On Parsing as Tagging
- URL: http://arxiv.org/abs/2211.07344v1
- Date: Mon, 14 Nov 2022 13:37:07 GMT
- Title: On Parsing as Tagging
- Authors: Afra Amini, Ryan Cotterell
- Abstract summary: We show how to reduce tetratagging, a state-of-the-art constituency tagger, to shift--reduce parsing.
We empirically evaluate our taxonomy of tagging pipelines with different choices of linearizers, learners, and decoders.
- Score: 66.31276017088477
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: There have been many proposals to reduce constituency parsing to tagging in
the literature. To better understand what these approaches have in common, we
cast several existing proposals into a unifying pipeline consisting of three
steps: linearization, learning, and decoding. In particular, we show how to
reduce tetratagging, a state-of-the-art constituency tagger, to shift--reduce
parsing by performing a right-corner transformation on the grammar and making a
specific independence assumption. Furthermore, we empirically evaluate our
taxonomy of tagging pipelines with different choices of linearizers, learners,
and decoders. Based on the results in English and a set of 8 typologically
diverse languages, we conclude that the linearization of the derivation tree
and its alignment with the input sequence is the most critical factor in
achieving accurate taggers.
Related papers
- Incremental Context-free Grammar Inference in Black Box Settings [17.601446198181048]
Black-box context-free grammar inference is a significant challenge in many practical settings.
We propose a novel method that segments example strings into smaller units and incrementally infers the grammar.
Our approach, named Kedavra, has demonstrated superior grammar quality (enhanced precision and recall), faster runtime, and improved readability through empirical comparison.
arXiv Detail & Related papers (2024-08-29T17:00:38Z) - Lexically Grounded Subword Segmentation [0.0]
We present three innovations in tokenization and subword segmentation.
First, we propose to use unsupervised morphological analysis with Morfessor as pre-tokenization.
Second, we present an method for obtaining subword embeddings grounded in a word embedding space.
Third, we introduce an efficient segmentation algorithm based on a subword bigram model.
arXiv Detail & Related papers (2024-06-19T13:48:19Z) - Greed is All You Need: An Evaluation of Tokenizer Inference Methods [4.300681074103876]
We provide a controlled analysis of seven tokenizer inference methods across four different algorithms and three vocabulary sizes.
We show that for the most commonly used tokenizers, greedy inference performs surprisingly well; and that SaGe, a recently-introduced contextually-informed tokenizer, outperforms all others on morphological alignment.
arXiv Detail & Related papers (2024-03-02T19:01:40Z) - Assessment of Pre-Trained Models Across Languages and Grammars [7.466159270333272]
We aim to recover constituent and dependency structures by casting parsing as sequence labeling.
Our results show that pre-trained word vectors do not favor constituency representations of syntax over dependencies.
occurrence of a language in the pretraining data is more important than the amount of task data when recovering syntax from the word vectors.
arXiv Detail & Related papers (2023-09-20T09:23:36Z) - Towards Unsupervised Recognition of Token-level Semantic Differences in
Related Documents [61.63208012250885]
We formulate recognizing semantic differences as a token-level regression task.
We study three unsupervised approaches that rely on a masked language model.
Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels.
arXiv Detail & Related papers (2023-05-22T17:58:04Z) - Joint Chinese Word Segmentation and Span-based Constituency Parsing [11.080040070201608]
This work proposes a method for joint Chinese word segmentation and Span-based Constituency Parsing by adding extra labels to individual Chinese characters on the parse trees.
Through experiments, the proposed algorithm outperforms the recent models for joint segmentation and constituency parsing on CTB 5.1.
arXiv Detail & Related papers (2022-11-03T08:19:00Z) - Multilingual Extraction and Categorization of Lexical Collocations with
Graph-aware Transformers [86.64972552583941]
We put forward a sequence tagging BERT-based model enhanced with a graph-aware transformer architecture, which we evaluate on the task of collocation recognition in context.
Our results suggest that explicitly encoding syntactic dependencies in the model architecture is helpful, and provide insights on differences in collocation typification in English, Spanish and French.
arXiv Detail & Related papers (2022-05-23T16:47:37Z) - Classifiers are Better Experts for Controllable Text Generation [63.17266060165098]
We show that the proposed method significantly outperforms recent PPLM, GeDi, and DExperts on PPL and sentiment accuracy based on the external classifier of generated texts.
The same time, it is also easier to implement and tune, and has significantly fewer restrictions and requirements.
arXiv Detail & Related papers (2022-05-15T12:58:35Z) - Unsupervised Parsing via Constituency Tests [49.42244463346612]
We propose a method for unsupervised parsing based on the linguistic notion of a constituency test.
To produce a tree given a sentence, we score each span by aggregating its constituency test judgments, and we choose the binary tree with the highest total score.
The refined model achieves 62.8 F1 on the Penn Treebank test set, an absolute improvement of 7.6 points over the previous best published result.
arXiv Detail & Related papers (2020-10-07T04:05:01Z) - 2kenize: Tying Subword Sequences for Chinese Script Conversion [54.33749520569979]
We propose a model that can disambiguate between mappings and convert between the two scripts.
Our proposed method outperforms previous Chinese Character conversion approaches by 6 points in accuracy.
arXiv Detail & Related papers (2020-05-07T10:53:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.