Related papers: On Parsing as Tagging
We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem…
Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has…
We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, we show that adding a parsing paradigm as an…
This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…
There are currently two philosophies for building grammars and parsers -- Statistically induced grammars and Wide-coverage grammars. One way to combine the strengths of both approaches is to have a wide-coverage grammar with a heuristic…
Previous work on English determiners has primarily concentrated on their semantics or scoping properties rather than their complex ordering behavior. The little work that has been done on determiner ordering generally splits determiners…
We present the first supertagging-based parser for LCFRS. It utilizes neural classifiers and tremendously outperforms previous LCFRS-based parsers in both accuracy and parsing speed. Moreover, our results keep up with the best (general)…
We present a family of encodings for sequence labeling dependency parsing, based on the concept of hierarchical bracketing. We prove that the existing 4-bit projective encoding belongs to this family, but it is suboptimal in the number of…
Direct dependency parsing of the speech signal -- as opposed to parsing speech transcriptions -- has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing…
Large language models (LLMs) are increasingly used for text analysis tasks, such as named entity recognition or error detection. Unlike encoder-based models, however, generative architectures lack an explicit mechanism to refer to specific…
We evaluate three leading dependency parser systems from different paradigms on a small yet diverse subset of languages in terms of their accuracy-efficiency Pareto front. As we are interested in efficiency, we evaluate core parsers without…
In this paper we present a new tree-rewriting formalism called Link-Sharing Tree Adjoining Grammar (LSTAG) which is a variant of synchronous TAGs. Using LSTAG we define an approach towards coordination where linguistic dependency is…
The paper defends the notion that semantic tagging should be viewed as more than disambiguation between senses. Instead, semantic tagging should be a first step in the interpretation process by assigning each lexical item a representation…
Automatic speech transcripts are often delivered as unstructured word streams that impede readability and repurposing. We recast paragraph segmentation as the missing structuring step and fill three gaps at the intersection of speech…
In this work, we propose a novel constituency parsing scheme. The model predicts a vector of real-valued scalars, named syntactic distances, for each split position in the input sentence. The syntactic distances specify the order in which…
SYNTAGMA is a rule-based parsing system, structured on two levels: a general parsing engine and a language specific grammar. The parsing engine is a language independent program, while grammar and language specific rules and resources are…
Syntactic parsing is essential in natural-language processing, with constituent structure being one widely used description of syntax. Traditional views of constituency demand that constituents consist of adjacent words, but this poses…
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…
This paper outlines the results of sentence level linguistics based rules for improving part-of-speech tagging. It is well known that the performance of complex NLP systems is negatively affected if one of the preliminary stages is less…
Current State-of-the-Art models in Named Entity Recognition (NER) are neural models with a Conditional Random Field (CRF) as the final network layer, and pre-trained "contextual embeddings". The CRF layer is used to facilitate global…