Articles

. This paper describes a modeling in a logical framework of the semantic content of a class of action nouns in French that are ambiguous between a processive interpretation and a resultative one in which these nouns refer to new objects in the world that are created by the process …...

. Current work in terminology mining from corpora tends to favour corpus size over corpus quality. Concerning multilingual lexical acquisition from comparable corpora, the best results are obtained on large corpora, i.e. several million words. But for many domains and language pairs, such huge corpora are simply not available. Our …...

. This paper presents an exploration of a lexical graph, within the framework of lexical semantics. The aim of the exploration is reveal the structure of the lexicon modelled by the graph so an automatic system can reach the information it contains. We developed geometric tools to build a semantic …...

. We present an analogical learning model which exploits the notion of formal analogi- cal proportions; this approach requires the ability to define these proportions and to implement them efficiently. We propose an algebraic definition of this notion, which applies to a large range of structured objects: words, attribute-value structures, …...

. In this paper, we report a set of results obtained by tuning a base of lexical relation patterns for CAMÉLÉON, a tool that supports ontology engineering from texts. When evaluating these patterns on eight different corpora, their efficiency varied strongly depending on the test corpus. This leads to two …...

AbstractNatural language analysis systems which combine knowledge-based and corpus-based methods are now becoming accurate enough to be used in various applications. We describe one such parsing system for Dutch, known as Alpino, and we show how corpus-based methods are essential to obtain accurate knowledge-based parsers. In particular we show a …...

It is practically impossible to build a word-based lexicon for speech recogni- tion in agglutinative languages that would cover all the relevant words. The prob- lem is that words are generally built by concatenating several prefixes and suffixes to the word roots. Together with com- pounding and inflections this leads …...

We propose a new document vector represen- tation specifically designed for the document clustering task. Instead of the traditional term- based vectors, a document is represented as an �-dimensional vector, where � is the number of documents in the cluster. The value at each di- mension of the vector is …...

This paper presents a solution to the prob- lem of matching personal names in Eng- lish to the same names represented in Arabic script. Standard string comparison measures perform poorly on this task due to varying transliteration conventions in both languages and the fact that Arabic script does not usually …...

This paper studies the impact of para- phrases on the accuracy of automatic eval- uation. Given a reference sentence and a machine-generated sentence, we seek to find a paraphrase of the reference sen- tence that is closer in wording to the ma- chine output than the original reference. We apply …...

We present a novel statistical approach to semantic parsing, WASP, for construct- ing a complete, formal meaning represen- tation of a sentence. A semantic parser is learned given a set of sentences anno- tated with their correct meaning represen- tations. The main innovation of WASP is its use of state-of-the-art …...

Recent work on semantic role labeling (SRL) has focused almost exclusively on the analysis of the predicate-argument structure of verbs, largely due to the lack of human-annotated resources for other types of predicates that can serve as train- ing and test data for the semantic role labeling systems. However, it …...

ParaEval is an automated evaluation method for comparing reference and peer summaries. It facilitates a tiered- comparison strategy where recall-oriented global optimal and local greedy searches for paraphrase matching are enabled in the top tiers. We utilize a domain- independent paraphrase table extracted from a large bilingual parallel corpus us- …...

We describe finite-state constraint relaxation, a method for ap- plying global constraints, expressed as automata, to sequence model decoding. We present algorithms for both hard con- straints and binary soft constraints. On the CoNLL-2004 se- mantic role labeling task, we report a speedup of at least 16x over a previous …...

Large-scale web-search engines are generally designed for linear text. The linear text repre- sentation is suboptimal for audio search, where accuracy can be significantly improved if the search includes alternate recognition candi- dates, commonly represented as word lattices. This paper proposes a method for indexing word lattices that is suitable …...

Language model information retrieval de- pends on accurate estimation of document models. In this paper, we propose a docu- ment expansion technique to deal with the problem of insufficient sampling of docu- ments. We construct a probabilistic neigh- borhood for each document, and expand the document with its neighborhood infor- …...

Test collections are essential to evaluate Information Retrieval (IR) systems. The relevance assessment set has been recog- nized as the key bottleneck in test col- lection building, especially on very large sized document collections. This paper addresses the problem of efficiently se- lecting documents to be included in the assessment …...

We present an approach to building a test collection of research papers. The ap- proach is based on the Cranfield 2 tests but uses as its vehicle a current conference; research questions and relevance judge- ments of all cited papers are elicited from conference authors. The resultant test col- lection …...

The present methodology for evaluating complex questions at TREC analyzes an- swers in terms of facts called “nuggets”. The official F-score metric represents the harmonic mean between recall and pre- cision at the nugget level. There is an implicit assumption that some facts are more important than others, which is …...

The TREC Definition and Relationship questions are evaluated on the basis of in- formation nuggets that may be contained in system responses. Human evalua- tors provide informal descriptions of each nugget, and judgements (assignments of nuggets to responses) for each response submitted by participants. While human evaluation is the most …...