Articles

We present a comparative investigation of word representations for part-of-speech (POS) and morphological tagging, focusing on sce- narios with considerable differences between training and test data where a robust approach is necessary. Instead of adapting the model towards a specific domain we aim to build a robust model across domains. …...

Most of previous work in knowledge base (KB) completion has focused on the problem of relation extraction. In this work, we focus on the task of inferring missing entity type in- stances in a KB, a fundamental task for KB competition yet receives little attention. Due to the novelty of …...

We present a new approach to harvesting a large-scale, high quality image-caption corpus that makes a better use of already existing web data with no additional human efforts. The key idea is to focus on D´ej`a Image-Captions: naturally existing image descriptions that are repeated almost verbatim – by more than …...

We take a novel approach to zero pronoun res- olution in Chinese: our model explicitly tracks the flow of focus in a discourse. Our approach, which generalizes to deictic references, is not reliant on the presence of overt noun phrase antecedents to resolve to, and allows us to ad- dress …...

Gradable terms such as brief, lengthy and ex- tended illustrate varying degrees of a scale and can therefore participate in comparative con- structs. Knowing the set of words that can be compared on the same scale and the associ- ated ordering between them (brief < lengthy < extended) is very …...

In spite of the apparent irregularity of the English spelling system, Chomsky and Halle (1968) characterize it as “near optimal”. We investigate this assertion using computational techniques and resources. We design an al- gorithm to generate word spellings that max- imize both phonemic transparency and mor- phological consistency. Experimental results …...

Context representations are a key element in distributional models of word meaning. In contrast to typical representations based on neighboring words, a recently proposed ap- proach suggests to represent a context of a tar- get word by a substitute vector, comprising the potential fillers for the target word slot in …...

Tree trimming is the problem of extracting an optimal subtree from an input tree, and sentence extraction and sentence compres- sion methods can be formulated and solved as tree trimming problems. Previous ap- proaches require integer linear programming (ILP) solvers to obtain exact solutions. The problem of this approach is …...

We present a simple and yet effective ap- proach that can incorporate rationales elicited from annotators into the training of any off- the-shelf classifier. We show that our sim- ple approach is effective for multinomial na¨ıve Bayes, logistic regression, and support vector machines. We additionally present an active learning method …...

More and more of the information available on the web is dialogic, and a significant por- tion of it takes place in online forum conver- sations about current social and political top- ics. We aim to develop tools to summarize what these conversations are about. What are the CENTRAL PROPOSITIONS …...

Recent years have seen increased interest in text normalization in social media, as the in- formal writing styles found in Twitter and other social media data often cause problems for NLP applications. Unfortunately, most current approaches narrowly regard the nor- malization task as a “one size fits all” task of …...

People vary widely in their temporal orientation—how often they emphasize the past, present, and future—and this affects their finances, health, and happiness. Traditionally, temporal orientation has been assessed by self-report questionnaires. In this paper, we develop a novel behavior-based assessment using human language on Facebook. We first create a past, …...

This paper presents a framework to infer spa- tial knowledge from verbal semantic role rep- resentations. First, we generate potential spa- tial knowledge deterministically. Second, we determine whether it can be inferred and a degree of certainty. Inferences capture that something is located or is not located some- where, and …...

Most modern statistical machine translation systems are based on linear statistical models. One extremely effective method for estimating the model parameters is minimum error rate training (MERT), which is an efficient form of line optimisation adapted to the highly non- linear objective functions used in machine translation. We describe a …...

We present a two-stage framework to parse a sentence into its Abstract Meaning Repre- sentation (AMR). We first use a dependency parser to generate a dependency tree for the sentence. In the second stage, we design a novel transition-based algorithm that trans- forms the dependency tree to an AMR graph. …...

This work focuses on the insensitivity of ex- isting word alignment models to domain dif- ferences, which often yields suboptimal re- sults on large heterogeneous data. A novel latent domain word alignment model is pro- posed, which induces domain-conditioned lexical and alignment statistics. We propose to train the model on …...

structures from which the generation naturally starts often do not contain any func- tional nodes, while surface-syntactic struc- tures or a chain of tokens in a linearized tree contain all of them. Therefore, data-driven linguistic generation needs to be able to cope with the projection between non-isomorphic structures that differ …...

The advent of social media has brought Inter- net memes, a unique social phenomenon, to the front stage of the Web. Embodied in the form of images with text descriptions, little do we know about the “language of memes”. In this paper, we statistically study the correla- tions among popular …...

We present an approach to speech recogni- tion that uses only a neural network to map acoustic input to characters, a character-level language model, and a beam search decoding procedure. This approach eliminates much of the complex infrastructure of modern speech recognition systems, making it possible to di- rectly train …...

A weakly-supervised method is applied to anonymized queries to extract lexical interpre- tations of compound noun phrases (e.g., “for- tune 500 companies”). The interpretations explain the subsuming role (“listed in”) that modifiers (fortune 500) play relative to heads (companies) within the noun phrases. Exper- imental results over evaluation sets of …...