Articles

Structured information plays a critical role in many NLP tasks, such as semantic relation ex- traction between named entities and semantic role labeling. This paper proposes a principled way to automatically generate constituent structure representation for tree kernel-based protein-protein interaction (PPI) extraction. The main idea behind our approach is that …...

Sparse learning framework, which is very popular in the field of nature language processing recently due to the advantages of efficiency and generalizability, can be applied to Conditional Random Fields (CRFs) with L1 regularization method. Stochastic gradient descent (SGD) method has been used in training L1-regularized CRFs, because it often …...

We present a method for characterizing a research work in terms of its focus, do- main of application, and techniques used. We show how tracing these aspects over time provides a novel measure of the in- fluence of research communities on each other. We extract these characteristics by matching semantic …...

Word Sense Disambiguation (WSD) is one of the fundamental natural language pro- cessing tasks. However, lack of train- ing corpora is a bottleneck to construct a high accurate all-words WSD system. Annotating a large-scale corpus by ex- perts costs enormous time and financial re- sources. Human Computation is a novel …...

The limitations of keyword-only ap- proaches to information retrieval were rec- ognized since the early days, specially in cases where different but closely-related words are used in the query and the rel- evant document. Query expansion tech- niques like pseudo-relevance feedback rely on the target document set in order to …...

We introduce a parallel corpus of spoken Can- tonese and written Chinese. This sentence- aligned corpus consists of transcriptions of Cantonese spoken in television programs in Hong Kong, and their corresponding Chinese (Mandarin) subtitles. Preliminary evaluation shows that the corpus reflects known syntactic differences between Cantonese and Mandarin, facilitates quantitative …...

Monolingual corpora which are aligned with similar text segments (paragraphs, sentences, etc.) are used to build and test a wide range of natural language processing applications. The drawback wanting to use them is the lack of publicly available an- notated corpora which obligates people to make one themselves. The annotation …...

In this paper we explore the effect of self- training on Hindi dependency parsing. We consider a state-of-the-art Hindi dependency parser and apply self-training by using a large raw corpus. We consider two types of raw corpus, one from same domain as of training and testing data and the other …...

Recent research usually models POS tag- ging as a sequential labeling problem, in which only local context features can be used. Due to the lack of morphological inflections, many tagging ambiguities in Chinese are difficult to handle unless con- sulting larger contexts. In this paper, we try to improve Chinese …...

The challenging issues of discourse relation recognition in Chinese are addressed. Due to the lack of Chinese discourse corpora, we construct a moderate corpus with human- annotated discourse relations. Based on the corpus, a statistical classifier is proposed, and various features are explored in the experi- ments. The experimental results …...

Non-standard spellings in text messages often convey extra pragmatic information not found in the standard word form. However, text message normalization sys- tems that transform non-standard text mes- sage spellings to standard form tend to ignore this information. To address this problem, this paper examines the types of extra pragmatic …...

Information need is an important factor in question retrieval. This paper proposes a method to diversify the results of question retrieval in term of types of information needs. CogQTaxo, a question hierarchy is leveraged to represent users’ information needs cognitively from three linguistic levels. Based on a prediction model of …...

In this study, we analyzed how answerers indicated unclear points in questions, and how questioners modified and resubmitted their questions based on indications of un- clear points. 1...

A learner’s language data of speaking, writing, listening, and reading have been compiled for a learner corpus in this study. The language data consist of linguistic output and language processing. Linguistic output refers to data of pronunciation, sentences, listening compre- hension rate, and reading comprehension rate. Language processing refers to …...

The world of E-commerce is expanding, pos- ing a large arena of products, their descrip- tions, customer and professional reviews that are pertinent to them. Most of the prod- uct attribute extraction techniques in litera- ture work on structured descriptions using sev- eral text analysis tools. However, attributes in these …...

Online forum is an important source that people use to find answers to questions. Most search engines simply retrieve “rele- vant” threads, but those are not necessarily good threads in terms of providing qual- ity answers. In this paper we propose a two-step approach to classify online forum threads according …...

Traditional approaches to semantic relat- edness are often restricted to text-based methods, which typically disregard other multimodal knowledge sources. In this paper, we propose a novel image-based metric to estimate the relatedness of words, and demonstrate the promise of this method through comparative evalua- tions on three standard datasets. We …...

We describe a new semantic relatedness mea- sure combining the Wikipedia-based Explicit Semantic Analysis measure, the WordNet path measure and the mixed collocation index. Our measure achieves the currently highest results on the WS-353 test: a Spearman ρ coeffi- cient of 0.79 (vs. 0.75 in (Gabrilovich and Markovitch, 2007)) when …...

In this paper, we compare a resource- driven approach with a task-specific clas- sification model for a new near-synonym word choice sub-task, predicting whether a full or a clipped form of a word will be used (e.g. doctor or doc) in a given con- text. Our results indicate that the …...

We propose an unsupervised bootstrapping method to generate a new type of affect knowl- edge base: the sentiment expectation of nouns (e.g., “high salary” is desirable while “high price” is usually undesirable, because peo- ple have opposite sentiment expectation to- wards “salary” and “price”). A bootstrapping framework is designed to …...