Articles

Distributional semantics creates vector- space representations that capture many forms of semantic similarity, but their re- lation to semantic entailment has been less clear. We propose a vector-space model which provides a formal foundation for a distributional semantics of entailment. Us- ing a mean-field approximation, we de- velop approximate inference …...

Parsing for a wide variety of grammar for- malisms can be performed by intersecting finite tree automata. However, naive im- plementations of parsing by intersection are very inefficient. We present techniques that speed up tree-automata-based pars- ing, to the point that it becomes practically feasible on realistic data when applied …...

We propose a joint formulation for learn- ing task-specific cross-lingual word em- beddings, along with classifiers for that task. Unlike prior work, which first learns the embeddings from parallel data and then plugs them in a supervised learning problem, our approach is one- shot: a single optimization problem com- bines …...

Coarse-grained semantic categories such as supersenses have proven useful for a range of downstream tasks such as question an- swering or machine translation. To date, no effort has been put into integrating the supersenses into distributional word rep- resentations. We present a novel joint em- bedding model of words and …...

We describe and evaluate a simple method to extract parallel sentences from com- parable corpora. The approach, termed STACC, is based on expanded lexical sets and the Jaccard similarity coefficient. We evaluate our system against state-of-the- art methods on a large range of datasets in different domains, for ten language …...

We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints. Our model selects textual units to include in the summary based on a rich set of sparse features whose weights are learned on a large corpus. We allow for the deletion of content within a …...

Distributional semantic models (DSMs) are often evaluated on artificial simi- larity datasets containing single words or fully compositional phrases. We present a large-scale multilingual eval- uation of DSMs for predicting the de- gree of semantic compositionality of nom- inal compounds on 4 datasets for En- glish and French. We build …...

Training neural network language mod- els over large vocabularies is computa- tionally costly compared to count-based models such as Kneser-Ney. We present a systematic comparison of neural strate- gies to represent and train large vocabular- ies, including softmax, hierarchical soft- max, target sampling, noise contrastive es- timation and self normalization. …...

There are numerous studies suggesting that published news stories have an im- portant effect on the direction of the stock market, its volatility, the volume of trades, and the value of individual stocks men- tioned in the news. There is even some published research suggesting that auto- mated sentiment analysis …...

While end-to-end neural machine transla- tion (NMT) has made remarkable progress recently, NMT systems only rely on par- allel corpora for parameter estimation. Since parallel corpora are usually limited in quantity, quality, and coverage, espe- cially for low-resource languages, it is appealing to exploit monolingual corpora to improve NMT. We …...

Morphologically rich languages often lack the annotated linguistic resources required to develop accurate natural language pro- cessing tools. We propose models suitable for training morphological taggers with rich tagsets for low-resource languages without using direct supervision. Our approach extends existing approaches of projecting part-of-speech tags across lan- guages, using bitext …...

For many applications, the query speed of N-gram language models is a computa- tional bottleneck. Although massively par- allel hardware like GPUs offer a poten- tial solution to this bottleneck, exploiting this hardware requires a careful rethink- ing of basic algorithms and data structures. We present the first language model …...

Grapheme-to-phoneme (g2p) models are rarely available in low-resource languages, as the creation of training and evaluation data is expensive and time-consuming. We use Wiktionary to obtain more than 650k word-pronunciation pairs in more than 500 languages. We then develop phoneme and language distance metrics based on phono- logical and linguistic …...

In this work, we focus on the problem of news citation recommendation. The task aims to recommend news citations for both authors and readers to create and search news references. Due to the sparsity issue of news citations and the engineering difficulty in obtaining infor- mation on authors, we focus …...

Community Question Answering (cQA) services like Yahoo! Answers1, Baidu Zhidao2, Quora3, StackOverflow4 etc. provide a platform for interaction with experts and help users to obtain precise and accurate answers to their questions. The time lag between the user posting a question and receiving its answer could be reduced by retrieving …...

Continuous space word embeddings have received a great deal of atten- tion in the natural language processing and machine learning communities for their ability to model term similarity and other relationships. We study the use of term relatedness in the context of query expansion for ad hoc informa- tion retrieval. …...

Different from traditional active learning based on sentence-wise full annotation (FA), this paper proposes active learning with dependency-wise partial annotation (PA) as a finer-grained unit for dependency parsing. At each iteration, we select a few most uncertain words from an unlabeled data pool, manually annotate their syntactic heads, and add …...

We present a new approach for document- level sentiment inference, where the goal is to predict directed opinions (who feels positively or negatively towards whom) for all entities mentioned in a text. To encour- age more complete and consistent predic- tions, we introduce an ILP that jointly models (1) sentence- …...

Sentiment classification aims to automati- cally predict sentiment polarity (e.g., pos- itive or negative) of user generated sen- timent data (e.g., reviews, blogs). Due to the mismatch among different domains, a sentiment classifier trained in one do- main may not work well when directly applied to other domains. Thus, domain …...

Through a particular choice of a predicate (e.g., “x violated y”), a writer can subtly connote a range of implied sentiment and presupposed facts about the entities x and y: (1) writer’s perspective: projecting x as an “antagonist” and y as a “victim”, (2) entities’ perspective: y probably dislikes x, …...