Syntactic and cognitive issues in investigating gendered coreference
نویسندگان
چکیده
منابع مشابه
Syntactic Parsing for Ranking-Based Coreference Resolution
Recent research efforts have led to the development of a state-of-the-art supervised coreference model, the cluster-ranking model. However, it is not clear whether the features that have been shown to be useful when employed in traditional coreference models will fare similarly when used in combination with this new model. Rather than merely re-evaluate them using the cluster-ranking model, we ...
متن کاملMulti-Lingual Coreference Resolution With Syntactic Features
In this paper, we study the impact of a group of features extracted automatically from machine-generated parse trees on coreference resolution. One focus is on designing syntactic features using the binding theory as the guideline to improve pronoun resolution, although linguistic phenomenon such as apposition is also modeled. These features are applied to the Arabic, Chinese and English corefe...
متن کاملCoreference in Child Russian: Distinguishing Syntactic and Discourse Constraints
(1R) Poka Poohi chital knigu, oni s'el yabloko. while Pooh was reading.imp the book he ate.perf the apple (2R) Poohi s'el yabloko, poka oni chital knigu. Pooh ate.perf the apple while he was reading.imp the book (3R) * Oni s'el yabloko, poka Poohi chital knigu. he ate.perf the apple while Pooh was reading.imp the book (4R) * Poka oni chital knigu, Poohi s'el yabloko. while he was reading.imp th...
متن کاملBasic Issues in Syntactic Parsing
Syntactic parsing is normally conceived as a structural prediction problem, where we map from an input space X of sentences to an output space Y of syntactic representations. In this first lecture, I will discuss different ways of defining the input space (§1), the output space (§2), and the mapping from inputs to outputs (§3). I will then discuss how to evaluate syntactic parsers (§5) and intr...
متن کاملSemantic and Syntactic Features for Dutch Coreference Resolution
We investigate the effect of encoding additional semantic and syntactic information sources in a classification-based machine learning approach to the task of coreference resolution for Dutch. We experiment both with a memory-based learning approach and a maximum entropy modeling method. As an alternative to using external lexical resources, such as the lowcoverage Dutch EuroWordNet, we evaluat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Glossa: a journal of general linguistics
سال: 2019
ISSN: 2397-1835
DOI: 10.5334/gjgl.721