We describe our entry in the CoNLL-X shared task. The system consists of three phases: a probabilistic vine parser (Eisner and N. Smith, 2005) that produces unlabeled dependency trees, a probabilistic relation-labelin...
详细信息
We describe our entry in the CoNLL-X shared task. The system consists of three phases: a probabilistic vine parser (Eisner and N. Smith, 2005) that produces unlabeled dependency trees, a probabilistic relation-labeling model, and a discriminative minimum risk reranker (D. Smith and Eisner, 2006). The system is designed for fast training and decoding and for high precision. We describe sources of crosslingual error and ways to ameliorate them. We then provide a detailed error analysis of parses produced for sentences in German (much training data) and Arabic (little training data).
We present and empirically compare a range of novel probabilistic finite-state transducer (PFST) models targeted at two major natural language string transduction tasks, transliteration selection and cognate translati...
详细信息
We describe finite-state constraint relaxation, a method for applying global constraints, expressed as automata, to sequence model decoding. We present algorithms for both hard constraints and binary soft constraints....
详细信息
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural language problems is piecewise constant and r...
详细信息
Many syntactic models in machine translation are channels that transform one tree into another, or synchronous grammars that generate trees in parallel. We present a new model of the translation process: quasi-synchro...
详细信息
We present a Weighted Finite State Transducer Translation Template Model for statistical machine translation. This is a source-channel model of translation inspired by the Alignment Template translation model. The mod...
详细信息
A framework for dialectal Chinese speech recognition is proposed and studied, in which a relatively small dialectal Chinese （or in other words Chinese influenced by the native dialect） speech corpus and dialect-rela...
详细信息
A framework for dialectal Chinese speech recognition is proposed and studied, in which a relatively small dialectal Chinese （or in other words Chinese influenced by the native dialect） speech corpus and dialect-related knowledge are adopted to transform a standard Chinese （or Putonghua, abbreviated as PTH） speech recognizer into a dialectal Chinese speech recognizer. Two kinds of knowledge sources are explored： one is expert knowledge and the other is a small dialectal Chinese corpus. These knowledge sources provide information at four levels： phonetic level, lexicon level, language level, and acoustic decoder level. This paper takes Wu dialectal Chinese （WDC） as an example target language. The goal is to establish a WDC speech recognizer from an existing PTH speech recognizer based on the Initial-Final structure of the Chinese language and a study of how dialectal Chinese speakers speak Putonghua. The authors propose to use contextindependent PTH-IF mappings （where IF means either a Chinese Initial or a Chinese Final）, context-independent WDC-IF mappings, and syllable-dependent WDC-IF mappings （obtained from either experts or data）, and combine them with the supervised maximum likelihood linear regression （MLLR） acoustic model adaptation method. To reduce the size of the multipronunciation lexicon introduced by the IF mappings, which might also enlarge the lexicon confusion and hence lead to the performance degradation, a Multi-Pronunciation Expansion （MPE） method based on the accumulated uni-gram probability （AUP） is proposed. In addition, some commonly used WDC words are selected and added to the lexicon. Compared with the original PTH speech recognizer, the resulting WDC speech recognizer achieves 10-18% absolute Character Error Rate （CER） reduction when recognizing WDC, with only a 0.62% CER increase when recognizing PTH. The proposed framework and methods are expected to work not only for Wu dialectal Chinese but also for other dialectal Chinese languages and
We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP without supervision into NP[0] and NP[1], wh...
详细信息
In a principal-agent problem, a principal seeks to motivate an agent to take a certain action beneficial to the principal, while spending as little as possible on the reward. This is complicated by the fact that the p...
详细信息
ISBN:
(纸本)1595933832
In a principal-agent problem, a principal seeks to motivate an agent to take a certain action beneficial to the principal, while spending as little as possible on the reward. This is complicated by the fact that the principal does not know the agent's utility function (or type). We study the online setting where at each round, the principal encounters a new agent, and the principal sets the rewards anew. At the end of each round, the principal only finds out the action that the agent took, but not his type. The principal must learn how to set the rewards optimally. We show that this setting generalizes the setting of selling a digital good online. We study and experimentally compare three main approaches to this problem. First, we show how to apply a standard bandit algorithm to this setting. Second, for the case where the distribution of agent types is fixed (but unknown to the principal), we introduce a new gradient ascent algorithm. Third, for the case where the distribution of agents' types is fixed, and the principal has a prior belief (distribution) over a limited class of type distributions, we study a Bayesian approach.
The paper presents a bilingual English-Spanish parallel corpus aligned at the paragraph level. The corpus consists of twelve large novels found in Internet and converted into text format with manual correction of form...
详细信息
暂无评论