Articles

This paper introduces the novel task of topic coherence evaluation, whereby a set of words, as generated by a topic model, is rated for coherence or interpretability. We apply a range of topic scoring models to the evaluation task, drawing on WordNet, Wikipedia and the Google search engine, and existing …...

The question of how meaning might be ac- quired by young children and represented by adult speakers of a language is one of the most debated topics in cognitive science. Existing semantic representation models are primarily amodal based on information provided by the linguistic input despite ample evidence indi- cating …...

Taxonomies are an important resource for a variety of Natural Language Processing (NLP) applications. Despite this, the current state- of-the-art methods in taxonomy learning have disregarded word polysemy, in effect, devel- oping taxonomies that conflate word senses. In this paper, we present an unsupervised method that builds a taxonomy of …...

In this paper we present an opinion summari- zation technique in spoken dialogue systems. Opinion mining has been well studied for years, but very few have considered its appli- cation in spoken dialogue systems. Review summarization, when applied to real dialogue systems, is much more complicated than pure text-based summarization. …...

For extractive meeting summarization, previ- ous studies have shown performance degrada- tion when using speech recognition transcripts because of the relatively high speech recogni- tion errors on meeting recordings. In this pa- per we investigated using confusion networks to improve the summarization performance on the ASR condition under an unsupervised …...

This paper investigates using prosodic infor- mation in the form of ToBI break indexes for parsing spontaneous speech. We revisit two previously studied approaches, one that hurt parsing performance and one that achieved minor improvements, and propose a new method that aims to better integrate prosodic breaks into parsing. Although …...

Current statistical parsers tend to perform well only on their training domain and nearby gen- res. While strong performance on a few re- lated domains is sufficient for many situations, it is advantageous for parsers to be able to gen- eralize to a wide variety of domains. When parsing document …...

We show that the automatically induced latent variable grammars of Petrov et al. (2006) vary widely in their underlying representations, de- pending on their EM initialization point. We use this to our advantage, combining multiple automatically learned grammars into an un- weighted product model, which gives signif- icantly improved performance …...

Extraction of entities from ad creatives is an important problem that can benefit many com- putational advertising tasks. Supervised and semi-supervised solutions rely on labeled data which is expensive, time consuming, and dif- ficult to procure for ad creatives. A small set of manually derived constraints on fea- ture expectations …...

In this paper, we present an innovative chart mining technique for improving parse cover- age based on partial parse outputs from preci- sion grammars. The general approach of min- ing features from partial analyses is applica- ble to a range of lexical acquisition tasks, and is particularly suited to domain-specific …...

This paper is about interpreting human com- munication in meetings using audio, video and other signals. Automatic meeting recognition and understanding is extremely challenging, since communication in a meeting is sponta- neous and conversational, and involves mul- tiple speakers and multiple modalities. This leads to a number of significant research …...

Mobile devices are becoming the dominant mode of information access despite being cumbersome to input text using small key- boards and browsing web pages on small screens. We present Qme!, a speech-based question-answering system that allows for spoken queries and retrieves answers to the questions instead of web pages. We …...

We present a novel approach to metaphor in- terpretation and a system that produces lit- eral paraphrases for metaphorical expressions. Such a representation is directly transferable to other applications that can benefit from a metaphor processing component. Our method is distinguished from the previous work in that it does not …...

In this paper, we describe an approach based on off-the-shelf parsers and semantic re- sources for the Recognizing Textual Entail- ment (RTE) challenge that can be generally applied to any domain. Syntax is exploited by means of tree kernels whereas lexical se- mantics is derived from heterogeneous re- sources, e.g. …...

We describe tree edit models for representing sequences of tree transformations involving complex reordering phenomena and demon- strate that they offer a simple, intuitive, and effective method for modeling pairs of seman- tically related sentences. To efficiently extract sequences of edits, we employ a tree kernel as a heuristic in …...

In this paper we report a behavioural ex- periment documenting that different lexico- syntactic formulations of the discourse rela- tion of causation are deemed more or less ac- ceptable by different categories of readers. We further report promising results for automati- cally selecting the formulation that is most ap- propriate …...

Hierarchical discourse segmentation is a use- ful technology, but it is difficult to eval- uate. I propose an error measure based on the word error rate of Beeferman et al. (1999). I then show that this new measure not only reliably distinguishes baseline seg- mentations from lexically-informed hierarchi- cal segmentations …...

Machine translation benefits from two types of decoding techniques: consensus decoding over multiple hypotheses under a single model and system combination over hypotheses from different models. We present model combina- tion, a method that integrates consensus de- coding and system combination into a uni- fied, forest-based technique. Our approach makes …...

A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend phrase-based decoding to allow both source and target phrasal discontinuities, which provide better generalization toon unseen data and yield significant improvements a standard phrase-based system (Moses). …...

This paper contributes a formalization of frame-semantic parsing as a structure predic- tion problem and describes an implemented parser that transforms an English sentence into a frame-semantic representation. It finds words that evoke FrameNet frames, selects frames for them, and locates the arguments for each frame. The system uses two …...