Articles

The newly-developed prosody module of our text-to-speech (TTS) system is described in the paper. We present two main works on it’s establishment and improvement. On the basis of potential factors influencing prosody parameters, inclusive of duration, pitch and intensity, the prosody model is built as groundwork of this module which …...

. Researches in speech synthesis and speech analysis are underpinned by the databases they used. The performance of an emotion classifier relies heavily on the qualities of the training and testing data. A good database can make researches in these fields achieving better results. Hearing-impaired people are poor in presenting …...

. In order to build an automatic named entity recognition (NER) system for machine learning, a large tagged corpus is necessary. This paper describes the manual construction of a Chinese named entity tagged corpus (CNEC 1.0) that can be used to improve NER performance. In this project, we define five …...

Most statistical parsers have used the gram- mar induction approach, in which a stochastic grammar is induced from a treebank. An alter- native approach is to induce a controller for a given parsing automaton. Such controllers may be stochastic; here, we focus on greedy con- trollers, which result in deterministic …...

Active learning (AL) promises to reduce the cost of annotating labeled datasets for trainable human language technologies. Contrary to expectations, when creating labeled training material for HPSG parse selection and later reusing it with other models, gains from AL may be negligible or even negative. This has serious impli- cations …...

We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying sup- port vector machines. Our formulation uses a factor- ization analogous to the standard dynamic programs for parsing. In particular, it allows one to efficiently learn a model which discriminates among the entire space of parse …...

In this paper we describe a biography summarization system using sentence classification and ideas from information retrieval. Although the individual techniques are not new, assembling and applying them to generate multi-document biographies is new. Our system was evaluated in DUC2004. It is among the top performers in task 5–short summaries …...

We compare and contrast two different models for detecting sentence-like units in continuous speech. The first approach uses hidden Markov sequence models based on N-grams and maximum likeli- hood estimation, and employs model interpolation to combine different representations of the data. The second approach models the posterior proba- bilities of …...

We describe how simple, commonly understood statisti- cal models, such as statistical dependency parsers, proba- bilistic context-free grammars, and word-to-word trans- lation models, can be effectively combined into a uni- fied bilingual parser that jointly searches for the best En- glish parse, Korean parse, and word alignment, where these hidden …...

Paraphrase recognition is a critical step for nat- ural language interpretation. Accordingly, many NLP applications would benefit from high coverage knowledge bases of paraphrases. However, the scal- ability of state-of-the-art paraphrase acquisition ap- proaches is still limited. We present a fully unsuper- vised learning algorithm for Web-based extraction of entailment …...

Broad-coverage repositories of semantic relations between verbs could benefit many NLP tasks. We present a semi-automatic method for extracting fine-grained semantic relations between verbs. We detect similarity, strength, antonymy, enablement, and temporal happens-before relations between pairs of strongly associated verbs using lexico- syntactic patterns over the Web. On a set …...

This paper explores the large-scale acquisition of sense-tagged examples for Word Sense Disam- biguation (WSD). We have applied the “WordNet monosemous relatives” method to construct auto- matically a web corpus that we have used to train disambiguation systems. The corpus-building pro- cess has highlighted important factors, such as the distribution …...

This paper presents our work on Semantic Role Labeling using a Transformation-Based Error- Driven approach in the style of Eric Brill (Brill, 1995). Our approach achieved an overall F1 score of 43.48 on non-verb annotations. We believe our approach is noteworthy because of its novelty in this area and because …...

We present a system submitted to the CoNLL- 2004 shared task for semantic role labeling. The system is composed of a set of classifiers and an inference procedure used both to clean the classification results and to ensure struc- tural integrity of the final role labeling. Lin- guistic information is …...

In this study, we try to apply SVMs to the se- mantic role labeling task, which is one of the multiclass problems. As a result, we propose a two-phase semantic role labeling model which consists of the identification phase and the clas- sification phase. We first identify semantic ar- guments, …...

In this paper, we propose a semantic role label- ing method using a maximum entropy model, which enables not only to exploit rich features but also to alleviate the data sparseness prob- lem in a well-founded model. For applying the maximum entropy model to semantic role la- beling, we take …...

In this paper, we present a semantic role la- beler (or chunker) that groups syntactic chunks (i.e. base phrases) into the arguments of a pred- icate. This is accomplished by casting the se- mantic labeling as the classification of syntactic chunks (e.g. NP-chunk, PP-chunk) into one of several classes such …...

Probabilistic models have been effective in re- solving prepositional phrase attachment am- biguity, but sparse data remains a significant problem. We propose a solution based on similarity-based smoothing, where the proba- bility of new PPs is estimated with informa- tion from similar examples generated using a thesaurus. Three thesauruses are …...

Semantic similarity measures have focused on individual word senses. However, in many ap- plications, it may be informative to compare the overall sense distributions for two differ- ent contexts. We propose a new method for comparing two probability distributions over WordNet, which captures in a single measure the aggregate semantic …...

We address the problem dealing with a large collection of data, and investigate the use of automatically constructing category hierarchy from a given set of categories to improve clas- sification of large corpora. We use two well- known techniques, partitioning clustering, �- means and a � ��� � ������� to …...