Articles

. We propose a novel statistical approach to automatically generate Chinese couplets and Chinese poetry. For Chinese couplets, the system takes as input the first sentence and generates as output an N-best list of second sentences using a phrase-based SMT model. A comprehensive evaluation using both human judgments and BLEU …...

. Emotion is a complicated concept, and can be represented in different ways. In this paper, we discuss two kinds of emotion representations: the enumerative representation and the compositional representation. Compared to the enumerative representation, the compositional representation is the less rigid description of an emotion. However, from the perspective …...

. We describe ongoing research in the development of speech technologies that strives to raise the efficacy of computer-aided pronunciation training, especially for Chinese learners of English. Our approach is grounded on the theory of language transfer and involves a systematic phonological comparison between the primary language (L1 being Chinese) …...

. In this paper, we introduce a minimally supervised method for learning to classify named-entity titles in a given encyclopedia into broad semantic categories in an existing ontology. Our main idea involves using overlapping entries in the encyclopedia and ontology and a small set of 30 handed tagged parenthetic explanations …...

. Verb classifications have been used to support a number of practical tasks and ap- plications, such as parsing, information extraction, question-answering, and machine trans- lation. However, large-scale exploitation of verb classes in real-world or domain-sensitive tasks has not been possible because existing manually built classifications are incomprehen- sive. This …...

. This paper analyzes anaphoric links in conditional and quantificational structures in which more than one operator occurs. To this end, we adopt the indexing system and the basic principles of Dynamic Discourse Representation Theory proposed by Chung (2008a, 2008b, 2009) and extend them to the structures in question. We …...

. The purpose of designing the lexical semantic representation model E-HowNet is for natural language understanding. E-HowNet is a frame-based entity-relation model extended from HowNet to define lexical senses and achieving compositional semantics. The followings are major extension features of E-HowNet to achieve the goal. a) Word senses (concepts) are …...

In this paper, we introduce an automatic method for classifying a given question using broad semantic categories in an existing lexical database (i.e., WordNet) as the class tagset. For this, we also constructed a large scale entity supersense database that contains over 1.5 million entities to the 25 WordNet lexicographer’s …...

The BLEU scores and translation fluency for the current state-of-the-art SMT systems based on IBM models are still too low for publication purposes. The major issue is that stochastically generated sentences hypotheses, produced through a stack decoding process, may not strictly follow the natural target language grammar, since the decoding …...

A two-stage latent prosody model-language model (LPM-LM)-based approach is proposed to identify two Mandarin accent types spoken by native speakers in Mainland China and Taiwan. The frontend LPM tokenizes and jointly models the affections of speaker, tone and prosody state of an utterance. The backend LM takes the decoded prosody …...

This study examines the influence of lexical tone upon voice onset time (VOT) in Mandarin and Hakka. Examination of VOT values for Mandarin and Hakka word-initial stops /p, t, k, ph, th, kh/ followed by three vowels /i, u, a/ in different lexical tones revealed that lexical tone has a …...

Data acquisition is a major concern in text classification. The excessive human efforts required by conventional methods to build up quality training collection might not always be available to research workers. In this paper, we look into possibilities to automatically collect training data by sampling the Web with a set …...

It is difficult for users to formulate appropriate queries for search. In this paper, we propose an approach to query term selection by measuring the effectiveness of a query term in IR systems based on its linguistic and statistical properties in document collections. Two query formulation algorithms are presented for …...

In this paper, we investigate the noise-robustness of features based on the cepstral time coef- ficients (CTC). By cepstral time coefficients, we mean the coefficients obtained from applying the discrete cosine transform to the commonly used mel-frequency cepstral coefficients (MFCC). Fur- thermore, we apply temporal filters used for computing delta …...

User generated content is characterized by short, noisy documents, with many spelling errors and unexpected language usage. To bridge the vocabulary gap be- tween the user’s information need and documents in a specific user generated content environment, the blogosphere, we apply a form of query expansion, i.e., adding and reweighing …...

Web search quality can vary widely across languages, even for the same information need. We propose to exploit this variation in quality by learning a ranking function on bilingual queries: queries that appear in query logs for two languages but represent equivalent search interests. For a given bilingual query, along …...

While Active Learning (AL) has already been shown to markedly reduce the anno- tation efforts for many sequence labeling tasks compared to random selection, AL remains unconcerned about the internal structure of the selected sequences (typ- ically, sentences). We propose a semi- supervised AL approach for sequence la- beling where …...

We present a simple and scalable algorithm for clustering tens of millions of phrases and use the resulting clusters as features in discriminative classifiers. To demonstrate the power and generality of this approach, we apply the method in two very different applications: named entity recognition and query classification. Our results …...

The use of phrases in retrieval models has been proven to be helpful in the literature, but no particular research addresses the problem of discriminating phrases that are likely to degrade the retrieval performance from the ones that do not. In this paper, we present a retrieval framework that utilizes …...

We consider the language identification problem for search engine queries. First, we propose a method to automatically generate a data set, which uses click- through logs of the Yahoo! Search En- gine to derive the language of a query indi- rectly from the language of the documents clicked by the …...