Coreference resolution systems are typically trained with heuristic loss functions that require careful tuning. In this paper we instead apply reinforcement learning to directly optimize a neural mention-ranking model for coreference evaluation metrics. We experiment with two approaches: the REINFORCE policy gradient algorithm and a rewardrescaled max-margin objective. We find the latter to be ...

Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim. A central property of abstract anaphora is that it establishes a relation between the anaphor embedded in the anaphoric sentence and its (typically non-nominal) antecedent. We propose a mention-ranking model that lear...

A visual-world eye-tracking experiment investigated the influence of order of mention and grammatical role on resolution of ambiguous pronouns in Finnish. According to the first-mention account, general cognitive structure-building processes make the firstmentioned noun phrase the preferred antecedent of an ambiguous pronoun. According to the subject-preference account, the preferred antecedent...

Identifying concepts and relationships in biomedical text enables knowledge to be applied in computational analyses. Many biological natural language processing (BioNLP) projects attempt to address this challenge, but the state of the art still leaves much room for improvement. Progress in BioNLP research depends on large, annotated corpora for evaluating information extraction systems and trai...

As natural language understanding research advances towards deeper knowledge modeling, the tasks become more and more complex: we are interested in more nuanced word characteristics, more linguistic properties, deeper semantic and syntactic features. One such example, explored in this article, is the mention detection and recognition task in the Automatic Content Extraction project, with the go...

First mention of Nomada barcelonensis Cockerell, 1917 for France (Hymenoptera: Apidae: Nomadinae) . - The authors relate here the discovery within Mediterranean fringe metropolitan France, in Var department, a species so far only known from Spain: Cockerell,1917. ecology, biology and morphological description allowing its determination are presented as well conditions capture specimen.

Traditional learning-based coreference resolvers operate by training the mention-pair model for determining whether two mentions are coreferent or not. Though conceptually simple and easy to understand, the mention-pair model is linguistically rather unappealing and lags far behind the heuristic-based coreference models proposed in the pre-statistical NLP era in terms of sophistication. Two ind...