SFS-TUE: Compound Paraphrasing with a Language Model and Discriminative Reranking
نویسنده
چکیده
This paper presents an approach for generating free paraphrases of compounds (task 4 at SemEval 2013) by decomposing the training data into a collection of templates and fillers and recombining/scoring these based on a generative language model and discriminative MaxEnt reranking. The system described in this paper achieved the highest score (with a very small margin) in the (default) isomorphic setting of the scorer, for which it was optimized, at a disadvantage to the non-isomorphic score.
منابع مشابه
Survey on Three Reranking Models for Discriminative Parsing
This survey is inspired by the so-called reranking techniques in natural language processing (NLP). The aim of this survey is to provide an overview of three main reranking tasks particularly for discriminative parsing. We will focus on the motivation for discriminative reranking, on the three models, boosting model, support vector machine (SVM) model and voted perceptron model, on the procedur...
متن کاملDiscriminative Reranking for Semantic Parsing
Semantic parsing is the task of mapping natural language sentences to complete formal meaning representations. The performance of semantic parsing can be potentially improved by using discriminative reranking, which explores arbitrary global features. In this paper, we investigate discriminative reranking upon a baseline semantic parser, SCISSOR, where the composition of meaning representations...
متن کاملStratégies discriminantes pour intégrer la reconnaissance des mots composés dans un analyseur syntaxique en constituants
We propose two discriminative strategies to integrate compound word recognition in a parsing context: (i) compound pregrouping with Conditional Random Fields before parsing, (ii) reranking parses with a maximum entropy model after parsing. These discriminative models integrate features dedicated to compounds, some of theme being computed from external lexical resources. We show that the pregrou...
متن کاملPerceptron Reranking for CCG Realization
This paper shows that discriminative reranking with an averaged perceptron model yields substantial improvements in realization quality with CCG. The paper confirms the utility of including language model log probabilities as features in the model, which prior work on discriminative training with log linear models for HPSG realization had called into question. The perceptron model allows the co...
متن کاملDiscriminative Syntactic Language Modeling for Speech Recognition
We describe a method for discriminative training of a language model that makes use of syntactic features. We follow a reranking approach, where a baseline recogniser is used to produce 1000-best output for each acoustic input, and a second “reranking” model is then used to choose an utterance from these 1000-best lists. The reranking model makes use of syntactic features together with a parame...
متن کامل