Proceedings of the conference. Association for Computational Linguistics. Meeting最新文献

Despite sequences being core to NLP, scant work has considered how to handle noisy sequence labels from multiple annotators for the same text. Given such annotations, we consider two complementary tasks: (1) aggregating sequential crowd labels to infer a best single set of consensus annotations; and (2) using crowd annotations as training data for a model that can predict sequences in unannotated text. For aggregation, we propose a novel Hidden Markov Model variant. To predict sequences in unannotated text, we propose a neural approach using Long Short Term Memory. We evaluate a suite of methods across two different applications and text genres: Named-Entity Recognition in news articles and Information Extraction from biomedical abstracts. Results show improvement over strong baselines. Our source code and data are available online.

Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics such as cosine similarity. However, neither categorical nor Gaussian observational distributions used in existing topic models are appropriate to leverage such correlations. In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere. Such a representation is well-suited for directional data. We use a Hierarchical Dirichlet Process for our base topic model and propose an efficient inference algorithm based on Stochastic Variational Inference. This model enables us to naturally exploit the semantic structures of word embeddings while flexibly discovering the number of topics. Experiments demonstrate that our method outperforms competitive approaches in terms of topic coherence on two different text corpora while offering efficient inference.

The phenotypic complexity of Autism Spectrum Disorder motivates the application of modern computational methods to large collections of observational data, both for improved clinical diagnosis and for better scientific understanding. We have begun to create a corpus of annotated language samples relevant to this research, and we plan to join with other researchers in pooling and publishing such resources on a large scale. The goal of this paper is to present some initial explorations to illustrate the opportunities that such datasets will afford.

BLANC is a link-based coreference evaluation metric for measuring the quality of coreference systems on gold mentions. This paper extends the original BLANC ("BLANC-gold" henceforth) to system mentions, removing the gold mention assumption. The proposed BLANC falls back seamlessly to the original one if system mentions are identical to gold mentions, and it is shown to strongly correlate with existing metrics on the 2011 and 2012 CoNLL data.

The definitions of two coreference scoring metrics- B³ and CEAF-are underspecified with respect to predicted, as opposed to key (or gold) mentions. Several variations have been proposed that manipulate either, or both, the key and predicted mentions in order to get a one-to-one mapping. On the other hand, the metric BLANC was, until recently, limited to scoring partitions of key mentions. In this paper, we (i) argue that mention manipulation for scoring predicted mentions is unnecessary, and potentially harmful as it could produce unintuitive results; (ii) illustrate the application of all these measures to scoring predicted mentions; (iii) make available an open-source, thoroughly-tested reference implementation of the main coreference evaluation measures; and (iv) rescore the results of the CoNLL-2011/2012 shared task systems with this implementation. This will help the community accurately measure and compare new end-to-end coreference resolution algorithms.

Vector space models (VSMs) represent word meanings as points in a high dimensional space. VSMs are typically created using a large text corpora, and so represent word semantics as observed in text. We present a new algorithm (JNNSE) that can incorporate a measure of semantics not previously used to create VSMs: brain activation data recorded while people read words. The resulting model takes advantage of the complementary strengths and weaknesses of corpus and brain activation data to give a more complete representation of semantics. Evaluations show that the model 1) matches a behavioral measure of semantics more closely, 2) can be used to predict corpus data for unseen words and 3) has predictive power that generalizes across brain imaging technologies and across subjects. We believe that the model is thus a more faithful representation of mental vocabularies.