Articles

Automatic assessment of reading ability builds on applying speech recognition tools to oral reading, measuring words correct per minute. This work looks at more fine-grained analysis that accounts for effects of prosodic context using a large corpus of read speech from a literacy study. Experiments show that lower-level readers tend …...

Atypical semantic and pragmatic expression is frequently reported in the language of children with autism. Although this atypicality often manifests itself in the use of unusual or un- expected words and phrases, the rate of use of such unexpected words is rarely directly measured or quantified. In this paper, we …...

We investigate two systems for automatic dis- fluency detection on English and Mandarin conversational speech data. The first system combines various lexical and prosodic fea- tures in a Conditional Random Field model for detecting edit disfluencies. The second system combines acoustic and language model scores for detecting filled pauses through …...

In this paper, we propose a novel Rhetorical Structure Index (RSI) to measure the struc- tural importance of a word or a phrase. Un- like TF-IDF and other content-driven mea- surements, RSI identifies words or phrases that are structural cues in an unstructured doc- ument. We show structurally motivated fea- …...

Social media users who post bullying related tweets may later experience regret, potentially causing them to delete their posts. In this pa- per, we construct a corpus of bullying tweets and periodically check the existence of each tweet in order to infer if and when it becomes deleted. We then …...

This opinion piece proposes that recent ad- vances in opinion detection are limited in the extent to which they can detect important cat- egories of opinion because they are not de- signed to capture some of the pragmatic as- pects of opinion. A component of these is the perspective of …...

Multi-Domain learning assumes that a sin- gle metadata attribute is used in order to di- vide the data into so-called domains. How- ever, real-world datasets often have multi- ple metadata attributes that can divide the data into domains. It is not always apparent which single attribute will lead to the …...

We adapt the popular LDA topic model (Blei et al., 2003) to the representation of stylistic lexical information, evaluating our model on the basis of human-interpretability at the word and text level. We show, in particular, that this model can be applied to the task of inducing stylistic lexicons, and …...

The topic of a document can prove to be use- ful information for Word Sense Disambigua- tion (WSD) since certain meanings tend to be associated with particular topics. This paper presents an LDA-based approach for WSD, which is trained using any available WSD sys- tem to establish a sense per …...

Inspired by robust generalization and adver- sarial learning we describe a novel approach to learning structured perceptrons for part-of- speech (POS) tagging that is less sensitive to domain shifts. The objective of our method is to minimize average loss under random distri- bution shifts. We restrict the possible target distributions …...

We consider the task of tagging Arabic nouns with WordNet supersenses. Three approaches are evaluated. The first uses an expert- crafted but limited-coverage lexicon, Arabic WordNet, and heuristics. The second uses un- supervised sequence modeling. The third and most successful approach uses machine trans- lation to translate the Arabic into …...

We propose a new method for translation ac- quisition which uses a set of synonyms to ac- quire translations from comparable corpora. The motivation is that, given a certain query term, it is often possible for a user to specify one or more synonyms. Using the resulting set of query …...

We present a novel approach for translation model (TM) adaptation using phrase train- ing. The proposed adaptation procedure is ini- tialized with a standard general-domain TM, which is then used to perform phrase training on a smaller in-domain set. This way, we bias the probabilities of the general TM towards …...

We present a simple log-linear reparame- terization of IBM Model 2 that overcomes problems arising from Model 1’s strong assumptions and Model 2’s overparame- terization. Efficient inference, likelihood evaluation, and parameter estimation algo- rithms are provided. Training the model is consistently ten times faster than Model 4. On three large-scale …...

A respelling is an alternative spelling of a word in the same writing system, intended to clarify pronunciation. We introduce the task of automatic generation of a respelling from the word’s phonemic representation. Our ap- proach combines machine learning with lin- guistic constraints and electronic resources. We evaluate our system …...

Dependency analysis relies on morphosyntac- tic evidence, as well as semantic evidence. In some cases, however, morphosyntactic ev- idence seems to be in conflict with seman- tic evidence. For this reason dependency grammar theories, annotation guidelines and tree-to-dependency conversion schemes often differ in how they analyze various syntactic constructions. Most …...

We present a systematic study of the effect of crowdsourced translations on Machine Trans- lation performance. We compare Machine Translation systems trained on the same data but with translations obtained using Amazon’s Mechanical Turk vs. professional translations, and show that the same performance is ob- tained from Mechanical Turk translations …...

Most NLP tools are applied to text that is dif- ferent from the kind of text they were eval- uated on. Common evaluation practice pre- scribes significance testing across data points in available test data, but typically we only have a single test sample. This short paper argues that in …...

Bibliometric measures are commonly used to estimate the popularity and the impact of pub- lished research. Existing bibliometric mea- sures provide “quantitative” indicators of how good a published paper is. This does not nec- essarily reflect the “quality” of the work pre- sented in the paper. For example, when h- …...

In cases in which there is no standard or- thography for a language or language vari- ant, written texts will display a variety of or- thographic choices. This is problematic for natural language processing (NLP) because it creates spurious data sparseness. We study the transformation of spontaneously spelled Egyptian Arabic …...