Articles

Current word alignment models for statisti- cal machine translation do not address mor- phology beyond merely splitting words. We present a two-level alignment model that dis- tinguishes between words and morphemes, in which we embed an IBM Model 1 inside an HMM based word alignment model. The model jointly induces …...

There have been many recent investigations into methods to tune SMT systems using large numbers of sparse features. However, there have not been nearly so many examples of helpful sparse features, especially for phrase- based systems. We use sparse features to ad- dress reordering, which is often considered a weak …...

N-gram-based models co-exist with their phrase-based counterparts as an alternative SMT framework. Both techniques have pros and cons. While the N-gram-based frame- work provides a better model that captures both source and target contexts and avoids spurious phrasal segmentation, the ability to memorize and produce larger translation units gives an …...

Standard phrase-based translation models do not explicitly model context dependence be- tween translation units. As a result, they rely on large phrase pairs and target language mod- els to recover contextual effects in translation. In this work, we explore n-gram models over Minimal Translation Units (MTUs) to explic- itly capture …...

In this paper, we propose a multi-step stacked learning model for disfluency detection. Our method incorporates refined n-gram features step by step from different word sequences. First, we detect filler words. Second, edited words are detected using n-gram features ex- tracted from both the original text and filler fil- tered …...

This study focuses on modeling discourse co- herence in the context of automated assess- ment of spontaneous speech from non-native speakers. Discourse coherence has always been used as a key metric in human scoring rubrics for various assessments of spoken lan- guage. However, very little research has been done to …...

Document-level sentiment analysis can bene- fit from fine-grained subjectivity, so that sen- timent polarity judgments are based on the relevant parts of the document. While fine- grained subjectivity annotations are rarely available, encouraging results have been ob- tained by modeling subjectivity as a latent variable. However, latent variable models fail …...

We present a method of improving the perfor- mance of dialog act tagging in identifying mi- nority classes by using per-class feature opti- mization and a method of choosing the class based not on confidence, but on a cascade of classifiers. We show that it gives a minor- ity class …...

Wizard-of-Oz experimental setup in a dia- logue system is commonly used to gather data for informing an automated version of that system. Previous work has exposed depen- dencies between user behavior towards sys- tems and user belief about whether the sys- tem is automated or human-controlled. This work examines whether …...

Twitter has been shown to be a fast and reli- able method for disease surveillance of com- mon illnesses like influenza. However, previ- ous work has relied on simple content anal- ysis, which conflates flu tweets that report infection with those that express concerned awareness of the flu. By discriminating …...

We present the 1.0 release of our para- phrase database, PPDB. Its English portion, PPDB:Eng, contains over 220 million para- phrase pairs, consisting of 73 million phrasal and 8 million lexical paraphrases, as well as 140 million paraphrase patterns, which cap- ture many meaning-preserving syntactic trans- formations. The paraphrases are …...

This paper presents an approach that exploits the scope of negation cues for relation extrac- tion (RE) without the need of using any specif- ically annotated dataset for building a separate negation scope detection classifier. New fea- tures are proposed which are used in two dif- ferent stages. These also …...

Iterative bootstrapping methods are widely employed for relation extraction, especially because they require only a small amount of human supervision. Unfortunately, a phenomenon known as semantic drift can affect the accuracy of iterative bootstrapping and lead to poor extractions. This paper proposes an alternative bootstrapping method, which ranks relation tuples …...

Distant supervision, heuristically labeling a corpus using a knowledge base, has emerged as a popular choice for training relation ex- tractors. In this paper, we show that a sig- nificant number of “negative“ examples gen- erated by the labeling process are false neg- atives because the knowledge base is incom- …...

We propose a novel semantic anno- tation type of assigning truth values to predicate occurrences, and present TruthTeller, a standalone publicly- available tool that produces such annota- tions. TruthTeller integrates a range of semantic phenomena, such as nega- tion, modality, presupposition, implicativ- ity, and more, which were dealt only partly …...

Continuous space language models have re- cently demonstrated outstanding results across a variety of tasks. In this paper, we ex- amine the vector-space word representations that are implicitly learned by the input-layer weights. We find that these representations are surprisingly good at capturing syntactic and semantic regularities in language, and …...

Sentence Similarity [SS] computes a similar- ity score between two sentences. The SS task differs from document level semantics tasks in that it features the sparsity of words in a data unit, i.e. a sentence. Accordingly it is crucial to robustly model each word in a sen- tence to capture …...

Word Sense Disambiguation (WSD) ap- proaches have reported good accuracies in recent years. However, these approaches can be classified as weak AI systems. According to the classical definition, a strong AI based WSD system should perform the task of sense disambiguation in the same manner and with similar accuracy as …...

One way to improve the accuracy of auto- matic speech recognition (ASR) is to use dis- criminative language modeling (DLM), which enhances discrimination by learning where the ASR hypotheses deviate from the uttered sentences. However, DLM requires large amounts of ASR output to train. Instead, we can simulate the output …...

In this paper we leverage methods from sub- modular function optimization developed for document summarization and apply them to the problem of subselecting acoustic data. We evaluate our results on data subset selection for a phone recognition task. Our framework shows significant improvements over random selection and previously proposed methods …...