Articles

As more historical texts are digitized, there is interest in applying natural language pro- cessing tools to these archives. However, the performance of these tools is often unsatisfac- tory, due to language change and genre dif- ferences. Spelling normalization heuristics are the dominant solution for dealing with histori- cal texts, …...

In the absence of annotations in the target lan- guage, multilingual models typically draw on extensive parallel resources. In this paper, we demonstrate that accurate multilingual part- of-speech (POS) tagging can be done with just a few (e.g., ten) word translation pairs. We use the translation pairs to establish a …...

We describe an LSTM-based model which we call Byte-to-Span (BTS) that reads text as bytes and outputs span annotations of the form [start, length, label] where start posi- tions, lengths, and labels are separate entries in our vocabulary. Because we operate di- rectly on unicode bytes rather than language- specific …...

We present a simple yet powerful approach to non-factoid answer reranking whereby question-answer pairs are represented by con- catenated distributed representation vectors and a multilayer perceptron is used to compute the score for an answer. Despite its simplicity, our approach achieves state-of-the-art perfor- mance on a public dataset of How …...

Question answering forums are rapidly grow- ing in size with no effective automated abil- ity to refer to and reuse answers already avail- able for previous posted questions. In this paper, we develop a methodology for find- ing semantically related questions. The task is difficult since 1) key pieces of …...

We describe a technique for adding contex- tual distinctions to word embeddings by ex- tending the usual embedding process — into two phases. The first phase resembles existing methods, but also constructs K classifications of concepts. The second phase uses these clas- sifications in developing refined K embed- dings for …...

A key challenge in entity linking is making ef- fective use of contextual information to dis- ambiguate mentions that might refer to differ- ent entities in different contexts. We present a model that uses convolutional neural net- works to capture semantic correspondence be- tween a mention’s context and a proposed …...

Recurrent neural network language models (RNNLM) have recently demonstrated vast potential in modelling long-term dependen- cies for NLP problems, ranging from speech recognition to machine translation. In this work, we propose methods for conditioning RNNLMs on external side information, e.g., metadata such as keywords, description, doc- ument title or topic …...

We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND1 v.1, includes 81,743 unique photos in 20,211 se- quences, aligned to both descriptive (caption) and story language. We establish several strong …...

A simile is a figure of speech comparing two fundamentally different things. Sometimes, a simile will explain the basis of a comparison by explicitly mentioning a shared property. For example, “my room is as cold as Antarc- tica” gives “cold” as the property shared by the room and Antarctica. But …...

In this paper, we study, compare and combine two state-of-the-art approaches to automatic feature engineering: Convolution Tree Ker- nels (CTKs) and Convolutional Neural Net- works (CNNs) for learning to rank answer sentences in a Question Answering (QA) set- ting. When dealing with QA, the key aspect is to encode relational …...

We present a simple algorithm to efficiently train language models with noise-contrastive estimation (NCE) on graphics processing units (GPUs). Our NCE-trained language models achieve significantly lower perplexity on the One Billion Word Benchmark language modeling challenge, and contain one sixth of the parameters in the best single model in Chelba …...

Current approaches to Information Extraction (IE) are capable of extracting large amounts of facts with associated probabilities. Because no current IE system is perfect, complemen- tary and conflicting facts are obtained when different systems are run over the same data. Knowledge Fusion (KF) is the problem of ag- gregating facts …...

Interactive machine translation (IMT) is a method which uses human-computer interac- tions to improve the quality of MT. Tradition- al IMT methods employ a left-to-right order for the interactions, which is difficult to di- rectly modify critical errors at the end of the sentence. In this paper, we propose an …...

Given the limited success of medication in re- versing the effects of Alzheimer’s and other dementias, a lot of the neuroscience research has been focused on early detection, in order to slow the progress of the disease through different interventions. We propose a Natural Language Processing approach applied to de- …...

We introduce the task of cross-lingual lexical entailment, which aims to detect whether the meaning of a word in one language can be in- ferred from the meaning of a word in another language. We construct a gold standard for this task, and propose an unsupervised solu- tion based on …...

INSTANTIATION is a fairly common discourse relation and past work has suggested that it plays special roles in local coherence, in sen- timent expression and in content selection in summarization. In this paper we provide the first systematic corpus analysis of the rela- tion and show that relation-specific features can …...

When translating into a morphologically com- plex language, segmenting the target language can reduce data sparsity, while introducing the complication of desegmenting the system output. We present a method for decoder- integrated desegmentation, allowing features that consider the desegmented target, such as a word-level language model, to be considered throughout …...

We present Emergent, a novel data-set de- rived from a digital journalism project for ru- mour debunking. The data-set contains 300 rumoured claims and 2,595 associated news articles, collected and labelled by journalists with an estimation of their veracity (true, false or unverified). Each associated article is sum- marized into …...

The goal of Event extraction is to extract struc- tured information of events that are of interest from unstructured documents. Existing event extractors for social media suffer from two major problems: lack of context and informal nature. In this paper, instead of conducting event extraction solely on each social media …...