Articles

“Deep-syntactic” dependency structures that capture the argumentative, attributive and coordi- native relations between full words of a sentence have a great potential for a number of NLP- applications. The abstraction degree of these structures is in-between the output of a syntactic dependency parser (connected trees defined over all words of …...

In this paper, we investigate the differences between Hungarian sentence parses based on auto- matically converted and manually annotated dependency trees. We also train constituency parsers on the manually annotated constituency treebank and then convert their output to dependency trees. We argue for the importance of training on gold standard …...

We present an effective modification of the popular Brown et al. 1992 word clustering algorithm, using a dependency language model. By leveraging syntax-based context, resulting clusters are better when evaluated against a wordnet for Dutch. The improvements are stable across parameters such as number of clusters, minimum frequency and granularity. …...

We introduce the concept of hybrid grammars, which are extensions of synchronous grammars, obtained by coupling of lexical elements. One part of a hybrid grammar generates linear struc- tures, another generates hierarchical structures, and together they generate discontinuous struc- tures. This formalizes and generalizes some existing mechanisms for dealing with …...

Target-polarity word (T-P) collocation extraction, a basic sentiment analysis task, relies primarily on syntactic features to identify the relationships between targets and polarity words. A major problem of current research is that this task focuses on customer reviews, which are natural or spontaneous, thus posing a challenge to syntactic parsers. …...

Latent models for opinion classification are studied. Training a probabilistic model with a number of latent variables is found unstable in some cases; thus this paper presents how to construct a stable model for opinion classification by constraining classification transitions. The baseline model is a CRF classification model with plural …...

In this paper, we develop a novel semi-supervised learning algorithm called hybrid deep be- lief networks (HDBN), to address the semi-supervised sentiment classification problem with deep learning. First, we construct the previous several hidden layers using restricted Boltzmann machines (RBM), which can reduce the dimension and abstract the information of …...

Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or neg- ative) of user-generated sentiment data (e.g., reviews, blogs). To obtain sentiment classifica- tion with high accuracy, supervised techniques require a large amount of manually labeled data. The labeling work can be time-consuming and expensive, which makes unsupervised (or …...

Recently the research on supervised term weighting has attracted growing attention in the field of Tradi- tional Text Categorization (TTC) and Sentiment Analysis (SA). Despite their impressive achievements, we show that existing methods more or less suffer from the problem of over-weighting. Overlooked by prior studies, over-weighting is a new …...

In this paper, we study the task of product record linkage across multiple e-commerce web- sites. We solve this task via a semi-supervised approach and adopt the self-training algorithm for learning with little labeled data. In previous self-training algorithms, the learner tries to convert the most confidently predicted unlabeled examples …...

Word sense induction is an unsupervised task to find and characterize different senses of polyse- mous words. This work investigates two unsupervised approaches that focus on using distribu- tional word statistics to cluster the contextual information of the target words using two different algorithms involving latent dirichlet allocation and spectral …...

We consider multilingual semantic parsing – the task of simultaneously parsing semantically equivalent sentences from multiple different languages into their corresponding formal semantic representations. Our model is built on top of the hybrid tree semantic parsing framework, where natural language sentences and their corresponding semantics are assumed to be generated …...

We address the problem of transferring semantic annotations to new languages using parallel corpora. Previous work has transferred these annotations on a token-to-token basis, an approach that is sensitive to alignment errors and translation shifts. We present a global approach to transfer that aggregates information across the whole parallel corpus …...

Non-literal expression recognition is a challenging task in natural language processing. An ironic expression implies the opposite of the literal meaning, causing problems in opinion mining and sentiment analysis. In this paper, ironic messages are collected from microblogs to form an irony corpus based on the use of emoticons, linguistic …...

Although hyperlinks enhance the utility of Wikipedia, embedding them in articles imposes a burden on contributors. To alleviate this burden as well as enrich hyperlinks in Wikipedia articles, we propose a method for transferring intra-language links between different-language articles linked via an inter- language link. The method avoids anchor selection …...

Inference about whether a word in one text has similar meaning to another word in the other text is an essential task in order to understand whether two texts have similar meaning. However, this inference becomes difficult especially when two words do not share a lexical root, do not have …...

We propose the use of a game with a purpose (GWAP) to facilitate crowd-sourcing of phrase- equivalents, as an alternative to expert or paid crowd-sourcing. Doodling is an online multi- player game, in which one player (drawer), draws pictures on a shared board to get the other players (guessers) to …...

Most previous research on authorship attribution (AA) assumes that the training and test data are drawn from same distribution. But in real scenarios, this assumption is too strong. The goal of this study is to improve the prediction results in cross-topic AA (CTAA), where the training data comes from one …...

This paper integrates techniques in natural language processing and computer vision to improve recognition and description of entities and activities in real-world videos. We propose a strategy for generating textual descriptions of videos by using a factor graph to combine visual detections with language statistics. We use state-of-the-art visual recognition …...

Graph-based learning algorithms have been shown to be an effective approach for query-focused multi-document summarization (MDS). In this paper, we extend the standard graph ranking algo- rithm by proposing a two-layer (i.e. sentence layer and topic layer) graph-based semi-supervised learning approach based on topic modeling techniques. Experimental results on TAC …...