Articles

This paper presents two approaches to ranking reader emotions of documents. Past studies assign a document to a single emotion cate- gory, so their methods cannot be applied di- rectly to the emotion ranking problem. Furthermore, whereas previous research ana- lyzes emotions from the writer’s perspective, this work examines readers’ …...

The intersection of tree transducer-based translation models with n-gram language models results in huge dynamic programs for machine translation decoding. We propose a multipass, coarse-to-fine approach in which the language model complexity is incremen- tally introduced. In contrast to previous order- based bigram-to-trigram approaches, we fo- cus on encoding-based methods, …...

This paper presents a new hypothesis alignment method for combining outputs of multiple machine translation (MT) systems. An indirect hidden Markov model (IHMM) is proposed to address the synonym matching and word ordering issues in hypothesis alignment. Unlike traditional HMMs whose parameters are trained via maximum likelihood estimation (MLE), the …...

This paper proposes a novel maximum en- tropy based rule selection (MERS) model for syntax-based statistical machine transla- tion (SMT). The MERS model combines lo- cal contextual information around rules and information of sub-trees covered by variables in rules. Therefore, our model allows the de- coder to perform context-dependent rule …...

We present a study on how grammar binariza- tion empirically affects the efficiency of the CKY parsing. We argue that binarizations af- fect parsing efficiency primarily by affecting the number of incomplete constituents gener- ated, and the effectiveness of binarization also depends on the nature of the input. We pro- …...

Most Web-based Q/A systems work by find- ing pages that contain an explicit answer to a question. These systems are helpless if the answer has to be inferred from multiple sen- tences, possibly on different pages. To solve this problem, we introduce the HOLMES sys- tem, which utilizes textual inference …...

We present a PropBank semantic role label- ing system for English that is integrated with a dependency parser. To tackle the problem of joint syntactic–semantic analysis, the sys- tem relies on a syntactic and a semantic sub- component. The syntactic model is a projec- tive parser using pseudo-projective transfor- mations, …...

We propose a new approach to language mod- eling which utilizes discriminative learning methods. Our approach is an iterative one: starting with an initial language model, in each iteration we generate 'false' sentences from the current model, and then train a clas- sifier to discriminate between them and sen- tences …...

We present a discriminative method for learn- ing selectional preferences from unlabeled text. Positive examples are taken from ob- served predicate-argument pairs, while nega- tives are constructed from unobserved combi- nations. We train a Support Vector Machine classifier to distinguish the positive from the negative instances. We show how to …...

Having seen a news title “Alba denies wedding reports”, how do we infer that it is primar- ily about Jessica Alba, rather than about wed- dings or reports? We probably realize that, in a randomly driven sentence, the word “Alba” is less anticipated than “wedding” or “reports”, which adds value …...

Regular expressions have served as the dom- inant workhorse of practical information ex- traction for several years. However, there has been little work on reducing the manual ef- fort involved in building high-quality, com- plex regular expressions for information ex- traction tasks. In this paper, we propose Re- LIE, a …...

Automatic processing of medical dictations poses a significant challenge. We approach the problem by introducing a statistical frame- work capable of identifying types and bound- aries of sections, lists and other structures occurring in a dictation, thereby gaining ex- plicit knowledge about the function of such elements. Training data is …...

Contradiction Detection (CD) in text is a difficult NLP task. We investigate CD over functions (e.g., BornIn(Person)=Place), and present a domain-independent algorithm that automatically discovers phrases denoting functions with high precision. Previous work on CD has investigated hand-chosen sentence pairs. In contrast, we automatically harvested from the Web pairs of …...

. The automatic extraction of biographical information from business news is a com- plex task. This approach deals with the characterization of the so called biographical relations by means of local grammars. In order to provide a well-founded proceeding, it is necessary to give a complete and accurate definition of …...

. This work is part of a large research project entitled "Oreillodule" aimed at developing tools for automatic speech recognition, translation, and synthesis for Arabic language. Our attention has mainly been focused on an attempt to present the semantic analyzer developed for the automatic comprehension of the standard spontaneous arabic …...

. This paper addresses semantic ellipsis control in language generation for human- computer dialogue. For this, the rhetorical structure of the dialogue is used, as well as a repository of facts that are accepted by the recipient of the utterance. Rhetorical structure is represented in the framework of SDRT, where …...

. The aim of this paper is to present a description of antonym constructions, which is integrated in a formal grammar of spontanous french in order to allow its use for NLP. The characteristic of these constructions is to be simultaneously constrained at many different levels (lexicon, syntax, semantics and …...

. We present in this paper how Prolexbase can be expressed within the LMF (Language resource management - Lexical Markup Framework) ISO project framework. Prolexbase is a lexical resource of proper names, organized according to an onomasiological view, with entries based on the concept of conceptual proper name. In the …...

. We introduce an error mining technique for automatically detecting errors in re- sources that are used in parsing systems. We applied this technique to parsing results produced on several million words by two distinct parsing systems, which share the syntactic lexicon and the pre-parsing processing chain. We are thus …...

. Unknown words are a well-known hindrance to natural language applications. In particular, they drastically impact machine translation quality. An easy way out commercial translation systems usually offer their users is the possibility to add unknown words and their translations into a dedicated lexicon. Recently, (Stroppa et Yvon, 2005) shown …...