Articles

We present a word alignment framework that can incorporate partial manual align- ments. The core of the approach is a novel semi-supervised algorithm extend- ing the widely used IBM Models with a constrained EM algorithm. The par- tial manual alignments can be obtained by human labelling or automatically by high-precision-low-recall …...

This paper describes our Statistical Ma- chine Translation systems for the WMT10 evaluation, where LIMSI participated for two language pairs (French-English and German-English, in both directions). For German-English, we concentrated on nor- malizing the German side through a proper preprocessing, aimed at reducing the lex- ical redundancy and at splitting …...

This paper presents the results of the WMT10 and MetricsMATR10 shared tasks,1 which included a translation task, a system combination task, and an eval- uation task. We conducted a large-scale manual evaluation of 104 machine trans- lation systems and 41 system combina- tion entries. We used the ranking of these …...

We present the Carnegie Mellon Univer- sity Stat-XFER group submission to the WMT 2010 shared translation task. Up- dates to our syntax-based SMT system mainly fell in the areas of new feature for- mulations in the translation model and im- proved filtering of SCFG rules. Compared to our WMT 2009 …...

Unrehearsed spoken language often contains many disfluencies. If we want to correctly interpret the content of spoken language, we need to be able to detect these disfluencies and deal with them appropriately. In the work de- scribed here, we use a statistical noisy channel model to detect disfluencies in transcripts …...

In this work, we propose a novel representa- tion of text based on patterns derived from lin- guistic annotation graphs. We use a subgraph mining algorithm to automatically derive fea- tures as frequent subgraphs from the annota- tion graph. This process generates a very large number of features, many of …...

The NewsViz system aims to enhance news reading experiences by integrating 30 seconds long Flash-animations into news article web pages depicting their content and emotional aspects. NewsViz interprets football match news texts automatically and creates abstract 2D visualizations. The user interface en- ables animators to further refine the anima- tions. …...

This work explores the utility of sentiment and arguing opinions for classifying stances in ide- ological debates. In order to capture arguing opinions in ideological stance taking, we con- struct an arguing lexicon automatically from a manually annotated corpus. We build su- pervised systems employing sentiment and ar- guing opinions …...

Emotion analysis (EA) is a rapidly developing area in computational linguistics. An EA system can be extremely useful in fields such as information retrieval and emotion-driven computer animation. For most EA systems, the number of emotion classes is very limited and the text units the classes are assigned to are …...

We investigate the effect of text summarisa- tion in the problem of rating-inference – the task of associating a fine-grained numerical rating to an opinionated document. We set-up a comparison framework to study the effect of different summarisation algorithms of various compression rates in this task and compare the classification …...

Subtle social information is available in text such as a speaker’s emotional state, intentions, and attitude, but current information extrac- tion systems are unable to extract this infor- mation at the level that humans can. We de- scribe a methodology for creating databases of messages annotated with social information based …...

In this paper we present an evaluation of new techniques for automatically detecting emo- tions in text. The study estimates categorical model and dimensional model for the recogni- tion of four affective states: Anger, Fear, Joy, and Sadness that are common emotions in three datasets: SemEval-2007 “Affective Text”, ISEAR (International …...

This paper describes methods aimed at solv- ing the novel problem of automatically dis- covering ‘wishes’ from (English) documents such as reviews or customer surveys. These wishes are sentences in which authors make suggestions (especially for improvements) about a product or service or show intentions to purchase a product or …...

Emotion cause detection is a new research area in emotion processing even though most theo- ries of emotion treat recognition of a triggering cause event as an integral part of emotion. As a first step towards fully automatic inference of cause-emotion correlation, we propose a text- driven, rule-based approach to …...

Since paraphrasing is one of the crucial tasks in natural language understanding and gener- ation, this paper introduces a novel technique to extract paraphrases for emotion terms, from non-parallel corpora. We present a bootstrap- ping technique for identifying paraphrases, starting with a small number of seeds. Word- Net Affect emotion …...

We explore the task of automatic classifica- tion of texts by the emotions expressed. Our novel method arranges neutrality, polarity and emotions hierarchically. We test the method on two datasets and show that it outperforms the corresponding “flat” approach, which does not take into account the hierarchical informa- tion. The …...

Even though considerable attention has been given to semantic orientation of words and the creation of large polarity lexicons, research in emotion analysis has had to rely on lim- ited and small emotion lexicons. In this pa- per, we show how we create a high-quality, moderate-sized emotion lexicon using Me- …...

We present a system called AESOP that au- tomatically produces affect states associated with characters in a story. This research repre- sents a first step toward the automatic genera- tion of plot unit structures from text. AESOP incorporates several existing sentiment analy- sis tools and lexicons to evaluate the effective- …...

The automatic analysis and classification of text using fine-grained attitude labels is the main task we address in our research. The de- veloped @AM system relies on compositio- nality principle and a novel approach based on the rules elaborated for semantically distinct verb classes. The evaluation of our method on …...

Prompt and knowledgeable responses to cus- tomers’ emails are critical in maximizing cus- tomer satisfaction. Such emails often con- tain complaints about unfair treatment due to negligence, incompetence, rigid protocols, un- friendly systems, and unresponsive personnel. In this paper, we refer to these emails as emo- tional emails. They provide …...