A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Improving Neural Parsing by Disentangling Model Combination and Reranking Effects
[article]
2017
arXiv
pre-print
Recent work has proposed several generative neural models for constituency parsing that achieve state-of-the-art results. ...
We then demonstrate that the rescoring results are at least partly due to implicit model combination rather than reranking effects. ...
In this paper, we present experiments to isolate the degree to which each gain occurs for each of two state-of-the-art generative neural parsing models: the Recurrent Neural Network Grammar generative ...
arXiv:1707.03058v1
fatcat:4hm7zlxs7jeupc43efwhjcyt64
Combining Improvements for Exploiting Dependency Trees in Neural Semantic Parsing
[article]
2021
arXiv
pre-print
However, it is unclear whether those methods which exploit such dependency information for semantic parsing can be combined to achieve further improvement and the relationship of those methods when they ...
combine. ...
Combining Improvements for Exploiting
Dependency Trees in Neural Semantic Parsing ...
arXiv:2112.13179v1
fatcat:speapueqczbnrohirakzqxw4fq
Improving Neural Parsing by Disentangling Model Combination and Reranking Effects
2017
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Recent work has proposed several generative neural models for constituency parsing that achieve state-of-the-art results. ...
We then demonstrate that the rescoring results are at least partly due to implicit model combination rather than reranking effects. ...
In this paper, we present experiments to isolate the degree to which each gain occurs for each of two state-of-the-art generative neural parsing models: the Recurrent Neural Network Grammar generative ...
doi:10.18653/v1/p17-2025
dblp:conf/acl/FriedSK17
fatcat:cpifozyuuvcgzamzhtvxz5af7e
CYK Parsing over Distributed Representations
2020
Algorithms
With the recent development of deep learning techniques, several artificial intelligence applications, especially in natural language processing, have combined traditional parsing methods with neural networks ...
These operations are compatible with recurrent neural networks. Preliminary experiments show that D-CYK approximates the original CYK algorithm. ...
The parsing algorithm is based on the CYK method combined with a beam search strategy and applies the neural network component in a second pass to rerank the obtained derivations. Dyer et al. ...
doi:10.3390/a13100262
fatcat:wcovlq4ayjg3nfo4j6fud7eer4
An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing
2020
IEEE Access
In this paper, we empirically evaluate different combinations of neural and non-neural encoders with first-and second-order decoders to thoroughly examine their effect on parsing performance. ...
FIGURE 4 : 4 Average UAS relative to the combination of the non-neural encoder and the first-order decoder. ...
doi:10.1109/access.2020.2974109
fatcat:xinalhfbsrgphnhfwdu3fzifky
Multi-Source Syntactic Neural Machine Translation
2018
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. ...
This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism ...
Related Work
Seq2seq Neural Parsing Using linearized parse trees within sequential frameworks was first done in the context of neural parsing. ...
doi:10.18653/v1/d18-1327
dblp:conf/emnlp/CurreyH18
fatcat:xbfldf3tbzdsfc6zqiwztajzza
Multi-Source Syntactic Neural Machine Translation
[article]
2018
arXiv
pre-print
We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. ...
This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism ...
of neural parsing. ...
arXiv:1808.10267v1
fatcat:4alp7j36u5ehlosve6siuekhse
Probabilistic Graph-based Dependency Parsing with Convolutional Neural Network
2016
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
This paper presents neural probabilistic parsing models which explore up to thirdorder graph-based parsing with maximum likelihood training criteria. ...
Two neural network extensions are exploited for performance improvement. ...
to combine manually specified representations with distributed neural representations as in . ...
doi:10.18653/v1/p16-1131
dblp:conf/acl/ZhangZQ16
fatcat:zvv2likasrc4xoqif35pu6zwwe
Syntactic Analysis of the Sentences of the Russian Language Based on Neural Networks
2015
Procedia Computer Science
The model of Russian language parser based on a combination of neural networks along with extraction of set of parameters which allows to establish relations with the minimal syntactic ambiguity is presented ...
The parse tree of sentence is constructed in the format of Russian National Corpus (RNC). ...
Syntactic analysis of the sentences of the Russian language based on neural networks Sboev A, et. al ...
doi:10.1016/j.procs.2015.11.033
fatcat:gxrdvzeqs5ghpgtumb2b4ksdmy
Parsing with Neural and Finite Automata Networks: A Graph Grammar Approach
2011
International Journal of Computer Applications
In "Parsing with finite automata networks" finite automata are frequently combined using a set of rules for various operations like union, concatenation, and kleene closure; while in "Parsing with neural ...
its validity) for parsing with (i) neural networks and (ii) finite automata networks. ...
neural networks and natural language processing; incremental parsing; and neural networks and recurrent neural networks. ...
doi:10.5120/2878-3747
fatcat:ikw5hpj255acpmuucnd2giv2du
The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization
2015
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
According to the principle of compositionality, the meaning of a sentence is computed from the meaning of its parts and the way they are syntactically combined. ...
Current recursive neural network (RNN) approaches for computing sentence meaning therefore run into a number of practical difficulties, including the need to carefully select a parser appropriate for the ...
Therefore, a good solution is to give 3 An indirect interaction can be set up through pooling. the system a set of parses and let it decide which parse is the best or to combine some of them. ...
doi:10.18653/v1/d15-1137
dblp:conf/emnlp/LeZ15
fatcat:ocbsimdx6zddrb7asnwlxehd6u
A Neural Probabilistic Structured-Prediction Model for Transition-Based Dependency Parsing
2015
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Neural probabilistic parsers are attractive for their capability of automatic feature combination and small data sizes. ...
We propose a neural probabilistic structured-prediction model for transition-based dependency parsing, which integrates search and learning. ...
Related Work Parsing with neural networks. ...
doi:10.3115/v1/p15-1117
dblp:conf/acl/ZhouZHC15
fatcat:vpimiankpfdkjbjxwii4stesh4
Transition-based Dependency Parsing Using Two Heterogeneous Gated Recursive Neural Networks
2015
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Recently, neural network based dependency parsing has attracted much interest, which can effectively alleviate the problems of data sparsity and feature engineering by using the dense features. ...
DAG-GRNN models the feature combinations of the nodes whose dependency relations have not been built yet. ...
Directed Acyclic Graph Structured Gated Recursive Neural Network Previous neural based parsing works feed the extracted features into a standard neural network with one hidden layer. ...
doi:10.18653/v1/d15-1215
dblp:conf/emnlp/ChenZZQH15
fatcat:4jlrld7pxvf4lfcqvzvg25vodm
The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing
[article]
2017
arXiv
pre-print
An ensemble combining our neural semantic parser with an existing, traditional parser, yields a small gain in performance. ...
Although we improve on previous character-based neural semantic parsing models, the overall accuracy is still lower than a state-of-the-art AMR parser. ...
The best result was obtained by combining the different methods. This model was then used to parse the evaluation data. ...
arXiv:1704.02156v2
fatcat:255exme54zhyfbctqhmec6bs4a
Combining Discrete and Continuous Features for Deterministic Transition-based Dependency Parsing
2015
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
We investigate a combination of a traditional linear sparse feature model and a multi-layer neural network model for deterministic transition-based dependency parsing, by integrating the sparse features ...
into the neural model. ...
Directly combining linear and neural features (This) We directly combine linear and neural features (Figure 1(e) ). ...
doi:10.18653/v1/d15-1153
dblp:conf/emnlp/ZhangZ15
fatcat:lwilj6x7fncw7fw7b6h5cyh7m4
« Previous
Showing results 1 — 15 out of 54,556 results