Articles

The important mass of textual documents is in perpetual growth and requires strong ap- plications to automatically process informa- tion. Automatic titling is an essential task for several applications: ’No Subject’ e-mails ti- tling, text generation, summarization, and so forth. This study presents an original ap- proach consisting in titling …...

We present an approach to automatically re- cover hidden attributes of scientific articles, such as whether the author is a native English speaker, whether the author is a male or a fe- male, and whether the paper was published in a conference or workshop proceedings. We train classifiers to predict …...

A tree transformation is sensible if the size of each output tree is uniformly bounded by a linear function in the size of the correspond- ing input tree. Every sensible tree transfor- mation computed by an arbitrary weighted ex- tended top-down tree transducer can also be computed by a weighted …...

We present an online learning algorithm for statistical machine translation (SMT) based on stochastic gradient descent (SGD). Under the online setting of rank learning, a corpus-wise loss has to be approximated by a batch lo- cal loss when optimizing for evaluation mea- sures that cannot be linearly decomposed into a …...

Much previous work on Transliteration Mining (TM) was conducted on short parallel snippets using limited training data, and successful methods tended to favor recall. For such methods, increasing training data may impact precision and application on large comparable texts may impact precision and recall. We adapt a state-of-the-art TM technique …...

This paper seeks to close the gap between training algorithms used in statistical machine translation and machine learning, specifically the framework of empirical risk minimization. We review well-known algorithms, arguing that they do not optimize the loss functions they are assumed to optimize when applied to machine translation. Instead, most …...

In a large-scale study of how people find top- ical shifts in written text, 27 annotators were asked to mark topically continuous segments in 20 chapters of a novel. We analyze the re- sulting corpus for inter-annotator agreement and examine disagreement patterns. The re- sults suggest that, while the overall …...

We propose an algorithm to find the best path through an intersection of arbitrarily many weighted automata, without actually perform- ing the intersection. The algorithm is based on dual decomposition: the automata attempt to agree on a string by communicating about fea- tures of the string. We demonstrate the algo- …...

As interest grows in the use of linguistically annotated corpora in research and teaching of foreign languages and literature, treebanks of various historical texts have been developed. We introduce the first large-scale dependency treebank for Classical Chinese literature. De- rived from the Stanford dependency types, it consists of over 32K …...

We propose a new shared task on grading stu- dent answers with the goal of enabling well- targeted and flexible feedback in a tutorial di- alogue setting. We provide an annotated cor- pus designed for the purpose, a precise speci- fication for a prediction task and an associated evaluation methodology. …...

We propose to re-examine the hypothesis that automated metrics developed for MT evalu- ation can prove useful for paraphrase iden- tification in light of the significant work on the development of new MT metrics over the last 4 years. We show that a meta-classifier trained using nothing but recent MT …...

We propose a new segmentation evaluation metric, called segmentation similarity (S), that quantifies the similarity between two segmen- tations as the proportion of boundaries that are not transformed when comparing them us- ing edit distance, essentially using edit dis- tance as a penalty function and scaling penal- ties by segmentation …...

Conditional Random Fields (CRFs) are a pop- ular formalism for structured prediction in NLP. It is well known how to train CRFs with certain topologies that admit exact inference, such as linear-chain CRFs. Some NLP phe- nomena, however, suggest CRFs with more complex topologies. Should such models be used, considering …...

This study aims to infer the social nature of conversations from their content automat- ically. To place this work in context, our moti- vation stems from the need to understand how social disengagement affects cognitive decline or depression among older adults. For this purpose, we collected a comprehensive and naturalistic …...

Most previous research on automated speech scoring has focused on restricted, predictable speech. For automated scoring of unrestricted spontaneous speech, speech proficiency has been evaluated primarily on aspects of pro- nunciation, fluency, vocabulary and language usage but not on aspects of content and topi- cality. In this paper, we explore …...

We present a model for detecting user dis- engagement during spoken dialogue interac- tions. Intrinsic evaluation of our model (i.e., with respect to a gold standard) yields results on par with prior work. However, since our goal is immediate implementation in a sys- tem that already detects and adapts to …...

Most existing theory of structured prediction assumes exact inference, which is often in- tractable in many practical problems. This leads to the routine use of approximate infer- ence such as beam search but there is not much theory behind it. Based on the structured perceptron, we propose a general framework …...

A citing sentence is one that appears in a sci- entific article and cites previous work. Cit- ing sentences have been studied and used in many applications. For example, they have been used in scientific paper summarization, automatic survey generation, paraphrase iden- tification, and citation function classification. Citing sentences that …...

Standard entity clustering systems commonly rely on mention (string) matching, syntactic features, and linguistic resources like English WordNet. When co-referent text mentions ap- pear in different languages, these techniques cannot be easily applied. Consequently, we develop new methods for clustering text men- tions across documents and languages simulta- neously, producing …...

This paper addresses the extraction of event records from documents that describe multi- ple events. Specifically, we aim to identify the fields of information contained in a docu- ment and aggregate together those fields that describe the same event. To exploit the in- herent connections between field extraction and event …...