Unsupervised Discourse Constituency Parsing Using Viterbi EM
نویسندگان
چکیده
منابع مشابه
Viterbi Training Improves Unsupervised Dependency Parsing
We show that Viterbi (or “hard”) EM is well-suited to unsupervised grammar induction. It is more accurate than standard inside-outside re-estimation (classic EM), significantly faster, and simpler. Our experiments with Klein and Manning’s Dependency Model with Valence (DMV) attain state-of-the-art performance — 44.8% accuracy on Section 23 (all sentences) of the Wall Street Journal corpus — wit...
متن کاملNeural Discontinuous Constituency Parsing
One of the most pressing issues in discontinuous constituency transition-based parsing is that the relevant information for parsing decisions could be located in any part of the stack or the buffer. In this paper, we propose a solution to this problem by replacing the structured perceptron model with a recursive neural model that computes a global representation of the configuration, therefore ...
متن کاملShallow Discourse Parsing Using Constituent Parsing Tree
This paper describes our system in the closed track of the shared task of CoNLL2015. We formulize the discourse parsing work into a series of classification subtasks. The official evaluation shows that the proposed framework can give competitive results and we give a few discussions over latent improvement as well.
متن کاملK-best Iterative Viterbi Parsing
This paper presents an efficient and optimal parsing algorithm for probabilistic context-free grammars (PCFGs). To achieve faster parsing, our proposal employs a pruning technique to reduce unnecessary edges in the search space. The key is to repetitively conduct Viterbi inside and outside parsing, while gradually expanding the search space to efficiently compute heuristic bounds used for pruni...
متن کاملA Framework for Unsupervised Dependency Parsing using a Soft-EM Algorithm and Bilexical Grammars
Unsupervised dependency parsing is acquiring great relevance in the area of Natural Language Processing due to the increasing number of utterances that become available on the Internet. Most current works are based on Dependency Model with Valence (DMV) [12] or Extended Valence Grammars (EVGs) [11], in both cases the dependencies between words are modeled by using a fixed structure of automata....
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: Transactions of the Association for Computational Linguistics
سال: 2020
ISSN: 2307-387X
DOI: 10.1162/tacl_a_00312