Articles

This paper studies three techniques that improve the quality of N-best hypotheses through additional regeneration process. Unlike the multi-system consensus ap- proach where multiple translation sys- tems are used, our improvement is achieved through the expansion of the N- best hypotheses from a single system. We explore three different methods …...

We present ParaMetric, an automatic eval- uation metric for data-driven approaches to paraphrasing. ParaMetric provides an ob- jective measure of quality using a collec- tion of multiple translations whose para- phrases have been manually annotated. ParaMetric calculates precision and recall scores by comparing the paraphrases dis- covered by automatic paraphrasing …...

Coordinations in noun phrases often pose the problem that elliptified parts have to be reconstructed for proper semantic inter- pretation. Unfortunately, the detection of coordinated heads and identification of el- liptified elements notoriously lead to am- biguous reconstruction alternatives. While linguistic intuition suggests that semantic criteria might play an important, …...

A noun-compound is a compressed proposition that requires an audience to recover the implicit relationship between two concepts that are expressed as nouns. Listeners recover this relationship by considering the most typical relations afforded by each concept. These relational possibilities are evident at a linguistic level in the syntagmatic patterns …...

We present an automatic method for sense- labeling of text in an unsupervised manner. The method makes use of distributionally similar words to derive an automatically labeled training set, which is then used to train a standard supervised classifier for distinguishing word senses. Experimental results on the Senseval-2 and Senseval-3 …...

In this paper we present a taxonomy of di- alogue moves which describe the actions that students and tutors perform in tutorial dialogue. We are motivated by the need for a categorisation of such actions in order to develop computational models for tutorial dialogue. As such, we build both on …...

Much previous work has investigated weak supervision with HMMs and tag dictionar- ies for part-of-speech tagging, but there have been no similar investigations for the harder problem of supertagging. Here, I show that weak supervision for supertag- ging does work, but that it is subject to severe performance degradation when …...

Latent Semantic Analysis (LSA) is based on the Singular Value Decompo- sition (SVD) of a term-by-document matrix for identifying relationships among terms and documents from co- occurrence patterns. Among the multi- ple ways of computing the SVD of a rectangular matrix X, one approach is to compute the eigenvalue decomposition …...

Our goal is to use natural language proc- essing to identify deceptive and non- deceptive passages in transcribed narra- tives. We begin by motivating an analy- sis of language-based deception that relies on specific linguistic indicators to discover deceptive statements. The indi- cator tags are assigned to a document us- …...

The state-of-the-art system combination method for machine translation (MT) is the word-based combination using confu- sion networks. One of the crucial steps in confusion network decoding is the align- ment of different hypotheses to each other when building a network. In this paper, we present new methods to improve alignment …...

This paper addresses the fundamental problem of document classification, and we focus attention on classification prob- lems where the classes are mutually exclu- sive. In the course of the paper we advo- cate an approximate sampling distribution for word counts in documents, and demon- strate the model’s capacity to outperform …...

In this paper we explore robustness and domain adaptation issues for Word Sense Disambiguation (WSD) using Singular Value Decomposition (SVD) and unlabeled data. We focus on the semi-supervised do- main adaptation scenario, where we train on the source corpus and test on the tar- get corpus, and try to improve …...

VerbNet (VN) is a major large-scale En- glish verb lexicon. Mapping verb instances to their VN classes has been proven use- ful for several NLP tasks. However, verbs are polysemous with respect to their VN classes. We introduce a novel supervised learning model for mapping verb instances to VN classes, …...

Addressing the task of acquiring semantic relations between events from a large cor- pus, we first argue the complementarity be- tween the pattern-based relation-oriented approach and the anchor-based argument- oriented approach. We then propose a two- phased approach, which first uses lexico- syntactic patterns to acquire predicate pairs and then …...

Annotated corpora are only useful if their annotations are consistent. Most large-scale annotation efforts take special measures to reconcile inter-annotator disagreement. To date, however, no-one has investigated how to automatically determine exemplars in which the annotators agree but are wrong. In this paper, we use OntoNotes, a large-scale corpus of …...

This paper proposes an approach using large scale case structures, which are automatically constructed from both a small tagged corpus and a large raw cor- pus, to improve Chinese dependency parsing. The case structure proposed in this paper has two characteristics: (1) it relaxes the predicate of a case structure …...

As human beings, our mental processes for recognising linguistic symbols gen- erate perceptual neighbourhoods around such symbols where confusion errors oc- cur. Such neighbourhoods also pro- vide us with conscious mental associa- tions between symbols. This paper for- malises orthographic models for similarity of Japanese kanji, and provides a proof- …...

In this paper we describe an empirical study of human-human multi-tasking dia- logues (MTD), where people perform mul- tiple verbal tasks overlapped in time. We examined how conversants switch from the ongoing task to a real-time task. We found that 1) conversants use discourse markers and prosodic cues to signal …...

We generalize Uno and Yagiura’s algo- rithm for finding all common intervals of two permutations to the setting of two sequences with many-to-many alignment links across the two sides. We show how to maximally decompose a word-aligned sentence pair in linear time, which can be used to generate all possible …...

Bracketing Transduction Grammar (BTG) is a natural choice for effective integration of desired linguistic knowledge into sta- tistical machine translation (SMT). In this paper, we propose a Linguistically Anno- tated BTG (LABTG) for SMT. It conveys linguistic knowledge of source-side syn- tax structures to BTG hierarchical struc- tures through linguistic …...