Articles

Neural probabilistic parsers are attrac- tive for their capability of automatic fea- ture combination and small data sizes. A transition-based greedy neural parser has given better accuracies over its lin- ear counterpart. We propose a neural probabilistic structured-prediction model for transition-based dependency parsing, which integrates search and learning. Beam search …...

Incremental parsing is the task of assign- ing a syntactic structure to an input sen- tence as it unfolds word by word. Incre- mental parsing is more difficult than full- sentence parsing, as incomplete input in- creases ambiguity. Intuitively, an incre- mental parser that has access to seman- tic information …...

Given a set of basic binary features, we propose a new L1 norm SVM based feature selection method that explicitly selects the features in their polynomial or tree kernel spaces. The efficiency comes from the anti-monotone property of the subgradients: the subgradient with respect to a combined feature can be …...

Constituent parsing is typically modeled by a chart-based algorithm under prob- abilistic context-free grammars or by a transition-based algorithm with rich fea- tures. Previous models rely heavily on richer syntactic information through lex- icalizing rules, splitting categories, or memorizing long histories. However en- riched models incur numerous parameters and sparsity …...

In this work, we address the prob- lem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntac- tic and compositional-semantic represen- tations of phrases and words in a depen- dency tree. …...

Dependency parsers are usually evaluated on attachment accuracy. Whilst easily in- terpreted, the metric does not illustrate the cascading impact of errors, where the parser chooses an incorrect arc, and is sub- sequently forced to choose further incor- rect arcs elsewhere in the parse. We apply arc-level constraints to MST- …...

The performance of discriminative con- stituent parsing relies crucially on feature engineering, and effective features usu- ally have to be carefully selected through a painful manual process. In this paper, we propose to automatically learn a set of effective features via neural networks. Specifically, we build a feedforward neu- ral …...

Semantic role labeling (SRL) is one of the basic natural language processing (NLP) problems. To this date, most of the suc- cessful SRL systems were built on top of some form of parsing results (Koomen et al., 2005; Palmer et al., 2010; Pradhan et al., 2013), where pre-defined feature tem- …...

We present an extension to incremental shift-reduce parsing that handles discon- tinuous constituents, using a linear clas- sifier and beam search. We achieve very high parsing speeds (up to 640 sent./sec.) and accurate results (up to 79.52 F1 on TiGer). 1...

Complex conjunctions and determiners are often considered as pretokenized units in parsing. This is not always realistic, since they can be ambiguous. We pro- pose a model for joint dependency parsing and multiword expressions identification, in which complex function words are rep- resented as individual tokens linked with morphological dependencies. …...

Natural language generation of coherent long texts like paragraphs or longer doc- uments is a challenging problem for re- current networks models. In this paper, we explore an important step toward this generation task: training an LSTM (Long- short term memory) auto-encoder to pre- serve and reconstruct multi-sentence para- graphs. …...

ROVER is a widely used method to combine the output of multiple auto- matic speech recognition (ASR) systems. Though effective, the basic approach and its variants suffer from potential draw- backs: i) their results depend on the order in which the hypotheses are used to feed the combination process, ii) …...

In this paper, we address the problem of evaluating spontaneous speech us- ing a combination of machine learning and crowdsourcing. Machine learning techniques inadequately solve the stated problem because automatic speaker- independent speech transcription inaccurate. The features derived from itis are also inaccurate and so is the machine learning model …...

We investigate a technique to adapt unsu- pervised word embeddings to specific ap- plications, when only small and noisy la- beled datasets are available. Current meth- ods use pre-trained embeddings to initial- ize model parameters, and then use the la- beled data to tailor them for the intended task. However, …...

This paper tackles the issue of the detec- tion of user’s verbal expressions of likes and dislikes in a human-agent interaction. We present a system grounded on the theo- retical framework provided by (Martin and White, 2005) that integrates the interac- tion context by jointly processing agent’s and user’s utterances. …...

A review text is normally represented as a bag-of-words (BOW) in sentiment clas- sification. Such a simplified BOW model has fundamental deficiencies in modeling some complex linguistic phenomena such as negation. In this work, we propose a dual-view co-training algorithm based on dual-view BOW representation for semi- supervised sentiment classification. …...

Predicting emotion categories, such as anger, joy, and anxiety, expressed by a sentence is challenging due to its inherent multi-label classification difficulty and data sparseness. In this paper, we address above two chal- lenges by incorporating the label dependence among the emotion labels and the context de- pendence among the …...

Automatically detecting verbal irony (roughly, sarcasm) in online content is important for many practical applications (e.g., sentiment detection), but it is dif- ficult. Previous approaches have relied predominantly on signal gleaned from word counts and grammatical cues. But such approaches fail to exploit the context in which comments are embedded. …...

Central to many sentiment analysis tasks are sentiment lexicons (SLs). SLs exhibit polarity inconsistencies. Previous work studied the problem of checking the con- sistency of an SL for the case when the en- tries have categorical labels (positive, neg- ative or neutral) and showed that it is NP- hard. In …...

Neural network methods have achieved promising results for sentiment classifica- tion of text. However, these models on- ly use semantics of texts, while ignoring users who express the sentiment and prod- ucts which are evaluated, both of which have great influences on interpreting the sentiment of text. In this paper, …...