Related papers: Improving a Strong Neural Parser with Conjunction-…
Parsing sentences into syntax trees can benefit downstream applications in NLP. Transition-based parsers build trees by executing actions in a state transition system. They are computationally efficient, and can leverage machine learning to…
While convolutional neural networks (CNNs) have come to match and exceed human performance in many settings, the tasks these models optimize for are largely constrained to the level of individual objects, such as classification and…
Sequence-based neural networks show significant sensitivity to syntactic structure, but they still perform less well on syntactic tasks than tree-based networks. Such tree-based networks can be provided with a constituency parse, a…
While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems. In this…
The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or…
Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…
We present a dependency parser implemented as a single deep neural network that reads orthographic representations of words and directly generates dependencies and their labels. Unlike typical approaches to parsing, the model doesn't…
Since the popularization of BiLSTMs and Transformer-based bidirectional encoders, state-of-the-art syntactic parsers have lacked incrementality, requiring access to the whole sentence and deviating from human language processing. This paper…
We propose two methods of learning vector representations of words and phrases that each combine sentence context with structural features extracted from dependency trees. Using several variations of neural network classifier, we show that…
We investigate the use of different syntactic dependency representations in a neural relation classification task and compare the CoNLL, Stanford Basic and Universal Dependencies schemes. We further compare with a syntax-agnostic approach…
Results of computational complexity exist for a wide range of phrase structure-based grammar formalisms, while there is an apparent lack of such results for dependency-based formalisms. We here adapt a result on the complexity of…
We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs. Since existing attentive models exert attention on the sequential structure, we…
The paper investigates the use of richer syntactic dependencies in the structured language model (SLM). We present two simple methods of enriching the dependencies in the syntactic parse trees used for intializing the SLM. We evaluate the…
This thesis presents a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The parser builds fully connected derivations incrementally, in a single pass from…
Compositionality -- the ability to combine familiar units like words into novel phrases and sentences -- has been the focus of intense interest in artificial intelligence in recent years. To test compositional generalization in semantic…
We reduce phrase-representation parsing to dependency parsing. Our reduction is grounded on a new intermediate representation, "head-ordered dependency trees", shown to be isomorphic to constituent trees. By encoding order information in…
Conventional graph-based dependency parsers guarantee a tree structure both during training and inference. Instead, we formalize dependency parsing as the problem of independently selecting the head of each word in a sentence. Our model…
Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neural network…
We propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic…
Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…