch …...

One of the most widely explored issues in natu- ral language generation is the generation of re- ferring expressions (gre): given an entity we want to refer to, how do we work out the content of a referring expression that uniquely identifies the intended referent? Over the last 15 years, …...

In this paper we present PENG-D, a proposal for a controlled natural language that can be used for expressing knowledge about resources in the Semantic Web and for specifying on- tologies in a human-readable way. After a brief overview of the main Semantic Web en- abling technologies (and their deficiencies), …...

Statistical parsers are extremely complex sys- tems, yet papers describing them almost always only discuss theoretical issues instead of imple- mentation issues. This paper attempts to ad- dress the imbalance by describing the imple- mentation issues faced in building a state-of- the-art statistical parser. In the process, we will describe …...

This work presents a type of parser that takes the process of chunking to the stage of producing full parse trees. This type of parser, denoted Thin Parsers (TP) in this work has the characteristics of: following a given grammar, creating full parse trees, producing only a limited number of …...

This paper presents an approach on a query- biased document summarisation and an evaluation of the use of such an approach for question answering tasks. We observed a significant difference in the user’s performance by presenting a list of documents customized to the task type, compared with a generic document …...

This paper presents an approach for question analysis that defines the question subject and its required answer type by building a trie- based structure from a set of question patterns. The question analysis consists of comparing the question tokens with the path of nodes in the trie. A look-ahead process …...

We present a question answering system that combines information at the lexical, syntactic, and semantic levels, in the process to find and rank the candidate answer sentences. The can- didate exact answers are extracted from the candidate answer sentences by means of a com- bination of information-extraction techniques (named entity …...

Although syntactic features offer more specific information about the context surrounding a target word in a Word Sense Disambiguation (WSD) task, in general, they have not distinguished themselves much above positional fea- tures such as bag-of-words. In this pa- per we offer two methods for increas- ing the recall rate …...

The detection of prosodic characteristics is an im- portant aspect of both speech synthesis and speech recognition. Correct placement of pitch accents aids in more natural sounding speech, while automatic detection of accents can contribute to better word- level recognition and better textual understanding. In this paper we investigate probabilistic, …...

We describe a statistical approach for modeling agreements and disagreements in conversational in- teraction. Our approach first identifies adjacency pairs using maximum entropy ranking based on a set of lexical, durational, and structural features that look both forward and backward in the discourse. We then classify utterances as agreement or …...

Generalized Multitext Grammar (GMTG) is a syn- chronous grammar formalism that is weakly equiv- alent to Linear Context-Free Rewriting Systems (LCFRS), but retains much of the notational and in- tuitive simplicity of Context-Free Grammar (CFG). GMTG allows both synchronous and independent rewriting. Such flexibility facilitates more perspic- uous modeling of …...

In an ordinary syntactic parser, the input is a string, and the grammar ranges over strings. This paper explores generalizations of ordinary parsing algo- rithms that allow the input to consist of string tu- ples and/or the grammar to range over string tu- ples. Such algorithms can infer the synchronous …...

This paper describes an algorithm for detecting empty nodes in the Penn Treebank (Marcus et al., 1993), finding their antecedents, and assigning them function tags, without access to lexical information such as valency. Unlike previous approaches to this task, the current method is not corpus-based, but rather makes use of …...

We introduce a new method for disambiguating word senses that exploits a nonlinear Kernel Prin- cipal Component Analysis (KPCA) technique to achieve accuracy superior to the best published indi- vidual models. We present empirical results demon- strating significantly better accuracy compared to the state-of-the-art achieved by either na¨ıve Bayes or …...

This paper presents an unsupervised word sense learning algorithm, which induces senses of target word by grouping its occurrences into a “natural” number of clusters based on the similarity of their contexts. For removing noisy words in feature set, feature selection is conducted by optimizing a clus- ter validation criterion …...

In this paper we propose a unified framework for automatic evaluation of NLP applications using N-gram co-occurrence statistics. The automatic evaluation metrics proposed to date for Machine Translation and Automatic Summarization are particular instances from the family of metrics we propose. We show that different members of the same family …...

We present the results of an experiment on extending the automatic method of Machine Translation evaluation BLUE with statistical weights for lexical items, such as tf.idf scores. We show that this extension gives additional information about evaluated texts; in particular it al- lows us to measure translation Adequacy, which, for …...

In this paper we describe two new objective automatic evaluation methods for machine translation. The first method is based on long- est common subsequence between a candidate translation and a set of reference translations. Longest common subsequence takes into ac- count sentence level structure similarity natu- rally and identifies longest …...

It is fairly common that different people are associated with the same name. In tracking person entities in a large document pool, it is important to determine whether multiple mentions of the same name across documents refer to the same entity or not. Previous approach to this problem involves measuring …...