This paper presents a fuzzy set theory based approach to Chinese sentence-level sentiment classification. Compared with traditional topic-based text classification techniques, the fuzzy set theory provides a straightforward way to model the intrinsic fuzziness between sentiment polarity classes. To approach fuzzy sentiment classification, we first propose a fine-to-coarse strategy to estimate s...

We propose a novel discriminative ranking model that learns embeddings from multilingual and multi-modal data, meaning that our model can take advantage of images and descriptions in multiple languages to improve embedding quality. To that end, we introduce an objective function that uses pairwise ranking adapted to the case of three or more input sources. We compare our model against different...

We introduce a corpus of 7,032 sentences rated by human annotators for formality, informativeness, and implicature on a 1-7 scale. The corpus was annotated using Amazon Mechanical Turk.1 Reliability in the obtained judgments was examined by comparing mean ratings across two MTurk experiments, and correlation with pilot annotations (on sentence formality) conducted in a more controlled setting. ...

Sentiment classification is a fundamental task in opinion mining. However, most existing systems require a sentiment lexicon to guide sentiment classification, which inevitably suffer from the problem of unknown words. In this paper, we present a morpheme-based fine-to-coarse strategy for Chinese sentence-level sentiment classification. To approach this, we first employ morphological productivi...

There is a small but growing body of research on statistical scripts, models of event sequences that allow probabilistic inference of implicit events from documents. These systems operate on structured verb-argument events produced by an NLP pipeline. We compare these systems with recent Recurrent Neural Net models that directly operate on raw tokens to predict sentences, finding the latter to ...

While speaking spontaneously, speakers often make errors such as self-correction or false starts which interfere with the successful application of natural language processing techniques like summarization and machine translation to this data. There is active work on reconstructing this errorful data into a clean and fluent transcript by identifying and removing these simple errors. Previous re...

In this paper, emotion analysis on blog texts has been carried out for a less privileged language like Bengali. Ekman’s six basic emotion types have been selected for reliable and semi automatic word level annotation. An automatic classifier has been applied for recognizing six basic emotion types for different words in a sentence. Application of different scoring strategies to identify sentenc...

The current study used event-related brain potentials (ERPs) and behavioral measures to examine effects of genre awareness on sentence processing and evaluation. We hypothesized that genre awareness modulates effects of genre-typical manipulations. We manipulated instructions between participants, either specifying a genre (poetry) or not (neutral). Sentences contained genre-typical variations ...

We investigate the problem of predicting the quality of sentences produced by machine translation systems when reference translations are not available. The problem is addressed as a regression task and a method that takes into account the contribution of different features is proposed. We experiment with this method for translations produced by various MT systems and different language pairs, ...

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 challenges by incorporating the label dependence among the emotion labels and the context dependence among the contextual instances into a factor graph model. Specifically, we rec...