Towards Making a Dependency Parser See
We explore whether it is possible to leverage eye-tracking data in an RNN dependency parser (for English) when such information is only available during training, i.e., no aggregated or token-level gaze features are used at inference time. To do so, we train a multitask learning model that parses sentences as sequence labeling and leverages gaze features as auxiliary tasks. Our method also learns to train from disjoint datasets, i.e. it can be used to test whether already collected gaze features are useful to improve the performance on new non-gazed annotated treebanks. Accuracy gains are modest but positive, showing the feasibility of the approach. It can serve as a first step towards architectures that can better leverage eye-tracking data or other complementary information available only for training sentences, possibly leading to improvements in syntactic parsing.
Code (1)
Similar Papers 제목 키워드 기반
Hybrid Oracle: Making Use of Ambiguity in Transition-based Chinese Dependency Parsing
In the training of transition-based dependency parsers, an oracle is used to predict a transition sequence for a sentence and its gold tree. However, the transition system may exhibit ambiguity, that is, there can be mul…
Chinese Dependency ParsingDependency ParsingSentenceDeep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing - A Tale of Two Parsers Revisited
Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, …
Dependency Parsingglobal-optimizationSentenceWord EmbeddingsDeep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing -- A Tale of Two Parsers Revisited
Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, …
Dependency Parsingglobal-optimizationSentenceWord EmbeddingsA System for Multilingual Dependency Parsing based on Bidirectional LSTM Feature Representations
In this paper, we present our multilingual dependency parser developed for the CoNLL 2017 UD Shared Task dealing with {``}Multilingual Parsing from Raw Text to Universal Dependencies{''}. Our parser extends the monolingu…
Dependency ParsingMultilingual Word EmbeddingsWord EmbeddingsMaking Ellipses Explicit in Dependency Conversion for a German Treebank
We present a carefully designed dependency conversion of the German phrase-structure treebank TiGer that explicitly represents verb ellipses by introducing empty nodes into the tree. Although the conversion process uses …