Articles

Entity linking disambiguates a mention of an entity in text to a Knowledge Base (KB). Most previous studies disambiguate a mention of a name (e.g.“AZ”) based on the distribution knowledge learned from labeled instances, which are related to other names (e.g.“Hoffman”,“Chad Johnson”, etc.). The gaps among the distributions of the …...

Previous joint models of Chinese part-of-speech (POS) tagging and dependency parsing are extended from either graph- or transition-based dependency models. Our analysis shows that the two models have different error distributions. In addition, integration of graph- and transition-based dependency parsers by stacked learning (stacking) has achieved significant improvements. These motivate …...

Abbreviation is a common linguistic phenomenon with wide popularity and high rate of growth. Correctly linking full forms to their abbreviations will be helpful in many applications. For example, it can improve the recall of information retrieval systems. An intuition to solve this is to build an abbreviation dictionary in …...

Parse trees are indispensable to the existing tree-based translation models. However, there exist two major challenges in utilizing parse trees: 1) For most language pairs, it is hard to get parse trees due to the lack of syntactic resources for training. 2) Numerous parse trees are not compatible with word …...

Automatic detection of sentence errors is an important NLP task and is valuable to assist foreign language learners. In this paper, we investigate the problem of word ordering errors in Chinese sentences and propose classifiers to detect this type of errors. Word n-gram features in Google Chinese Web 5-gram corpus …...

We present a novel scheme of language modeling for a spoken dialogue system by effectively filtering query sentences collected via a Web site of wisdom of crowds. Our goal is a speech- based information navigation system by retrieving from backend documents such as Web news. Then, we expect that users …...

Extractive multi-document summarization is mostly treated as a sentence ranking problem. Existing graph-based ranking methods for key-sentence extraction usually attempt to compute a global importance score for each sentence under a single relation. Motivated by the fact that both documents and sentences can be presented by a mixture of semantic …...

Most existing learning to rank based summarization methods only used content relevance of sentences with respect to queries to rank or estimate sentences, while neglecting sentence relationships. In our work, we propose a novel model, RelationListwise, by integrating relation information among all the estimated sentences into listMLE-Top K, a basic …...

This paper presents a novel method of measuring the similarity between TV programs by using summaries of the Electronic Program Guide (EPG). Most previous methods use statistics such as the TFIDF based cosine measure of word vectors, whose elements are words appearing in the summaries. However, these approaches are not …...

Machine translation aims to generate a target sentence that is semantically equivalent to the source sentence. However, most of current statistical machine translation models do not model the semantics of sentences. In this paper, we propose a novel translation framework based on predicate-argument structure (PAS) for its capacity on grasping …...

Automatic error correction systems for English as a Second Language(ESL) speakers often rely on the use of a confusion set to limit the choices of possible correction candidates. Typically, the confusion sets are either manually constructed or extracted from a corpus of manually corrected ESL writings. Both options require the …...

We present initial investigation into the task of paraphrasing language while targeting a particular writing style. The plays of William Shakespeare and their modern translations are used as a testbed for evaluating paraphrase systems targeting a specific style of writing. We show that even with a relatively small amount of …...

We present a global log-linear model for synchronous grammar induction, which is capable of incorporating arbitrary features. The parameters in the model are trained in an unsuper- vised fashion from parallel sentences without word alignments. To make parameter training tractable, we also propose a novel and efficient cube pruning based …...

Recently, various unsupervised representation learning approaches have been investigated to produce augmenting features for natural language processing systems in the open-domain learning scenarios. In this paper, we propose a dynamic dependency network model to conduct semi-supervised representation learning. It exploits existing task-specific labels in the source domain in addition to …...

Among various neural network language models (NNLMs), recurrent neural network-based lan- guage models (RNNLMs) are very competitive in many cases. Most current RNNLMs only use one single feature stream, i.e., surface words. However, previous studies proved that language models with additional linguistic information achieve better performance. In this study, we …...

Subjectivity analysis has received increasing attention in natural language processing field. Most of the subjectivity analysis works however are conducted on single languages. In this paper, we propose to perform multilingual subjectivity analysis by combining multi-view learn- ing and AdaBoost techniques. We aim to show that by boosting multi-view classifiers …...

One of the biggest bottlenecks for conversational systems is large-scale provision of suitable content. In this paper, we present the use of content mined from online question-and-answer forums to automatically construct system utterances. Although this content is mined in the form of question-answer pairs, our system is able to use …...

Together with the ever-growing amount of Chinese web data, the number of opinions voiced by Chinese users is rapidly increasing, and analyzing them is an important task. This paper intro- duces a Chinese Evaluative Information Analyzer (CEIA) and proposes a method to improve its performance. We use evaluative information as …...

Implicit discourse relation recognition is a challenging task in the natural language processing field, but important to many applications such as question answering, summarization and so on. Previous research used either artificially created implicit discourse relations with connectives removed from explicit relations or annotated implicit relations as training data to …...

Online discussion forums are a valuable means for users to resolve specific information needs, both interactively for the participants and statically for users who search/browse over historical thread data. However, the complex structure of forum threads can make it difficult for users to extract relevant information. Automatically identifying whether the …...